{"id":"e99ca050-2317-4f7f-83d8-7d46d9906b9c","slug":"decision-map","kind":"skill","name":"decision-map","summary":"Installable Agent Skill and open protocol for mapping complex business, product, and go-to-market decisions into testable options and cascade logs.","owner":"markoblogo","repoUrl":"https://github.com/markoblogo/decision-map","license":"MIT","licenseTier":"permissive","trust":"community","stars":1,"match":null,"fewStars":true,"format":"skill","createdAt":"2026-04-30T10:03:21.000Z","addedAt":"2026-10-21T10:57:54.299Z","logoUrl":"https://avatars.githubusercontent.com/u/220744937?u=3aba3b4ff3cb4a89c430b424b49a6658d9bffb14&v=4","linkOnly":false,"collection":null,"skillPath":null,"categories":["data-analytics"],"tags":["ai","ai-tools","business-strategy","decision-making","decision-support","go-to-market","llm","market-strategy"],"runtime":"binary","local":true,"cloudCapable":false,"cloudCapability":"unknown","cloudReadyOnPlatform":false,"needsApiKey":false,"reviewed":false,"syncedAt":"2026-10-26T07:51:21.328Z","sample":false,"url":"https://conduits.dev/tools/decision-map","language":"Python","transports":["stdio"],"install":{},"requirements":{"env":[],"upstreamMayCharge":false},"tools":null,"readme":"# DecisionMap\n\n![DecisionMap Logo](DesMaps.png)\n\n[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)\n[![GitHub stars](https://img.shields.io/github/stars/markoblogo/decision-map?style=social)](https://github.com/markoblogo/decision-map/stargazers)\n[![Last commit](https://img.shields.io/github/last-commit/markoblogo/decision-map)](https://github.com/markoblogo/decision-map/commits/main)\n[![Schema validation](https://github.com/markoblogo/decision-map/actions/workflows/validate-examples.yml/badge.svg)](https://github.com/markoblogo/decision-map/actions/workflows/validate-examples.yml)\n[![Latest release](https://img.shields.io/github/v/release/markoblogo/decision-map)](https://github.com/markoblogo/decision-map/releases/latest)\n\n**DecisionMap is a practical protocol for turning complex business, product, market, and marketing decisions into visible strategy maps.**\n\nIt is an installable Agent Skill, an open protocol, and a prompt toolkit. It is not a hosted service or a substitute for leadership judgment.\n\n## Try It in 60 Seconds\n\nInstall the skill for Codex or another supported coding agent:\n\n```bash\nnpx skills add markoblogo/decision-map --skill decision-map\n```\n\nThen ask:\n\n> Use DecisionMap to map this decision: [decision]. Compare realistic options, expose the assumptions, and tell me what evidence would change the recommendation.\n\nThe skill is self-contained. The protocol, schemas, and worked examples in this repository provide deeper guidance and machine-readable outputs.\n\n## What It Is\n\nUse DecisionMap when the real problem is not a lack of ideas, but a messy decision with multiple plausible paths, asymmetric risks, and uncertain external reactions.\n\nDecisionMap helps users:\n- restate the real decision\n- separate facts, assumptions, interpretations, and unknowns\n- generate 3-7 distinct strategic options\n- compare trade-offs, risks, resources, and breakpoints\n- pressure-test shortlisted options\n- keep an update loop alive through a cascade log\n\nThe main output is a **working strategic hypothesis**, not a final truth.\n\n## Scope\n\nDecisionMap is designed for:\n- business strategy\n- product strategy\n- market positioning\n- competitive response\n- go-to-market decisions\n- marketing strategy under uncertainty\n\nIt is intentionally out of scope for:\n- military or political conflict\n- legal or medical advice\n- financial investment decisions\n- mergers and acquisitions\n- layoffs or HR restructuring\n\n## Manual Quick Start\n\n1. Start with [USAGE.md](USAGE.md) for the manual runbook.\n2. Use [prompts/system_prompt.md](prompts/system_prompt.md) as the runtime system/developer prompt.\n3. Run the stage prompts in order:\n   - `prompts/01_intake.md`\n   - `prompts/02_clarifying_questions.md`\n   - `prompts/03_strategy_map.md`\n   - `prompts/04_deep_dive.md`\n   - `prompts/05_decision_summary.md`\n4. If the decision continues over time, use the cascade log artifacts in `examples/`.\n\n## Optional ID Bootstrap\n\nDecisionMap stays standalone, but it can optionally consume `ID` as a portable human-context layer for longer-running strategic work.\n\nRecommended bootstrap order:\n\n1. `profiles/<owner>/soul.md`\n2. `profiles/<owner>/profile.core.md`\n3. `profiles/<owner>/handshake.md`\n\nUse that order when:\n\n- the same decision evolves across multiple sessions\n- the user has strong formatting, tone, or decision-style preferences\n- you want continuity without re-explaining the same working style every time\n\nDo not treat `ID` as market evidence or decision truth. It is only user-context and operating-constraints input.\n\n## Canonical Examples\n\nThese are the flagship examples for v0.3.\n\n- [examples/agri_commodity_market_entry.md](examples/agri_commodity_market_entry.md) - compact agri/commodities strategy map for a Ukrainian sunflower oil exporter evaluating Indian market entry.