MCP servers and skills: search, filter by where they run, and compare.
Use when the user asks for a shared plan, a task needs at least three substantive execution steps, or a loose TODO is pending. Without an explicit plan request, not for one-shot answers or checks, or
OfficialSkillApache-2.0★ 517 in collectionNo key
Afu · LLM Todo: turn an Obsidian inbox into a living wiki, then into todo cards for this week.
SkillMIT★ 87No key
INVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, and HITL interrupts.
OfficialSkillMIT★ 1.3k in collectionNo key
An agent-agnostic skill for organizing last messages, digital legacy, and end-of-life handoff notes.
SkillMIT★ 3Few starsNo key
Use this skill when the user explicitly asks to map, document, or onboard into an existing codebase. Trigger for prompts like "map this codebase", "document this architecture", "onboard me to this rep
in the skill textsource files, config, or terminal output. 3. Unknowns are marked as `[TODO]`; intent-dependent decisions are marked `[ASK USER]`. 4. Every document includes a short "evidence
OfficialSkillMIT★ 40k in collectionNo key
Audits, writes, and refines maintained first-party source-code comments and declaration-level documentation across languages. Use when adding, editing, reviewing, cleaning up, or auditing comments, do
in the skill textwhen adding, editing, reviewing, cleaning up, or auditing comments, doc comments, docstrings, TODO, FIXME, NOTE, suppressions, or other source commentary, including while modifying code and deciding
OfficialSkillMIT★ 40k in collectionNo key
Add a new cuTile GPU kernel operator to TileGym. Covers dispatch registration in ops.py, cuTile backend implementation, __init__.py exports, test creation, and benchmark in tests/benchmark. Use when a
in the skill textwith cuTile backend. ## Execution Rules **MUST follow these rules strictly:** 1. Use TodoWrite to create the checklist below BEFORE writing any code 2. Execute steps
OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key
A micro-prompt that reminds the agent that it is an interactive programmer. Works great in Clojure when Copilot has access to the REPL (probably via Backseat Driver). Will work with any system that ha
in the skill textprefer to use the structural editing tools. Also remember to tend your todo list
OfficialSkillMIT★ 40k in collectionNo key
Know what to fix next — local .pm governance skill pack for AI coding agents (Spec Kit–inspired).
in the skill text/pm-next` | `pm-next` | Claim the next todo (`in_progress`) | | `/pm-done` | `pm-done` | Close `TODO-xxx`, refresh overview | | `/pm-fix` | `pm-fix` | Triage pasted logs into todos (**does
SkillMIT★ 88No key
Interactive, input-tool powered, task refinement workflow: interrogates scope, deliverables, constraints before carrying out the task; Requires the Joyride extension.
in the skill textthe user with redundancy kept to a minimum 2. Create a todo list 3. Get to work
OfficialSkillMIT★ 40k in collectionNo key
Update Azure Verified Modules (AVM) to latest versions in Bicep files.
in the skill textupdates below. ## Tool Usage Always use tools `#search`, `#searchResults`,`#fetch`, `#editFiles`, `#runCommands`, `#todos` if available. Avoid writing code to perform tasks. ## Breaking Change Policy ⚠️ **PAUSE for
OfficialSkillMIT★ 40k in collectionNo key
Merges mature lessons from a domain memory file into its instruction file. Syntax: `/memory-merger >domain [scope]` where scope is `global` (default), `user`, `workspace`, or `ws`.
in the skill textinto its instruction file, ensuring knowledge preservation with minimal redundancy. **Use the todo list** to track your progress through the process steps and keep the user
OfficialSkillMIT★ 40k in collectionNo key
Create, set up, or update the personal context portfolio: structured markdown files describing who you are, how you work, your teams, and your tool/ADO configuration. Runs the interview workflow for f
in the skill textconfiguration. Trigger when another skill fails to find context (missing files or TODO markers) and needs context populated. Also trigger when the user mentions a context
OfficialSkillMIT★ 40k in collectionNo key
INVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format, and configuration options.
