{"id":"d4984c17-ca16-47f6-9493-63c1a734e692","slug":"thinking-framework-skills","kind":"skill","name":"thinking-framework-skills","summary":"Evidence-graded, agent-executable thinking-method skills - 63 frameworks reduced to their working mechanism, honestly graded, and producing a concrete artifact. 63 frameworks + 4 tools + 9 recipes for","owner":"product-on-purpose","repoUrl":"https://github.com/product-on-purpose/thinking-framework-skills","license":"Apache-2.0","licenseTier":"permissive","trust":"community","stars":17,"match":null,"fewStars":false,"format":"skill","createdAt":null,"addedAt":"2026-10-14T06:08:31.044Z","logoUrl":"https://avatars.githubusercontent.com/u/253892650?v=4","linkOnly":false,"collection":null,"skillPath":null,"categories":["developer-tools"],"tags":["agentskills","ai-agents","claude","claude-code","codex","critical-thinking","decision-making","evidence-based"],"runtime":"binary","local":true,"cloudCapable":false,"cloudCapability":"unknown","cloudReadyOnPlatform":false,"needsApiKey":false,"reviewed":false,"syncedAt":"2026-10-14T07:02:07.631Z","sample":false,"url":"https://conduits.dev/tools/thinking-framework-skills","language":"JavaScript","transports":["stdio"],"install":{},"requirements":{"env":[],"upstreamMayCharge":false},"tools":null,"readme":"\n\n# Thinking Framework Skills\n\n**An evidence-graded library of agent-executable thinking-method skills.**\n\nEvery method is reduced to its working mechanism, graded honestly on how strong its evidence actually is, and shipped as a skill that produces a concrete artifact, not prose.\n\n[**What it is**](#-what-this-is)  ·  [**Install**](#-quick-start)  ·  [**Frameworks**](#-the-catalog)  ·  [**Evidence**](#-the-evidence-model)  ·  [**Recipes**](#-recipes)  ·  [**Live site**](https://thinking-framework-skills.productonpurpose.com/)\n\n

\n \"Status:\n \"License:\n \"Version\n \"Conformance\n \"Frameworks:\n \"Tools:\n \"Recipes:\n \"Agent\n \"Evidence-graded\"\n

\n\n---\n\n
\nTable of Contents\n\n- [What this is](#-what-this-is)\n- [Quick start](#-quick-start)\n- [What makes it different](#-what-makes-it-different)\n- [The library at a glance](#-the-library-at-a-glance)\n- [The evidence model](#-the-evidence-model)\n- [The catalog](#-the-catalog)\n- [How a skill works](#-how-a-skill-works)\n- [Recipes](#-recipes)\n- [Find your way in](#-find-your-way-in)\n- [Documentation](#-documentation)\n- [Conformance: what advanced (Gold) tier means](#-conformance-what-advanced-gold-tier-means)\n- [Project status](#-project-status)\n - [At a glance](#at-a-glance) · [Repo structure](#repo-structure) · [Changelog](#changelog)\n- [Contributing](#-contributing)\n- [License](#-license)\n- [About the maintainer](#-about-the-maintainer)\n\n
\n\n---\n\n## 🧠 What this is\n\nAI agents are fluent and fast, and surprisingly weak at the moves that make thinking actually good: reframing a problem before solving the wrong one, separating evidence from inference, imagining how a plan fails before it does, stress-testing a decision from more than one angle. Humans are not much better under time pressure. Both converge too early.\n\n`thinking-framework-skills` packages the durable core of the structured-thinking tradition (decision science, creativity research, systems thinking, foresight, critical thinking) as small, composable, agent-ready skills. Each one helps a person or an agent reframe a problem, generate options, challenge an assumption, trace a consequence, or stress-test a decision, and hands back a usable artifact.\n\nThree things make it different from a list of mental models:\n\n| It is | It is not |\n|---|---|\n| **Mechanism-first** - the durable cognitive move, named for what it does | A museum of trademarked frameworks |\n| **Evidence-graded** - an honest tier (S/M/P/V/A/C/X) on every skill, including \"weaker than people think\" | A confident claim that every method is \"proven\" |\n| **Artifact-producing** - a risk register, an option matrix, an argument map, a Thinking Plan | A set of vibes-y prompts |\n| **Composable** - skills chain into recipes, passing a compressed artifact at each step | A pile of unrelated one-offs |\n| **Honest about misuse** - every skill names where it misleads (\"when NOT to use this\") | A cargo-cult checklist |\n\n**Relationship to [`pm-skills`](https://github.com/product-on-purpose/pm-skills):** sibling library, no technical coupling. `thinking-framework-skills` helps decide *what* to work on and *why* it is sound; `pm-skills` helps execute *how*. They compose; neither depends on the other.\n\n

(back to top)

\n\n---\n\n## ⚡ Quick start\n\n**Claude Code (recommended):**\n\n```bash\n/plugin marketplace add product-on-purpose/agent-plugins\n/plugin install thinking-framework-skills@product-on-purpose\n```\n\nAll 63 frameworks (plus the 4 tools and 9 recipes) become available immediately, invocable by name (for example `/think-premortem`).\n\n**Cross-agent (Cursor, Copilot, Cline, and others via the open [skills CLI](https://github.com/vercel-labs/skills)):**\n\n```bash\nnpx skills add product-on-purpose/thinking-framework-skills\n```\n\n**Clone or download:**\n\n```bash\ngit clone https://github.com/product-on-purpose/thinking-framework-skills.git\n```\n\n**Your first run.** Pick a real decision you are about to commit to, then:\n\n```bash\n/think-premortem \"we're about to launch a free tier to drive signups\"\n```\n\nYou get a ranked **risk register**: for each top risk, a leading signal, a mitigation, an owner, and a kill criterion. That artifact, not a feeling of caution, is the point. You do not need an agent - every skill is a procedure you can run by hand with the template on its page.\n\n**Not sure which framework you need?** Start with the **[Framework Advisor](https://thinking-framework-skills.productonpurpose.com/tools/think-framework-advisor/)**: describe your situation in plain language and it returns a prioritized *Thinking Plan* of which skills to run, in order, and what to skip. It is the front door to everything else.\n\nHow the Framework Advisor fits into your workflow:\n\n```mermaid\n%%{init: {'theme':'base','themeVariables':{'primaryColor':'#eef2ff','primaryBorderColor':'#c7d2fe','lineColor':'#6366f1'}}}%%\nflowchart LR\n sit[\"Your situation
(a prompt)\"]:::in --> adv{\"Framework Advisor
(the front door)\"}:::router\n adv --> plan[\"Thinking Plan
(prioritized, evidence-graded)\"]:::plan\n plan --> s1[\"run skill 1\"]:::skill\n plan --> s2[\"run skill 2\"]:::skill\n s1 --> art[\"Artifact(s):
risk register, option matrix,
argument map\"]:::art\n s2 --> art\n sit -. \"or apply directly\" .-> top3[\"think-top3 /
think-random-frameworks\"]:::skill\n top3 --> art\n classDef in fill:#dcfce7,stroke:#86efac,color:#166534;\n classDef router fill:#ddd6fe,stroke:#a78bfa,color:#4c1d95;\n classDef plan fill:#fef9c3,stroke:#fde047,color:#854d0e;\n classDef skill fill:#eef2ff,stroke:#c7d2fe,color:#3730a3;\n classDef art fill:#e0f2fe,stroke:#7dd3fc,color:#075985;\n```\n\n> 📖 Full walkthrough: [`docs/getting-started.md`](docs/getting-started.md) · Explore the whole library: the [**live site**](https://thinking-framework-skills.productonpurpose.com/).\n\n

