Loading...
Loading...
Found 3,379 Skills
Use before claiming work is done, fixed, or passing — requires running verification commands and confirming output before any success claim. Prevents false completion claims, unverified assertions, and "should work" statements.
Strategic planning with optional interview workflow
This skill should be used when the user asks to "develop a concept", "explore a new idea", "brainstorm a system concept", "do concept development", "create a concept document", "run Phase A", "define the problem and architecture", or mentions concept exploration, feasibility studies, concept of operations, system concept, architecture exploration, solution landscape, or NASA Phase A.
The entry point for building a client website. Walks you through a structured intake — business details, design preferences, content needs — then orchestrates the full build and deploy pipeline.
Build sticker-pack prompts and GIF sticker outputs from a reference image. Use this skill whenever the user wants emoji, 表情包, sticker packs, 微信表情, reaction GIFs, image-to-sticker workflows, 4x6 expression sheets, Nano Banana / Gemini image editing, or asks to turn EmojiGen-style generation into a reusable workflow. Prefer Nano Banana models through Gemini or Vertex AI, but still use this skill when the image grid comes from another tool and only the prompt assembly or GIF production is needed.
Run configurable BMAD pipeline for story delivery using subagent
Spawn claude, codex, or gemini CLI workers in tmux panes for parallel task execution
Socratic deep interview with mathematical ambiguity gating before autonomous execution
Full lifecycle orchestrator - spec/impl/test. Spawn-wait-close pipeline with inline discuss subagent, shared explore cache, fast-advance, and consensus severity routing.
Explore-first wave pipeline. Decomposes requirement into exploration angles, runs wave exploration via spawn_agents_on_csv, synthesizes findings into execution tasks with cross-phase context linking (E*→T*), then wave-executes via spawn_agents_on_csv.
Active knowledge intelligence. Runs Mine → Grow → Defrag cycle. Mine extracts signal from git/.agents/code. Grow validates existing learnings against current reality, synthesizes cross-domain insights, traces provenance chains, and identifies knowledge gaps. Defrag cleans up. Triggers: "athena", "knowledge cycle", "mine and grow", "knowledge defrag", "clean flywheel", "grow knowledge".
Project documentation that stays alive. Read before starting work, update after finishing. Covers project setup, specs, architecture diagrams, and execution plans. Use when starting a project, writing a spec, checking existing docs, updating docs after changes, or when someone says "set up docs", "create a plan", "audit docs", or "init project".