in the skill textopinionated agent framework built on LangChain/LangGraph with built-in middleware: - **Task Planning**: TodoListMiddleware for breaking down complex tasks - **Context Management**: Filesystem tools with pluggable backends - **Task
OfficialSkillMIT★ 1.3k in collectionNo key
A thin orchestration dashboard over Claude Code for managing context, automation, and developer headspace. You need tentacles. 🦑
in the skill textwork with scoped markdown files instead of broad, messy chat context - **Uses `todo.md` as an execution surface** so tasks stay visible, trackable, and ready for delegation
SkillMIT★ 1.4kNo key
Populates Dataverse tables with sample records for testing and demoing a Power Pages site. Use when the user wants to add sample data, seed data, generate test records, or insert demo data into their
in the skill textwhen needed. - **Use TaskCreate/TaskUpdate**: Track all progress throughout all phases -- create the todo list upfront with all phases before starting any work. - **Fail gracefully**: On insertion
OfficialSkillMIT★ 1.0k in collectionNo key
Creates Dataverse tables, columns, and relationships for a Power Pages site based on a data model proposal. Use when the user wants to set up the data model, create database tables, or build the Datav
in the skill textDataverse changes. - **Use TaskCreate/TaskUpdate**: Track all progress throughout all phases — create the todo list upfront with all phases before starting any work. - **Resilient execution**: Refresh tokens
OfficialSkillMIT★ 1.0k in collectionNo key
Deploys an existing Power Pages code site to a Power Pages environment using PAC CLI. Handles tooling verification, authentication, environment confirmation, building, and uploading. Use when the user
in the skill textany deployment. - **Use TaskCreate/TaskUpdate**: Track all progress throughout all phases — create the todo list upfront with all phases before starting any work. - **Never change environment settings
OfficialSkillMIT★ 1.0k in collectionNo key
Capture a 2-3 line pitch from the user, draft a product overview (PRD.md) and a technical design (ARCHITECTURE.md) for a third-party `.ppmplugin` native control, then walk through every operation's iO
in the skill textwhat lets the scaffold skill generate complete working code instead of TODO placeholders. Iterates with the user until they approve both docs. Optionally seeds from
OfficialSkillMIT★ 1.0k in collectionNo key
Use when the user has finished building a mobile app, started Metro with `npm run dev`, and wants the running app monitored for runtime errors AND silent failures (empty lists, blank screens, swallowe
in the skill textnetwork errors) and fixed autonomously. Accepts a free-text symptom (e.g., `/debug-app "todos not appearing on home screen"`) to drive persisted-log diagnostics — injects temporary console.log
OfficialSkillMIT★ 1.0k in collectionNo key
Use this skill when creating or editing an agent.yaml (or .yml/.hcl) configuration file for Docker Agent (cagent), including defining agents, models/providers, built-in or MCP toolsets, multi-agent te
in the skill textsub_agents, fallback), the models/providers sections, built-in toolsets (filesystem, shell, think, todo, memory, fetch), MCP toolset references, and named commands. # Docker Agent Configuration ## Overview Docker
OfficialSkillApache-2.0★ 561 in collectionNo key
Hub for getting started with Notion, including documentation, customizable scripts, and quick-start guides.
in the skill textrequests , GitHub stars , HubSpot , Intercom , Linear , PagerDuty , Readwise and Reader , Salesforce , Sentry , Todoist , Zendesk and more. - **Give a Notion Agent a reliable new capability:** execute
OfficialSkillMIT★ 218No key
Use this when scaffolding a new Terraform provider with the Plugin Framework: workspace layout, go module setup, provider server main.go, and a provider.go with schema and Configure. Also use when a u
in the skill textvariables, and the authentication attributes to match the target API. 1. Remove TODO comments from `main.go` and `provider.go`. 1. Run `go mod tidy` 1. Run
OfficialSkillMPL-2.0★ 894 in collectionNo key
Creates and configures web roles for a Power Pages code site. Web roles control access and permissions for site users, including authenticated and anonymous roles. Use when the user wants to create, a
in the skill textCore Principles - **Use TaskCreate/TaskUpdate**: Track all progress throughout all phases — create the todo list upfront with all phases before starting any work. - **Always use the UUID
OfficialSkillMIT★ 1.0k in collectionNo key
This skill should be used when the user asks to \"analyze this codebase\", \"document this service\", \"generate technical docs\", \"I inherited this code\", \"help me understand this system\", \"crea
in the skill textexplain why the architecture is shaped this way. Search for code comments, TODOs, and commit messages that reveal design rationale. When no rationale exists, mark
OfficialSkillApache-2.0★ 918 in collectionNo key
Drop-in skills that stop AI coding agents from shipping garbage — kill-slop, security-review, PR hygiene
in the skill textprompt: > Create a production-ready FastAPI backend for authentication and a personal todo list. > I need register, login, create/list/toggle todos. In-memory storage is fine
SkillMIT★ 27No key
A reactive data store & sync engine.