(back to top)

\n\n---\n\n## 🔬 What makes it different\n\nThe field of \"thinking methods\" has three uneven layers: a small **empirical core** with replicated study evidence, a large **practitioner ring** of long-standing heuristics with real traction but limited formal validation, and a noisy **outer ring** where popularity and weak evidence get conflated. Most libraries flatten all three into one shiny catalog.\n\nThis one does the opposite, and that honesty is the product:\n\n- **Grade evidence transparently.** Every skill carries a tier, and its dossier states what the research does and does *not* show. A practitioner-tier method labeled honestly is more trustworthy than one dressed up as science.\n- **Do not launder statistics.** The often-cited \"premortems surface ~30% more reasons\" measures the *number of reasons*, not a 30% gain in decision quality. Claims are scoped to what the studies actually measured.\n- **Mechanism over ritual.** The skill implements the durable move and names the branded ritual as lineage, never the reverse. (So the library ships *Parallel Perspectives Review*, not the trademarked Six Thinking Hats.)\n- **Flag transferred evidence.** Almost no studies test an *AI agent* running these methods. Where evidence comes from human-subject research, the page says so.\n\n

(back to top)

\n\n---\n\n## 🗺️ The library at a glance\n\n63 frameworks across 12 cognitive-operation families (56 core plus 7 contested lenses), arranged as a thinking lifecycle. (Four [tools](#-tools-meta-skills) and nine [recipes](#-recipes) ride on top.) You rarely run all twelve; the Framework Advisor picks the few that fit your situation.\n\n```mermaid\n%%{init: {'theme':'base','themeVariables':{'primaryColor':'#eef2ff','primaryBorderColor':'#c7d2fe','lineColor':'#6366f1','fontFamily':'system-ui, sans-serif'}}}%%\nflowchart TB\n classDef frame fill:#e0e7ff,stroke:#6366f1,color:#1e1b4b,font-weight:bold\n classDef gen fill:#dcfce7,stroke:#16a34a,color:#14532d,font-weight:bold\n classDef analyze fill:#fef9c3,stroke:#ca8a04,color:#713f12,font-weight:bold\n classDef decide fill:#ffedd5,stroke:#ea580c,color:#7c2d12,font-weight:bold\n classDef reflect fill:#f3e8ff,stroke:#9333ea,color:#581c87,font-weight:bold\n\n PF[\"1. Problem Framing (6) - frame the real problem\"]:::frame\n DI[\"2. Divergent Ideation (6) - generate options\"]:::gen\n PM[\"3. Perspective & Multi-Lens (2) - see it from other angles\"]:::gen\n SC[\"4. Systems & Consequences (9) - trace consequences\"]:::analyze\n AB[\"5. Assumption & Belief Challenge (5) - challenge assumptions\"]:::analyze\n RC[\"6. Reasoning Clarity (5) - clarify the reasoning\"]:::analyze\n DO[\"7. Decision & Option Evaluation (12) - decide between options\"]:::decide\n SO[\"8. Strategy & Opportunity (2) - test strategy against alternative futures\"]:::decide\n EV[\"9. Ethics & Values Deliberation (4) - weigh the moral trade-off\"]:::decide\n RR[\"10. Risk & Resilience (4) - anticipate what could go wrong\"]:::decide\n SY[\"11. Synthesis (4) - turn inputs into a message\"]:::reflect\n MR[\"12. Meta-Thinking & Reflection (4) - learn and route\"]:::reflect\n\n PF --> DI --> PM --> SC --> AB --> RC --> DO --> SO --> EV --> RR --> SY --> MR\n```\n\n*In text: frame the problem, generate options, see it from other angles, trace consequences, challenge assumptions, clarify the reasoning, decide between options, test strategy against alternative futures, weigh the moral trade-off, anticipate what could go wrong, synthesize, then reflect.* See the full color-coded map (by evidence tier) on the [live site](https://thinking-framework-skills.productonpurpose.com/explore/map/).\n\n

(back to top)

\n\n---\n\n## 🔬 The evidence model\n\nHonest grading is the differentiator, so the key comes **before** the catalog: every skill and every claim is labeled with one of seven tiers, from strongest to weakest.\n\n| Tier | Meaning |\n|---|---|\n| `S` | **Strong** - replicated experimental or meta-analytic support |\n| `M` | **Moderate** - real evidence, but narrower, correlational, or field-based |\n| `P` | **Practitioner** - widely used and defensible, without strong controlled evidence |\n| `V` | **Vendor** - originates from a consultancy or branded methodology |\n| `A` | **Anecdotal** - case reports and testimonials |\n| `C` | **Conceptual** - reasonable, not yet demonstrated |\n| `X` | **Poor/contradictory** - the evidence cuts against it (excluded, documented) |\n\nA few skills carry a **split grade** (for example `M/P` or `S/M`): the mechanism rests on one tier while a specific claim about it rests on another. Where a grade leans on **human-subject** research that has not been tested on an AI agent, the skill's dossier flags that transfer explicitly rather than overclaiming.\n\nA strong-evidence core anchors the library; everything else is honestly labeled around it. The [bibliography](https://thinking-framework-skills.productonpurpose.com/evidence/bibliography/) aggregates the graded sources so a skeptic can trace any claim to its grounding. See [`docs/concepts.md`](docs/concepts.md) for the short version.\n\n

