Loading...
Loading...
Found 3,038 Skills
Use when creating a PRD, writing requirements, or transforming a feature request into an implementation-ready GitHub issue.
Distills a completed deep-plan document (e.g. docs/PLAN.md) into durable project knowledge files: AGENTS.md (agent operating rules and verified ground truth), docs/ARCHITECTURE.md (component map, data flow, framework mechanisms with citations), and ROADMAP.md (phased roadmap with live status). Carries only VERIFIED evidence forward, re-checks stale claims, and merges into existing files instead of overwriting. Use after a deep-plan finishes, when the user mentions deep-plan-ingest or ingest the plan, or asks to generate/update AGENTS.md, ARCHITECTURE.md, or ROADMAP.md from a plan.
Initialize IDD structure in a project. Checks existing state, creates directory structure, and generates templates. Use /intent-init to set up Intent-driven development in current project.
Manages cross-session knowledge persistence. Triggers on "remember", "recall", "what did we", "save this decision", "todo", or session handoff.
Meta-skill for internal codebase exploration at varying depths (quick/deep/architecture)
Processes meeting notes or transcripts to extract structured information. Use after meetings to quickly generate action items, capture decisions, and create follow-up tasks. Extracts: action items with owners, decisions made, key discussion points, follow-up tasks with priorities.
Apply strategic frameworks through facilitated workshop dialogue. Use when user selected framework via choose-framework; explicitly requests specific framework; knows which framework to apply; or needs structured guidance. Conducts 30-60 minute workshops guiding step-by-step through framework application. Creates workshop documents in .frameworks-output/ folder.
Evaluates agent skills against Anthropic's best practices. Use when asked to review, evaluate, assess, or audit a skill for quality. Analyzes SKILL.md structure, naming conventions, description quality, content organization, and identifies anti-patterns. Produces actionable improvement recommendations.
Perform a comprehensive session retrospective. Use when user says "retro", "retrospective", "회고", or at the end of a working session.
Keep README.md in sync with code changes (APIs, features).
Production-ready code implementation following approved designs. Writes clean, tested, documented code. Zero linting violations. All code includes tests.
Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes