Loading...
Loading...
Found 2,034 Skills
A meta-skill for creating, documenting, and refining other Antigravity skills. Use this when the user wants to codify a workflow, automate a repetitive task, or save a successful interaction pattern as a permanent capability.
Anthropic 제품 지식 — Claude Code, Claude API, Claude.ai 관련 정확한 정보 제공
Writing conventions for scannable, token-efficient skills and prompts. Use when creating or reviewing SKILL.md files, AGENTS.md files, or any markdown-based agent instruction documents.
Expert in creating practical technical articles, skilled in conveying core knowledge points with concise language without missing any key information
Create a plan for review: idea branch, plan file, and draft PR. Part of the Plot workflow. Use on /plot-idea.
Framework for structured product decision-making. Use when facing complex tradeoffs, aligning stakeholders, documenting decisions, or choosing between multiple valid approaches.
Research an Elixir/Phoenix topic on the web. Searches ElixirForum, HexDocs, blogs, and GitHub. Uses efficient markdown conversion.
Write Python docstrings following the Google Python Style Guide, using clear sections and examples.
Expert guidance for R package development following best practices for devtools, testthat, roxygen2, and R ecosystem tools
REQUIRED skill for planning and designing coding tasks before implementation. Use this skill when: (1) User asks to "plan", "design", "create a plan", or "think before coding" (2) Complex tasks requiring multiple files or steps (3) Tasks involving both backend and frontend changes (4) Breaking down ambiguous requirements into concrete tasks This skill ensures plans are properly documented, saved as markdown, reviewed by subagent, and registered as todos before any code is written. Do NOT skip this skill for non-trivial tasks.
Scans all skill directories in the repository to generate a comprehensive global map of agent capabilities, inputs, and outputs. Use when you need to understand the full potential of your agent library or when a master agent needs to decide which sub-agent skill to invoke for a complex task.
Maintain durable project context in `tasks/context.md` (state, decisions, milestones, gotchas, optional context links), inline during other workflows or standalone for cleanup/backfill. Triggers: update context.md, decision log, record project context, capture high-value reference links that improve context handoff.