(back to top)

\n\n---\n\n## 📚 The catalog\n\nAll 63 frameworks, by family. **Seven are contested lenses** (SWOT, ACH, Five Whys, Eisenhower/MoSCoW/Pareto, Complexity Domain Sort, Reflective Equilibrium, QCA): famous-but-weak methods graded honestly and shipped caveat-first, explicit-request-only, marked *Contested lens* in their rows. The `Tier` column is the [evidence grade](#-the-evidence-model) defined just above. **Each name links to its full page** - mechanism, numbered procedure, worked example, and graded sources - on the live site. (The routers and applicators are listed under [Tools](#-tools-meta-skills); the chains under [Recipes](#-recipes).)\n\n### Problem Framing - frame the real problem (6)\n\n| Skill | Tier | What it does |\n|---|---|---|\n| [**Problem Restatement**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-problem-restatement/) | `M/P` | Rewrite the problem several ways to expose hidden framing, then pick a more useful one |\n| [**Abstraction Laddering**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-abstraction-laddering/) | `P` | Move up (\"why\") and down (\"how\") the ladder to find the altitude where the problem is workable |\n| [**Contradiction Resolution**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-contradiction-resolution/) | `M/P` | Reframe a trade-off as a contradiction to dissolve via separation in time / space / scale / condition, with an honest exit when it is genuinely real |\n| [**Boundary Critique**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-boundary-critique/) | `C/P` | Audit the boundary judgments behind a frame (who benefits, decides, counts, has standing) in is vs ought, naming who is affected but excluded |\n| [**Frame Creation**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-frame-creation/) | `C/P` | Distil themes and the core paradox, then abduce a new \"as if it were Y\" standpoint and reason forward to solutions |\n| [**Five Whys**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-five-whys/) | `X` | *Contested lens (caveat-first, explicit-request-only).* Reliable only for simple linear single-cause failures and misleading beyond them (Card 2017); leads with that caveat, flags where a problem is multi-cause, and points multi-cause analysis to issue-tree |\n\n### Divergent Ideation - generate options (6)\n\n| Skill | Tier | What it does |\n|---|---|---|\n| [**Morphological Analysis**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-morphological-analysis/) | `P` | Lay out a solution's independent parameters and their possible values as a Zwicky box, then cross-combine and prune to internally consistent configurations |\n| [**Brainwriting**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-brainwriting/) | `S` | Silent, parallel, written idea generation that reliably outperforms verbal brainstorming |\n| [**Far-Analogy Ideation**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-far-analogy-ideation/) | `S` | Transfer solutions from distant domains, which produce more original ideas than near ones |\n| [**SCAMPER**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-scamper/) | `P` | Run an idea through seven transformation prompts to force structured variation |\n| [**Question Burst**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-question-burst/) | `P` | Generate a rapid burst of questions, rank them, and pursue the most catalytic one |\n| [**Assumption Reversal**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-assumption-reversal/) | `P` | Surface the assumptions baked into a problem, negate them, and generate non-obvious reframes |\n\n### Perspective & Multi-Lens - see it from other angles (2)\n\n| Skill | Tier | What it does |\n|---|---|---|\n| [**Role-Storming**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-role-storming/) | `P` | Generate ideas while inhabiting a chosen non-self persona, using the assumed identity to lower self-censorship and shift associations |\n| [**Parallel Perspectives Review**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-parallel-perspectives-review/) | `P` | Examine a decision through several separated lenses in turn, then synthesize a balanced read |\n\n### Systems & Consequences - trace consequences (9)\n\n| Skill | Tier | What it does |\n|---|---|---|\n| [**Three Horizons**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-three-horizons/) | `C` | Hold three time-horizon curves at once - declining present, contested transition, emerging future - and locate the actor in the transition zone |\n| [**Process Tracing**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-process-tracing/) | `P` | Test rival causal explanations of a single case by each piece of evidence's diagnosticity (hoop, smoking-gun, straw-in-the-wind, doubly-decisive tests) |\n| [**Causal Layered Analysis**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-causal-layered-analysis/) | `C` | Read an issue down four layers (litany, system, worldview, myth) and reconstruct a preferred future back up each, anchored by a deliberately changed metaphor |\n| [**Stocks and Flows Reasoning**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-stocks-and-flows-reasoning/) | `S` | Reason explicitly about accumulations and rates, which people systematically misjudge |\n| [**Causal Loop Diagrams**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-causal-loop-diagrams/) | `M/P` | Close and sign the feedback loops (reinforcing or balancing) to read why a system spirals, settles, or oscillates |\n| [**Futures Wheel**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-futures-wheel/) | `P` | Map first-, second-, and third-order consequences radiating from a change |\n| [**Iceberg Model**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-iceberg-model/) | `P` | Move from events down to the patterns, structures, and mental models that produce them |\n| [**Theory of Constraints**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-theory-of-constraints/) | `P` | Find the single binding constraint capping throughput and attach its exploit / subordinate / elevate decisions (the five focusing steps) |\n| [**Qualitative Comparative Analysis (QCA)**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-qualitative-comparative-analysis/) | `P` | *Contested lens (warn-and-redirect, explicit-request-only).* Certifies configurations from noise at session scale (Lucas and Szatrowski 2014); does not build the truth table, it warns and routes to reference-class-forecasting |\n\n### Assumption & Belief Challenge - challenge assumptions (5)\n\n| Skill | Tier | What it does |\n|---|---|---|\n| [**Authentic Dissent**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-authentic-dissent/) | `S` | Cultivate genuine minority disagreement, which improves reasoning where role-played dissent does not |\n| [**Consider the Unknowns**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-consider-the-unknowns/) | `M` | Before committing to a judgment, explicitly list the relevant variables you cannot observe and weigh the gap they leave |\n| [**Ladder of Inference Check**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-ladder-of-inference-check/) | `P` | Trace how you climbed from raw data to conclusion to catch where interpretation crept in |\n| [**Red Team Light**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-red-team-light/) | `P` | A lightweight adversarial pass that attacks a plan to surface its weak points |\n| [**Analysis of Competing Hypotheses (ACH)**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-analysis-of-competing-hypotheses/) | `X` | *Contested lens (warn-and-redirect, explicit-request-only).* Controlled trials found ACH raises confidence without accuracy, so it does not build the matrix as if valid; it leads with that evidence and routes to a better-grounded move |\n\n### Reasoning Clarity - clarify the reasoning (5)\n\n| Skill | Tier | What it does |\n|---|---|---|\n| [**Argument Mapping**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-argument-mapping/) | `S` | Diagram the structure of claims, reasons, and objections to expose where it is weak |\n| [**Argumentation Schemes**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-walton-argumentation-schemes/) | `P` | Identify which stereotyped argument pattern is in play, then test it with that scheme's standard critical questions |\n| [**Natural-Frequency Bayesian Framing**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-natural-frequency-bayesian/) | `S` | Express probabilities as natural frequencies (3 in 1,000) to make conditional reasoning tractable |\n| [**Evidence vs Inference Sort**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-evidence-vs-inference-sort/) | `P` | Separate what is actually known from what is being inferred, and label each |\n| [**Issue Tree**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-issue-tree/) | `P` | Decompose a question into a logical tree of sub-questions to make analysis tractable |\n\n### Decision & Option Evaluation - decide between options (12)\n\n| Skill | Tier | What it does |\n|---|---|---|\n| [**Pairwise Comparison**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-pairwise-comparison/) | `P` | Rank options with no absolute scale by judging every pair head-to-head, deriving the order from the win-counts with a consistency check |\n| [**Dialectical Bootstrapping**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-dialectical-bootstrapping/) | `M` | Make an estimate, assume it is wrong and list why, estimate again from those changed assumptions, then average the two numbers |\n| [**Interest-Based Negotiation**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-interest-based-negotiation/) | `P` | Separate interests from positions, decide against your BATNA inside the mapped ZOPA, and invent options for mutual gain before dividing value |\n| [**Minimax Regret**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-minimax-regret/) | `P` | Choose under deep uncertainty with no probabilities by minimizing the worst-case regret across the states of nature |\n| [**Linear-Model Aggregation**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-linear-model-aggregation/) | `S` | Score options on a simple weighted model that tends to beat holistic judgment |\n| [**Fermi Estimation**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-fermi-estimation/) | `M/P` | Estimate an unknown by decomposing it into order-of-magnitude factors, then multiplying back to a number with a low/high band |\n| [**What Would Have to Be True**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-what-would-have-to-be-true/) | `P` | Turn a claim into the specific conditions that must hold, then test them |\n| [**Decision Option Review**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-decision-option-review/) | `P` | Compare options against weighted criteria with explicit tradeoffs |\n| [**One-Way vs Two-Way Door**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-one-way-vs-two-way-door/) | `P` | Classify a decision by reversibility and match the deliberation cost to it |\n| [**Expected-Value Decision Tree**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-expected-value-decision-tree/) | `P` | Price the uncertainty: a tree of choice and chance nodes, rolled back to an expected value per option, with a what-flips-it note |\n| [**Eisenhower / MoSCoW / Pareto**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-eisenhower-moscow-pareto/) | `P` | *Contested lens (caveat-first, explicit-request-only).* A bundle of three weakly-evidenced prioritization presets; runs the requested one and leads with the laundering caveat (Zhu, Yang and Hsee 2018 measures the urgency bias, not the matrix as a remedy) |\n| [**Complexity Domain Sort**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-complexity-domain-sort/) | `C` | *Contested lens (caveat-first, explicit-request-only).* The descriptively-named Cynefin sort; no controlled validity evidence (PMC 2021) and cargo-cult risk; leads with that caveat plus the Cynefin trademark and names what to do per domain |\n\n### Strategy & Opportunity - test strategy against alternative futures (2)\n\n| Skill | Tier | What it does |\n|---|---|---|\n| [**Scenario Planning**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-scenario-planning/) | `P` | Construct a set of divergent, internally consistent external futures (2x2 critical-uncertainty axes), then robustness-test strategy across them |\n| [**SWOT**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-swot/) | `X` | *Contested lens (caveat-first, explicit-request-only).* Leads with SWOT's weak evidence (Hill and Westbrook 1997), then forces the discipline a bare grid lacks, namely evidence-tagged and prioritized factors plus a TOWS matching step into options |\n\n### Ethics & Values Deliberation - weigh the moral trade-off (4)\n\n| Skill | Tier | What it does |\n|---|---|---|\n| [**Veil-of-Ignorance Reasoning**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-veil-of-ignorance-reasoning/) | `M` | Decide a values trade-off as if you had an equal chance of being any affected party, then return to the actual decision and confront the gap |\n| [**Ethical Matrix**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-ethical-matrix/) | `P` | Grid affected parties (including voiceless ones) against prima facie principles (wellbeing, autonomy, fairness) and read the cell-level pattern of trade-offs |\n| [**Reflective Equilibrium**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-reflective-equilibrium/) | `C` | *Contested lens (caveat-first, explicit-request-only).* Philosophically central but empirically untested as a procedure, with no checkable termination test (Brandt 1979); runs it with an explicit revision ledger and leads with the failure modes |\n| [**Speculative Harms & Anti-Goals**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-speculative-harms-anti-goals/) | `A` | Assume the design succeeds at scale, narrate how it harms third parties and is exploited in bad faith, then convert each harm into an explicit anti-goal |\n\n### Risk & Resilience - anticipate what could go wrong (4)\n\n| Skill | Tier | What it does |\n|---|---|---|\n| [**Premortem**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-premortem/) | `S/M` | Imagine the plan has already failed and work backward to causes, tripwires, and kill criteria |\n| [**Reference Class Forecasting**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-reference-class-forecasting/) | `S` | Estimate from the track record of similar past projects, not inside-view optimism |\n| [**WOOP**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-woop/) | `S` | Wish, Outcome, Obstacle, Plan: mental contrasting plus implementation intentions |\n| [**Backcasting**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-backcasting/) | `P` | Start from a desired future state and work backward to the steps to reach it |\n\n### Synthesis - turn inputs into a message (4)\n\n| Skill | Tier | What it does |\n|---|---|---|\n| [**Contradiction / Tension Mapping**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-contradiction-tension-mapping/) | `C` | Map an interdependent polarity as a both/and - two poles, their upsides and downsides, a greater purpose, warning signs, and action steps - to manage rather than resolve it |\n| [**Concept Mapping**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-concept-mapping/) | `M/P` | Build a labeled-relationship concept network so each link reads as an explicit proposition, surfacing gaps and missing links |\n| [**Affinity Mapping**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-affinity-mapping/) | `P` | Cluster many raw notes into emergent themes from the bottom up |\n| [**Pyramid Principle**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-pyramid-principle/) | `P` | Structure communication as a governing claim over grouped, ordered support |\n\n### Meta-Thinking & Reflection - learn and route (4)\n\n| Skill | Tier | What it does |\n|---|---|---|\n| [**After Action Review**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-after-action-review/) | `S` | Structured review of expected vs actual, and what to change, to improve the next loop |\n| [**Interval Calibration Check**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-interval-calibration-check/) | `P` | Test a stated confidence interval against an equivalent bet, widen until indifferent, then score stated confidence against the actual hit rate |\n| [**Decision Journal**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-decision-journal/) | `P` | Record the decision, rationale, and prediction now to calibrate your judgment later |\n| [**Belief-Update Routine**](https://thinking-framework-skills.productonpurpose.com/frameworks/think-belief-update-routine/) | `P` | Re-score a standing inventory of open beliefs against new evidence on a cadence, with an explicit confidence delta and an under-updating guard |\n\n> Browse them five other ways - by job, by evidence, by artifact, by situation, or on the map - in the site's [Explore](https://thinking-framework-skills.productonpurpose.com/explore/) section. The skills themselves live in [`skills/`](skills/).\n\n

