joshmock/dotfiles/skill-authoring
Claude Code and agent skill by joshmock/dotfiles
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Create and maintain Agent Skills that follow the agentskills.io specification and local conventions. Use when you need to add or update skills under ~/.pi/skills.
Install
npx vskill@latest install joshmock/dotfiles/skill-authoringSKILL.md
Skill Authoring Guide
Use this skill when you need to create or update skills in ~/.pi/skills. It captures the Agent Skills format plus local conventions learned in this environment.
Safety Rules (Do Not Violate)
- Do not modify user data outside
~/.pi/skillsunless explicitly instructed. - Prefer read-only inspection before editing any existing skill files.
- Any reusable scripts must go in the skill's
scripts/directory (do not embed large reusable snippets inSKILL.md). - If the task requires new automation, add it under
scripts/in the skill directory.
Required Structure
A skill directory must include at least:
SKILL.md frontmatter (required)
Constraints (from spec):
nameis 1–64 chars, lowercase letters/numbers/hyphens only.- No leading/trailing hyphen, no consecutive
--. - Must match the parent directory name exactly.
descriptionis 1–1024 chars and should include when to use the skill.
Optional fields:
license,compatibility,metadata,allowed-tools.
Recommended Body Sections
- Safety Rules (explicit allowed/forbidden actions).
- What to Produce (expected output format and decision rules).
- Suggested Workflow (step-by-step).
- Notes (edge cases, cautions).
Local Conventions Learned Here
- Use
scripts/for reusable code instead of embedding large snippets inSKILL.md. - Include explicit pre-commands when required (e.g., a sync command that must run before analysis).
- Keep instructions concise and unambiguous.
- Deduplicate outputs when threads or repeated items are expected.
Optional Directories
scripts/— executable helpers (Python/Bash/JS). Document usage inSKILL.md.references/— additional docs for progressive disclosure.assets/— templates, static data, diagrams.
Workflow Checklist
- Create
~/.pi/skills/<skill-name>/. - Add
SKILL.mdwith valid frontmatter. - Write clear rules for when and how the skill is used.
- Add helpers under
scripts/if needed, and reference them with relative paths. - Keep
SKILL.mdunder 500 lines and move extra details intoreferences/if needed. - Validate naming constraints and ensure the directory name matches
name.
Example Skeleton
References
- Agent Skills specification: /home/joshmock/Downloads/specification.md
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckinghome/dot_pi/agent/skills/skill-authoring/SKILL.md
Popularity
- Repository stars
- 18
- Repository forks
- 1
- 7-day trend score
- 20
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/joshmock/dotfiles/skill-authoring)