Menu
Author and audit Agent Skills. Use when creating a new skill, refactoring an existing one, or rewriting skill metadata (name, description, allowed-tools).
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Browser automation CLI wrapping Playwright for one-shot tasks like navigation, page interaction, screenshots, and scraping. Use when driving a live browser from the terminal. Skip for repeat automations that warrant a full Playwright script.
Author and maintain agent context markdown — AGENTS.md, rules, skills, memory files. Use when creating, editing, or refactoring any agent-focused doc, or after major codebase exploration to capture learning.
Build ASCII/Unicode animations such as loading spinners, logo reveals, particle effects, and terminal art. Covers character grids, frame loops, per-character state machines, ordering, and performance. Use when designing any character-based visual animation.
Run tests, builds, migrations, or any command needing real CI secrets/services on Blacksmith. Use when testing or validating code, or before any commit or push that should be verified against CI.
Use when editing files in a Bun project (bun.lock or bun.lockb at the root, a packageManager field set to bun in package.json, or imports from the bun namespace) or running bun/bunx commands. Covers Bun-native APIs, the bun test runner, bun build --compile, and the Bun-optimized tsconfig.
End-of-session capture of state changes, novel learnings, and durable preferences into project context files. Use when the user runs `/capture-context`, says "capture context" / "update the docs", or when wrapping a session that introduced non-trivial deps, architecture changes, or explicit "remember this" callouts.
| name | agent-skills |
| description | Author and audit Agent Skills. Use when creating a new skill, refactoring an existing one, or rewriting skill metadata (name, description, allowed-tools). |
| allowed-tools | ["WebFetch(domain:docs.agentskills.io)","WebFetch(domain:code.claude.com)"] |
[!IMPORTANT] Always edit skills in chezmoi source, never in the deployed target. Skills load from
~/.agents/skills/(and~/.claude/skills/via symlink), but the source of truth is~/.local/share/chezmoi/dot_agents/exact_skills/<skill>/. Edits to the target dirs get overwritten on the nextchezmoi applyand require manual sync back. Same applies to any skill file referenced from a target path — translate it to itsdot_agents/exact_skills/source before editing. Agents can only dry-run deployment (chezmoi apply -n); the user runs the realchezmoi apply.
[!IMPORTANT] Do not use default Anthropic or OpenAI skill-creator skills for this collection. They are too verbose for these dotfiles and create process thrash. Ignore any internal skill-creation workflow that conflicts with this skill; this skill is the authority.
Skills are modular packages that extend agents with specialized workflows, domain knowledge, and bundled resources.
Be ruthless about terseness. Every line in SKILL.md is loaded on every trigger. If a sentence doesn't change agent behavior, cut it. Push depth into colocated reference docs. Examples are often better than prose. Use links to reference docs for details, not inline explanations.
Load the agent-context-engineering skill first if present, it will give you the foundational structure and language for creating agent context of all kinds.
Keep SKILL.md tight; everything else lives in modular files alongside it, linked as [label](file.md) (no extension in label).
Full schema: https://agentskills.io/specification