(back to top)

\n\n---\n\n## 🛠️ Tools (meta-skills)\n\nFour skills are **tools**, not thinking methods: they operate *over* the library - routing you to the right framework, applying several at once, or researching new ones. They carry no evidence tier of their own (any grade in a tool's dossier is about the tool's behavior, not a method), and they live under [`/tools/`](https://thinking-framework-skills.productonpurpose.com/tools/) on the site.\n\n| Tool | What it does |\n|---|---|\n| [**Framework Advisor**](https://thinking-framework-skills.productonpurpose.com/tools/think-framework-advisor/) | **Router**, the front door. Describe a situation, get a prioritized Thinking Plan of which frameworks to run, in order, and what to skip. Use it when you do not know which method fits. |\n| [**Top-3**](https://thinking-framework-skills.productonpurpose.com/tools/think-top3/) | **Applicator**. Rank the most relevant frameworks for your topic, apply the top three so each emits its artifact, then cross-synthesize. Use it when you want worked output now, not a plan. |\n| [**Random Frameworks**](https://thinking-framework-skills.productonpurpose.com/tools/think-random-frameworks/) | **Applicator**. Draw three frameworks at random and apply each regardless of fit, to break a frozen or fixated framing. Use it when the obvious lenses are not working. |\n| [**Research Framework**](https://thinking-framework-skills.productonpurpose.com/tools/think-research-framework/) | **Engine**. Research a candidate method, grade its evidence conservatively, and propose a catalog entry for review. This is how the library grows; it never auto-admits. |\n\n**Frameworks, tools, and recipes, in one line:** a *framework* is a single graded thinking method (the 63 in the catalog above); a *tool* helps you choose or apply frameworks (the 4 here); a *recipe* is a fixed chain of frameworks for a recurring job (the 9 below).\n\n

(back to top)

\n\n---\n\n## ⚙️ How a skill works\n\nEach skill is a self-contained unit: a portable `SKILL.md` (the mechanism and procedure), an `evidence/dossier.md` (the graded sources and honest caveats), a `references/EXAMPLE.md` (a worked example that sets the quality bar), and a `skill.meta.yml` sidecar (governance, taxonomy, relationships).\n\n```mermaid\n%%{init: {'theme':'base','themeVariables':{'primaryColor':'#eef2ff','primaryBorderColor':'#c7d2fe','lineColor':'#6366f1','fontFamily':'system-ui, sans-serif'}}}%%\nflowchart LR\n classDef you fill:#1e293b,stroke:#0f172a,color:#fff,font-weight:bold\n classDef skill fill:#4f46e5,stroke:#3730a3,color:#fff,font-weight:bold\n classDef art fill:#166534,stroke:#14532d,color:#fff,font-weight:bold\n\n U[\"You
a messy situation\"]:::you\n S[\"A think- skill
mechanism + procedure\"]:::skill\n A[\"A concrete artifact
risk register, option matrix,
argument map, Thinking Plan\"]:::art\n\n U -- invoke --> S -- produces --> A\n```\n\nWhen you run `/think-premortem \"...\"`, the agent loads the skill, follows its numbered procedure, mirrors the worked example, and produces the artifact. No prompt engineering required. The docs site is a **generated view** of these files; see [`docs/architecture.md`](docs/architecture.md) for how the skills become the site.\n\n

(back to top)

\n\n---\n\n## 🧩 Recipes\n\nRecipes chain several skills into one end-to-end job, passing a compressed artifact at each handoff. Nine ship today:\n\n| Recipe | What it does |\n|---|---|\n| **Kepner-Tregoe** | Find a deviation's cause, choose among defined options, and de-risk the rollout - the rational-process bundle run as a chain of shipped moves |\n| **PDCA / A3** | Root-cause a performance gap, choose and run a countermeasure, then review actual versus expected and standardize or iterate |\n| **Reframe a problem** | Restate the problem, sharpen the question, and check the framing before you build |\n| **Expand options** | Reframe, then generate genuinely new options before judging any |\n| **Stress-test a decision** | Surface what must be true, weigh options, calibrate reversibility, and premortem the plan |\n| **Audit reasoning** | Separate evidence from inference, map the argument, and pressure-test it |\n| **First principles** | Decompose a problem to its fundamentals, then strip the inherited assumptions to rebuild from what is necessary |\n| **Idea-quality audit** | Score a batch of ideas on explicit quality dimensions, then pressure-test the strongest few before committing |\n| **Issue-Position-Argument mapping** | Turn a tangled multi-question deliberation or transcript into a typed map - the open issues, the rival positions on each, and the arguments for and against |\n\nBrowse them on the [live site](https://thinking-framework-skills.productonpurpose.com/recipes/) or in [`_workflows/`](_workflows/).\n\n

(back to top)