in the skill textTry the demos Read the docs Your first TinyBase app Create a todo list, a chat app, a drawing tool, a charting app, or a tic
SkillMIT★ 5.2kNo key
Devil's advocate skill/plugin for Claude Code and Cowork: turns Claude against you to harshly critique an idea or whole project across 8 angles and return a blunt verdict. Bilingual ES/EN. Made by tod
in the skill textwhat to fix first. Built by the tododeia community. Full guide (Spanish): ** tododeia.com/community/abogado-del-diablo ** --- ## Why it exists By default, Claude tends to agree with you
SkillMIT★ 35No key
Generate, validate, and review k6 test scripts — load, stress, spike, soak, smoke, breakpoint, functional, and protocol. Covers HTTP, WebSocket, gRPC, browser, all executors, thresholds, checks, custo
in the skill textshort linear recipe (read example → adapt → save → validate → review). A todo list would just mirror the headings without adding value, so skip the planning overhead and
OfficialSkillApache-2.0★ 285 in collectionNo key
Your coding agent says "done". Orvant asks for proof. A skill for Claude Code, Codex and other file-capable agents, plus a Python engine that clarifies the goal, prepares an independent acceptance ora
in the skill textone workable task and one blocked by its prerequisite: ```text - T-INCELE [todo] Örnek metnin tek cümle oluşunu incele (kayıt: todo) - T-KONTROL [blocked] İnceleme gerekçesini
SkillMIT★ 34No key
Project memory system for AI coding assistants (Claude Code, Cursor, Codex): session logs, project wiki, rules, TODOs, and handoff.
SkillMIT★ 374No key
A collection of Claude Skills from Posit
in the skill textcode references suitable for humans and AI agents - ** new-work ** - Create a todo tracking document for a new feature, bug, or task; keeps it updated with
SkillMIT★ 542No key
A Claude Code workspace template for PMs, designers, and analysts. Clone, personalize in 3 minutes, produce real artifacts in 30 min.
in the skill textnow live in-repo at `Dashboard/tasks.md` - no external task manager required. The old Todoist-coupled v1 is available on the `v1` tag if you need
SkillMIT★ 34No key
司南：个性化 AI 任务总控 Skills 系统 /COMPASS: Personal Alignment Skills OS for AI Agents
in the skill textrepo-local task forest / DAG with goals, subtasks, dependencies, progress, deviations, todos, decisions, and conversation history. | | `pause-and-resume` | Cooperatively pauses unfinished work at a safe
SkillMIT★ 754No key
微信小程序 Skills 示例集合 —— 从简单待办到解决数据存储、支付、AI 调用，开箱即用。帮你的小程序快速接入微信小程序 AI 开发模式
in the skill text生活缴费 · 3 API party-skill 聚会安排 · 4 API queue-skill 门店排队 · 4 API todolist-skill 简单待办 · 4 API payment-skill 微信支付 · 2 API text-gen-skill
SkillMIT★ 45No key
⚡ Universal Skill AI Agent Swarm Architecture for Antigravity, Claude Code, Cursor, and Windsurf. Vibe Coding 2.0 with Zero Tech Debt
in the skill textcheck | 🧹 **Zero-Tech-Debt Auditor & Red Teaming** | | **Sovereign Anti-Slop** | ❌ Lazy stubs, `// TODO`, & chat fluff | ⚠️ Untested static prompts | 🛡️ **Zero-Tolerance Anti-Slop Engine & Scanner** | | **Payment & Micro
SkillMIT★ 75No key
Skill para Claude Code que analiza textos argumentativos con el marco Paul-Elder (8 elementos + estándares intelectuales), detecta falacias y sesgos cognitivos, y declara la no-neutralidad del analiza
in the skill textpensar por ti mismo. ## Para quién es Está pensada sobre todo para gente que **escribe o lee opinión con cierta exigencia**: redactores de newsletters y blogs
SkillMIT★ 29No key
A Codex skill that turns vague long-running tasks into aligned, paste-ready /goal prompts.
