chemaclass/agnostic-ai/spec-author

Claude Code and agent skill by chemaclass/agnostic-ai

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Use to author an agent, skill, rule or hook

Install

npx vskill@latest install chemaclass/agnostic-ai/spec-author

SKILL.md

spec-author

Create or update the smallest spec that expresses the requested behavior. Infer the kind from the request and existing specs; ask only when the choice changes the outcome. Reuse a matching spec instead of creating a duplicate.

Steps

  1. Read agnostic-ai.yaml for configured source paths and inspect sibling specs. The default root is .agnostic-ai/.
  2. Read the matching page under docs/site/content/docs/spec-format/ for fields and native limits. For a new spec, use go run ./cmd/agnostic-ai new <kind> <name> --dry-run to inspect the scaffold, then create it. Never overwrite an existing spec with a scaffold.
  3. Use agents/<name>.md, rules/<name>.md, or hooks/<name>.yaml under the configured root. Skills can use <name>.md or <name>/SKILL.md; use the folder layout when bundling references or scripts.
  4. Write a short description that tells an agent when to use the spec. Keep the body focused on decisions and actions, with conditional details in existing references. Hooks need the documented event and exact command; test the emitted behavior in an isolated project.
  5. Run go run ./cmd/agnostic-ai validate and go run ./cmd/agnostic-ai lint, then preview with go run ./cmd/agnostic-ai sync --dry-run. Check the intended targets and output paths.
  6. Generate with go run ./cmd/agnostic-ai sync, then verify go run ./cmd/agnostic-ai sync --check. Review tracked output changes and keep ignored output ignored. Follow docs/internal/contributing.md#choose-checks-for-your-change for other checks the change requires.

Use lowercase, hyphenated names. An explicit name matches the Markdown file stem, or the containing folder for SKILL.md. Paths in shared instructions are repository-root relative; state that convention when generated copies live at different depths.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
27
Repository forks
5
7-day trend score
5

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
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/chemaclass/agnostic-ai/spec-author/badge)](https://verified-skill.com/skills/chemaclass/agnostic-ai/spec-author)

Something wrong with this skill or its page? Tell us.