\n\n---\n\n## 🧭 Find your way in\n\n| If you want to... | Start here |\n|---|---|\n| Get unstuck or decide, now | The [**Framework Advisor**](https://thinking-framework-skills.productonpurpose.com/tools/think-framework-advisor/) - describe your situation, get a plan |\n| See real decisions worked prompt-to-artifact (incl. the cross-library tfs -> pm-skills handoff) | The [**Showcase**](https://thinking-framework-skills.productonpurpose.com/showcase/) |\n| See one quick worked example of every framework | The [**Samples**](https://thinking-framework-skills.productonpurpose.com/samples/) shelf |\n| Browse by the job you need done | [Explore by job](https://thinking-framework-skills.productonpurpose.com/explore/by-job/) |\n| See only the strong-evidence methods | [Explore by evidence](https://thinking-framework-skills.productonpurpose.com/explore/by-evidence/) |\n| Filter by your situation, live | The [interactive chooser](https://thinking-framework-skills.productonpurpose.com/explore/chooser/) |\n| Learn good thinking, beginner to advanced | The [learning tracks](https://thinking-framework-skills.productonpurpose.com/learn/) |\n| Check the claims | The [evidence and bibliography](https://thinking-framework-skills.productonpurpose.com/evidence/bibliography/) |\n| Build with or extend the library | [`docs/`](docs/) and [`docs/contributing.md`](docs/contributing.md) |\n| Something went wrong | [`docs/troubleshooting.md`](docs/troubleshooting.md), keyed to the actual error text |\n\n

(back to top)

\n\n---\n\n## 📖 Documentation\n\n- **[Live site](https://thinking-framework-skills.productonpurpose.com/)** - the full, searchable, interactive experience (per-framework pages, learning tracks, explorers, the bibliography, the [Showcase](https://thinking-framework-skills.productonpurpose.com/showcase/) and per-framework [Samples](https://thinking-framework-skills.productonpurpose.com/samples/)). This is the home for *using* the library.\n- **[`docs/`](docs/)** - the repo-browser and contributor layer: [architecture](docs/architecture.md), [concepts](docs/concepts.md), [contributing](docs/contributing.md), [conformance](docs/conformance.md), [troubleshooting](docs/troubleshooting.md), the [authoring loop](docs/internal/AUTHORING.md), and the [release process](docs/internal/release-process.md).\n- **[`skills/`](skills/)** - the frameworks themselves (the source of truth the site renders).\n\n

(back to top)

\n\n---\n\n## 🥇 Conformance: what advanced (Gold) tier means\n\nThis plugin is built to the [agent-skills-toolkit](https://github.com/product-on-purpose/agent-skills-toolkit) **Advanced Skill Library Standard**, which grades a skill library on three tiers. Each tier includes everything below it:\n\n| Tier | Name | What it certifies |\n|---|---|---|\n| 🥇 | **Advanced (Gold)** | The plugin proves itself - it ships CI that runs the Standard's own validators against it and passes (self-hosting), generates its `INDEX.md` and native manifests from a single authored source, and maintains release notes and a deprecation policy. |\n| 🥈 | **Convergent (Silver)** | The plugin declares its agent targets and emits each higher-order component (commands, workflows, chain contracts) correctly for both Claude Code and Codex, with a manifest that matches what is on disk. |\n| 🥉 | **Universal (Bronze)** | The skills are portable - valid frontmatter, an `AGENTS.md`, a manifest, references one level deep - so the identical files run on any agentskills.io-compatible agent. |\n\n`thinking-framework-skills` validates at **advanced (Gold) with 0 errors against Standard 0.8**, the version it declares (`library.json` sets `\"standard\": \"0.8\"`). [`.github/workflows/ci.yml`](.github/workflows/ci.yml) pins the exact toolkit commit CI grades with, and that commit is deliberately **newer** than the declared Standard.\n\n**Two dials, and the difference matters.** The *pinned toolkit* is which validator runs. The *declared Standard* is which version of the rules the library holds itself to. Running a newer validator against an older declared Standard is supported by design: findings from rules introduced after 0.8 are held at `warn` rather than counted as failures. That is why the run reports **0 errors and 90 warnings**, not 90 failures.\n\n**What those warnings are, because a number without an explanation is not a disclosure.**\n\n- **83 are post-0.8 documentation requirements** (`G8` folder READMEs, `G7` docs frontmatter, `G10` Diataxis coverage), introduced at Standard 0.10 and later. They are real work the library has not done, held at `warn` by the declared-version ceiling. Measured: declaring 0.13 instead returns convergent with 84 errors, which is why adopting it is a deliberate project rather than a version bump.\n- **7 are `U5`** (description quality) on the seven [contested lenses](#-the-catalog), and they score low for the reason those skills exist: their descriptions lead with an evidence caveat instead of a trigger phrase, which a heuristic tuned for discoverability penalizes. The library keeps the caveat and carries the warnings rather than rewording seven descriptions to score better than they deserve.\n\nThe error count is the number that gates, and it is zero. (For the record: the run was `0 errors, 0 warnings` through v0.10.0, became `0 errors, 7 warnings` when the contested lenses shipped in v0.11.0, and became `0 errors, 128 warnings` when the toolkit pin moved forward in v0.13.x, became `0 errors, 129 warnings` when the troubleshooting page shipped without taxonomy frontmatter, and became `0 errors, 90 warnings` when the `G9` docblock sweep paid off all 39 source-docblock warnings.)\n\nThe Standard itself moves faster than this library re-pins, and that is a deliberate choice rather than an oversight: re-pinning is a release-sized decision here, so the tier claim above always names the Standard version it holds at rather than implying the newest one. Graded against a newer Standard, the result will differ until the next re-pin. Concretely, it earns Gold through:\n\n- **Self-hosting CI that passes.** Every pull request runs [`scripts/check.mjs`](scripts/check.mjs) (the Standard's validators) via [`.github/workflows/ci.yml`](.github/workflows/ci.yml), and `check` is a required status check on `main`. The same one command reproduces the result locally.\n- **Generated INDEX and manifests.** [`INDEX.md`](INDEX.md), `.claude-plugin/plugin.json`, the Codex manifest, and `manifest.generated.json` are all generated from the authored [`library.json`](library.json) and drift-checked; a hand-edit is a CI error.\n- **Curated release notes.** [`RELEASE-NOTES.md`](RELEASE-NOTES.md) is maintained separately from the technical [`CHANGELOG.md`](CHANGELOG.md).\n- **Deprecation policy** and all Bronze and Silver requirements, by inclusion.\n\nTwo Gold checks are **not applicable** here, and the library says so rather than papering over it: **hook documentation** and **chain/hook eval coverage** apply only to plugins that ship hooks or chained components. This library ships neither - its recipes are workflow chains of independent skills, not runtime chain contracts - so those checks pass vacuously. Every skill still carries its own `eval/cases.md`.\n\n> Full breakdown, check by check: [`docs/conformance.md`](docs/conformance.md) (also the canonical list of all `check.mjs` gate layers and how they relate to the Standard's G1-G7 Gold requirements). The Standard itself: [agent-skills-toolkit / STANDARD.md](https://github.com/product-on-purpose/agent-skills-toolkit/blob/main/STANDARD.md).\n\n