in the skill textGoal Todo ## Install with `$skill-installer` ```text $skill-installer install ``` Restart Codex to pick up the new skill. `goal-todo` is a single skill repository organized
SkillMIT★ 3Few starsNo key
My personal collection of Skills — open-source tools that extend Agent's capabilities for content creation, development logging, and productivity workflows.
in the skill textyour Obsidian vault | README | Link | | **article2ticktick** | Convert tech newsletter articles to TickTick todos with auto-categorization | README | Link | ## Quick Start ### Install all skills at once
SkillMIT★ 118No key
Autonomous AI agent loop that keeps working through your project while you keep planning what comes next.
in the skill textHow to cancel a task You can see the current state of the TODO-list with: ```sh lauren ``` This will open a simple TUI showing what
SkillMIT★ 13No key
Skill de Claude en español: una entrevista detecta tu ruta (Escalador, Activador, Redefinidor, Definidor, Explorador) y construye contigo el plan de tu negocio de servicios: mercado, oferta y precios,
in the skill textfacturo y quiero escalar" | **Escalador** | Productizar, subir precios y sistematizar | | "Lo tengo todo montado y no entra ni un cliente" | **Activador** | Diagnosticar por qué y diseñar
SkillMIT★ 17No key
Show it. Say it. Your AI gets it. Record your screen and talk — your coding agent turns it into bugs, ideas and to-dos, with the exact frames marked. 口喷鸡：边看边喷，AI 全懂。Agent Skill + macOS menu-bar app fo
in the skill textloud — your coding agent turns it into bug tickets, idea boards and todos. Website · 中文 · works with Claude Code, Codex and any agent that runs skills
SkillMIT★ 59No key
洁癖.skill：让 AI Agent 少留痕，留下的都有用。 Tidy Skill: make AI agent artifacts intentional, scoped, and disposable when needed.
in the skill textComparison English · 中文 --- ## Before and After **Without hygiene governance** > Agent drops `plan.md`, `todo.md`, `final_report.md` into the repo root. > Next session re-reads the repo, asks you
SkillMIT★ 18No key
The visual Kanban for long-running AI agents. Watch your agent's plan organize itself: dependencies unlock into Ready, the critical path lights up, the one next move is obvious. Nobody wants to read a
in the skill textAfter a context compaction or a `/clear`, an agent drops half the TODO list and stops mid-task, or it picks up the wrong thing next
SkillMIT★ 68No key
Production-ready prompt library for Claude coding agents. APEI methodology, ~35 specialist prompts, current Claude Code coverage, plus a /find-prompt skill that routes any task to the right prompt.
in the skill textmodel-cost scan for conflict markers, live-looking credentials, debug leftovers, untracked TODOs, oversized files | View | | `changelog-from-commits` | Cutting a release — Conventional Commits parsed into
SkillMIT★ 53No key
Agent Skills com conhecimento de produção sobre as APIs públicas do CNJ: DataJud e DJEN (Comunica PJe)
in the skill textdeploy, o parâmetro que falha em silêncio, a resposta 200 que mente. Todo o conteúdo vem da operação real do Judis , um SaaS jurídico que consome
SkillMIT★ 27No key
Shared memory and coordination for agents
in the skill texthas acknowledged it. - **Tasks** delegate work to another agent, with their consent. - **Todos** track an agent's own actions, not visible to other agents, with optional
SkillMITFew starsNo key
Who stands behind it
Who stands behind it
