bew/dotfiles/opencode-artefact-rules

Claude Code and agent skill by bew/dotfiles

Trust tier 2
  • community
LLM review pending
Source check pending

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

Quality criteria and review checklist for OpenCode artefacts (skills, skill-standalone, agents, commands, oc-tools, oc-plugins). Invoked by opencode-reviewer agent. Not for direct use.

Install

npx vskill@latest install bew/dotfiles/opencode-artefact-rules

SKILL.md

Quality Criteria for OpenCode Artefacts

Goal

Provide quality criteria for reviewing OpenCode artefacts. Type-specific criteria loaded on demand.

Universal criteria (all artefact types)

Check these first, regardless of artefact type.

  1. Description trigger — Is description specific enough to trigger correctly — not too broad, not too narrow?
  2. Frontmatter completeness — Is every relevant frontmatter field present and valid?
  3. Writing & structural rules — Does body conform to the writing-rules and steps/phases/headers rules files already loaded in context?

Check: tone, sentence-per-line, example format, formatting rules, named steps/phases syntax, header anchors.

  1. Missing rules — Is there anything artefact should always/never do? Any precondition it should verify before acting?
  2. Edge cases — What happens when required file is missing? When tool returns an error?
  3. Re-locatability — Check that no paths point outside of $draftpath (like: /foo or ~/foo or ../foo).

Referencing other artefacts by name is fine.

  1. Reference integrity — For every §slug reference in any file under $draftpath:
  • Same-file ref (§slug): a matching <!-- §slug --> anchor must exist in that file.
  • Cross-file ref (<./path/to/file.md§slug>): target file must exist and contain <!-- §slug -->.

Flag dangling references (no anchor) and dead anchors with no reference.

Type-specific criteria

Based on artefact type, read the appropriate file for additional criteria:

  • skill: read <./refs/skills.md>
  • skill-standalone: read <./refs/skill-standalone.md>
  • agent: read <./refs/agents.md>
  • command: read <./refs/commands.md>
  • oc-tool: read <./refs/oc-plugins.md> (same implementation as oc-plugin)
  • oc-plugin: read <./refs/oc-plugins.md>

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
57
Repository forks
4
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
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/bew/dotfiles/opencode-artefact-rules/badge)](https://verified-skill.com/skills/bew/dotfiles/opencode-artefact-rules)

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