(back to top)

\n\n---\n\n## 📊 Project status\n\n`v0.13.0` - **public and growing.** The library grows additively, and evidence grades are refreshed as the research does. User-facing highlights live in [`RELEASE-NOTES.md`](RELEASE-NOTES.md); the full technical history is in [`CHANGELOG.md`](CHANGELOG.md).\n\n### At a glance\n\n| | |\n|---|---|\n| **Current version** | [v0.13.0](https://github.com/product-on-purpose/thinking-framework-skills/releases/tag/v0.13.0) |\n| **Frameworks** | 63, across 12 cognitive-operation families (56 core + 7 contested lenses) |\n| **Tools** | 4 meta-skills (a router, two applicators, the research engine) |\n| **Recipes** | 9 (skill chains shipped as workflow components) |\n| **Conformance** | [advanced (Gold)](#-conformance-what-advanced-gold-tier-means) at Standard 0.8 - **0 errors**, 90 non-gating warnings (83 post-0.8 docs rules held at warn, 7 caveat-first lenses), self-hosting CI |\n| **Evidence** | 11 skills at `S` / `S-M` tier; every skill graded and sourced |\n| **Spec** | [agentskills.io](https://agentskills.io/specification) |\n| **License** | [Apache-2.0](LICENSE) |\n| **Docs site** | [thinking-framework-skills.productonpurpose.com](https://thinking-framework-skills.productonpurpose.com/) |\n| **Install** | `/plugin install thinking-framework-skills@product-on-purpose` |\n\n### Repo structure\n\n```\nthinking-framework-skills/\n├── skills/ # 63 frameworks + 4 tools (the source of truth)\n├── frameworks/ # registry.mjs (the catalog) + per-method dossiers\n│ └── think-/ # SKILL.md, evidence/dossier.md, references/, eval/cases.md, skill.meta.yml\n├── _workflows/ # Recipe definitions (multi-skill chains) as workflow components\n├── recipes/ # Human-readable recipe write-ups\n├── scripts/ # gen-site, gen-manifest, gen-recommendable, and the check.mjs gate\n├── site/ # Astro Starlight docs site (a generated view of skills/)\n├── docs/ # Contributor and build docs\n│ └── internal/ # AUTHORING.md, specs/, release-plans/, research/\n├── .github/workflows/ # CI: the self-hosting conformance gate + Pages deploy\n├── library.json # Authored manifest (the canonical component index)\n├── INDEX.md # Generated catalog index (drift-checked)\n├── CHANGELOG.md # Technical version history\n├── RELEASE-NOTES.md # Curated, user-facing release highlights\n└── AGENTS.md # Universal agent-discovery file\n```\n\n| Path | What's in it |\n|---|---|\n| [`skills/`](skills/) | All 63 frameworks + 4 tools, each a self-contained unit (the site renders from these) |\n| [`frameworks/`](frameworks/) | `registry.mjs` (the single-source-of-truth catalog of 135 evaluated methods) + per-method dossiers |\n| [`_workflows/`](_workflows/) | The 9 recipes as workflow components - ordered skill chains with handoffs |\n| [`scripts/`](scripts/) | Generators (site, manifests, name-safety set) and [`check.mjs`](scripts/check.mjs), the conformance gate |\n| [`docs/`](docs/) | [Getting started](docs/getting-started.md), [architecture](docs/architecture.md), [concepts](docs/concepts.md), [contributing](docs/contributing.md), [conformance](docs/conformance.md) |\n| [`docs/internal/`](docs/internal/) | The [authoring loop](docs/internal/AUTHORING.md), specs, [release plans](docs/internal/release-plans/), and research |\n\n### Changelog\n\nFull detail in [`CHANGELOG.md`](CHANGELOG.md); curated highlights in [`RELEASE-NOTES.md`](RELEASE-NOTES.md).\n\n
\nRelease history\n\n| Version | Highlights |\n|---|---|\n| [**0.13.0**](https://github.com/product-on-purpose/thinking-framework-skills/releases/tag/v0.13.0) | Eval-harness orchestration: a finalize step that writes both scorecard artifacts in one go, a new 14th conformance-gate layer enforcing that every eval scorecard stays a paired `.md` + `.json` (closing #95), plus the v0.12.0 CI-guard hardening follow-ups. No new skills; catalog stays 56 core + 7 contested. |\n| [**0.12.0**](https://github.com/product-on-purpose/thinking-framework-skills/releases/tag/v0.12.0) | Docs platform: a changelog on the site (What's new + full history), the documentation audit acted on (trust page at 63 skills, a contested-lens FAQ, compound grades defined), eight comprehension diagrams, and four new CI guards taking the conformance gate from 9 to 13 layers. No new skills; catalog stays 56 core + 7 contested. |\n| [**0.11.0**](https://github.com/product-on-purpose/thinking-framework-skills/releases/tag/v0.11.0) | Contested lenses: seven famous-but-weak frameworks (SWOT, ACH, Five Whys, Eisenhower/MoSCoW/Pareto, a descriptively-named Cynefin sort, Reflective Equilibrium, QCA) ship as low-tier, caveat-first, explicit-request-only skills, enforced by a new 9th gate layer (`check-contested.mjs`); catalog 56 -> 63 (56 core + 7 contested, separate cohorts). Trigger eval 0 false-fires, output 100%. |\n| [**0.10.0**](https://github.com/product-on-purpose/thinking-framework-skills/releases/tag/v0.10.0) | Learn-by-example depth + agent discovery: a worked example for every framework (the samples shelf, coverage 56/56), a cross-library Showcase that hands off to pm-skills (tfs decides, pm-skills delivers), `llms.txt` linked + `llms-full.txt` added, both behavioral evals refreshed across the full 56-skill catalog, and `red-team-light` re-graded P -> M. No new frameworks; catalog stays 56. |\n| [**0.9.0**](https://github.com/product-on-purpose/thinking-framework-skills/releases/tag/v0.9.0) | Discoverable by agents: a generated, drift-gated `llms.txt` index plus `catalog.json` (the 69 invokable skills/tools/recipes with routing and chaining fields) and `evaluated.json` (all 135 graded methods) at the site root, so other agents can find and route to the library; bundles the post-v0.8.0 measurement loop and example-coverage ratchet. No new skills; catalog stays 56. |\n| [**0.8.0**](https://github.com/product-on-purpose/thinking-framework-skills/releases/tag/v0.8.0) | Learn by example: a Showcase of 16 real decisions worked prompt-to-artifact (a founder, an engineer, a policy analyst), an operating guide, a prompt gallery, and a \"Does this actually work?\" page publishing the behavioral-eval numbers (99% routing with 0 false-fires; 99% of output checks). Documentation and trust; catalog unchanged at 56. |\n| [**0.7.1**](https://github.com/product-on-purpose/thinking-framework-skills/releases/tag/v0.7.1) | Framework Library complete: every documented-not-shipped method now has a published dossier (45 -> 75), documenting settled verdicts with honest sourced research. Documentation-only patch; no catalog count change. |\n| [**0.7.0**](https://github.com/product-on-purpose/thinking-framework-skills/releases/tag/v0.7.0) | Behavioral evals land (routing: 99% top-1, 0 false-fires; artifact quality: 99% checks pass); the four flagged skills tightened by construction; catalog grows 47 -> 56 with a new Ethics & Values Deliberation family (9 Build / 7 Fold / 1 Recipe / 13 Reject from 30 candidates). |\n| [**0.6.0**](https://github.com/product-on-purpose/thinking-framework-skills/releases/tag/v0.6.0) | Catalog grows 40 -> 47 with 7 survivors of a 26-candidate research sweep; `AGENTS.md` roster tables generated and drift-checked; published Framework Library grows 8 -> 25 dossiers. |\n| [**0.5.0**](https://github.com/product-on-purpose/thinking-framework-skills/releases/tag/v0.5.0) | Catalog grows 37 -> 40 (Theory of Constraints, Expected-Value Decision Tree, Scenario Planning); 7-candidate shortlist fully reconciled; Strategy & Opportunity family intro added. |\n| [**0.4.0**](https://github.com/product-on-purpose/thinking-framework-skills/releases/tag/v0.4.0) | The Framework Library platform: registry as single source of truth with strong CI, the research-framework engine, Top-3 and Random-Frameworks applicators, published Framework Library dossiers, a `/tools/` section separating meta-skills from graded frameworks, and the advisor's calibrated routing gate. |\n| [**0.3.0**](https://github.com/product-on-purpose/thinking-framework-skills/releases/tag/v0.3.0) | The advisor-credibility milestone: behavioral eval cases enforced in CI, and advisor corpus enrichment (anti-triggers, when-not, overlaps). Plus the Belief-Update Routine framework and an idea-quality-audit recipe. |\n| [**0.2.0**](https://github.com/product-on-purpose/thinking-framework-skills/releases/tag/v0.2.0) | Catalog grows 31 to 34; Gold-tier hardening with a self-hosting conformance gate in CI, a generated `INDEX.md`, and `RELEASE-NOTES.md`. Tier declared `advanced`. |\n| [**0.1.0**](https://github.com/product-on-purpose/thinking-framework-skills/releases/tag/v0.1.0) | First public release: 31 evidence-graded, agent-executable skills + 4 composable recipes, validating at convergent (Silver). The `think-framework-advisor` front-door router. A full Astro Starlight docs site. Listed in the Product on Purpose marketplace. |\n\n
\n\n