\n- [examples/fmcg_route_to_market_full_run.md](examples/fmcg_route_to_market_full_run.md) - full walkthrough for an FMCG chilled dairy brand redesigning route-to-market expansion.\n- [examples/cascade_log_agri_commodity_market_entry.md](examples/cascade_log_agri_commodity_market_entry.md) - worked update loop that continues the agri/commodities case after the first decision.\n\nStarter generic examples are still included, but they are no longer the flagship credibility artifacts:\n- [examples/full_run_product_launch.md](examples/full_run_product_launch.md)\n- [examples/product_launch.md](examples/product_launch.md)\n- [examples/competitive_response.md](examples/competitive_response.md)\n\n## JSON Outputs\n\nDecisionMap ships with normative schemas and real JSON fixtures:\n\n- [schemas/strategy_map.schema.json](schemas/strategy_map.schema.json)\n- [schemas/cascade_log.schema.json](schemas/cascade_log.schema.json)\n- [examples/json/strategy_map.agri_market_entry.json](examples/json/strategy_map.agri_market_entry.json)\n- [examples/json/cascade_log.agri_market_entry.json](examples/json/cascade_log.agri_market_entry.json)\n\nValidate the public examples with:\n\n```bash\npython3 -m pip install -r requirements-dev.txt\npython3 scripts/check_repo.py\n```\n\nValidate your own JSON output with:\n\n```bash\npython3 scripts/validate_examples.py path/to/output.json --schema strategy-map\n```\n\n## Cascade Log\n\nStage 6 is a first-class capability, not just a note.\n\nUse it when the decision evolves over weeks or months and you need structured memory for:\n- what was decided\n- which assumptions were active\n- which signals moved\n- what happened next\n- what changed in the working hypothesis\n\nArtifacts:\n- [examples/templates/cascade_log_template.md](examples/templates/cascade_log_template.md)\n- [examples/cascade_log_agri_commodity_market_entry.md](examples/cascade_log_agri_commodity_market_entry.md)\n- [examples/json/cascade_log.agri_market_entry.json](examples/json/cascade_log.agri_market_entry.json)\n\n## Document Roles\n\n| Artifact | Role |\n| --- | --- |\n| `README.md` | Canonical entrypoint for new users and contributors |\n| `USAGE.md` | Manual operator runbook for chat-based execution |\n| `protocol.md` | Normative spec for stages, outputs, confidence language, and cascade semantics |\n| `prompts/*` | Executable prompt assets used during a run |\n| `schemas/*` | Machine-readable shape for Stage 3 and Stage 6 outputs |\n\n## Repository Structure\n\n```text\ndecision-map/\n├── README.md\n├── USAGE.md\n├── protocol.md\n├── CONTRIBUTING.md\n├── CHANGELOG.md\n├── prompts/\n├── skills/decision-map/\n├── schemas/\n├── examples/\n│   ├── json/\n│   └── templates/\n├── scripts/\n└── .github/\n```\n\n## Contributing\n\nThe repo now has a lightweight open-source contribution layer:\n- [CONTRIBUTING.md](CONTRIBUTING.md)\n- `.github/ISSUE_TEMPLATE/`\n- [CHANGELOG.md](CHANGELOG.md)\n\nContributions are especially useful for:\n- stronger real-world examples\n- protocol clarity improvements\n- schema/example consistency\n- better manual operator guidance\n\n## Roadmap\n\nRoadmap is intentionally lightweight in-repo. Use GitHub Issues/Milestones for active work and prioritization.\n\nCurrent direction:\n- more measured real-world examples\n- interoperable exports and schema fixtures\n- clearer evidence provenance\n- tested compatibility across Agent Skills clients\n\n## ABVX Ecosystem\n\nDecisionMap remains standalone and usable with any LLM.\n\nInside the ABVX ecosystem:\n- `lab.abvx` can list it as a decision/strategy protocol artifact\n- `agentsgen` can maintain repo-local agent docs for contributors\n- `SET` can track or audit the repo\n- `ID` can optionally provide portable user context for longer-running decision work, with `soul.md` as the preferred first-pass bootstrap\n\nNone of these integrations are required for manual use.\n\nRelated repos:\n\n- [`lab.abvx`](https://github.com/markoblogo/lab.abvx) is the public hub where DecisionMap is cataloged.\n- [`abvx-agent-skills`](https://github.com/markoblogo/abvx-agent-skills) lists DecisionMap as a standalone companion skill.\n- [`AGENTS.md_generator`](https://github.com/markoblogo/AGENTS.md_generator), [`SET`](https://github.com/markoblogo/SET), and [`ID`](https://github.com/markoblogo/ID) are optional adjacent tools.\n\n## Privacy\n\nDecisionMap itself does not require storing data, but hosted LLM APIs may process your input externally.\n\nFor sensitive work:\n- anonymize names, companies, exact numbers, and internal documents\n- remove customer data and personal data\n- use a local model or approved internal environment when needed\n\n## Security\n\nReport vulnerabilities privately as described in [SECURITY.md](SECURITY.md).\n\n<!-- ABVX:ECOSYSTEM:BEGIN -->\n## ABVX ecosystem\n\n- [AGENTS.md_generator](https://agentsmd.abvx.xyz/) — Keeps repository guidance and machine-readable context current. Current release: `v0.5.1`.\n- [abvx-agent-skills](https://abvx.xyz/work/abvx-agent-skills) — Uses shared, reviewable agent capabilities during maintenance. Current release: `v0.16.1`.\n\n_This block is generated from the reviewed ABVX ecosystem registry._\n<!-- ABVX:ECOSYSTEM:END -->\n"}