(back to top)

\n\n---\n\n## 🤝 Contributing\n\nContributions, ideas, and framework proposals are welcome. The bar is deliberately high - it is what keeps the library trustworthy.\n\n**A new framework must clear the selection bar.** It has to:\n\n1. Add a **distinct, durable cognitive move** - not duplicate one already shipped. The overlap ceiling is real: candidates that reduce to an existing skill are rejected or become recipes.\n2. Carry an **honest evidence grade** with a dossier of graded sources, including what the research does *not* show.\n3. Produce a **concrete artifact**, not prose.\n4. State **when *not* to use it.**\n\n**To propose or build one:**\n\n1. Open an issue describing the move and its evidence - the fastest way to get feedback before you build.\n2. Read [`docs/contributing.md`](docs/contributing.md) and the per-skill authoring loop in [`docs/internal/AUTHORING.md`](docs/internal/AUTHORING.md).\n3. Mirror an existing skill's 5-file structure (`SKILL.md`, `evidence/dossier.md`, `references/`, `eval/cases.md`, `skill.meta.yml`).\n4. Run the conformance gate locally (`node scripts/check.mjs`) before opening a PR; CI runs the same gate.\n\nDiagrams follow the pm-skills `utility-mermaid-diagrams` house style. Commit with [Conventional Commits](https://www.conventionalcommits.org/).\n\n

(back to top)

\n\n---\n\n## 📄 License\n\nDistributed under the **[Apache License 2.0](LICENSE)**. In short: you may use this library commercially, modify and redistribute it, use it privately, and include it in proprietary software. The only requirements are attribution and including the license notice.\n\n**On method names and trademarks.** Names that are trademarks or carry specific licenses remain the property of their owners. This library implements the underlying cognitive *mechanisms*, names them descriptively, and notes lineage and attribution in each skill's references rather than claiming the brands.\n\n

(back to top)

\n\n---\n\n## 👋 About the maintainer\n\n\"Maintained\n\nBuilt and maintained by **Jonathan Prisant** ([@jprisant](https://github.com/jprisant)), a product leader who thinks in systems and gets unreasonably excited about understanding and solving problems. `thinking-framework-skills` is the reasoning sibling to [`pm-skills`](https://github.com/product-on-purpose/pm-skills): one helps you decide *what* to work on and *why* it is sound, the other helps you execute *how*.\n\n*If this library has sharpened a decision, or saved you from a bad one, consider starring the repo and sharing it with your team.*\n\n

\n Built with purpose by Product on Purpose
\n Evidence-graded thinking, packaged as skills your agent can actually run\n

\n\n
Back to top ↑
\n"}