itismixian/orrery/project-orrery
Claude Code and agent skill by itismixian/orrery
- community
Checking that the SKILL.md file is still in the repository.
Route Orrery documentation-system work through the platform-neutral Orrery CLI while preserving the target repository's canonical AGENTS.md authority chain. Use when asked to scaffold, validate, audit, update, or maintain Orrery documentation.
Install
npx vskill@latest install itismixian/orrery/project-orrerySKILL.md
Orrery Claude Code Adapter
This is a thin Claude Code Plugin Skill. It requires the separately installed project-orrery CLI declared in adapter-manifest.json; it does not contain Orrery templates, schema, compatibility rules, or project facts.
Route the task
- Read the target repository's root
AGENTS.mdand follow its local reading
order and safety boundaries before touching project files.
- Before invoking the CLI, run
python -X utf8 "${CLAUDE_PLUGIN_ROOT}/scripts/check_cli_dependency.py". If the check exits nonzero, report its structured dependency error instead of falling back to copied templates or inferred rules.
- Before the first product write, run `project-orrery worktree route --target
<repo> --adapter-manifest "${CLAUDE_PLUGIN_ROOT}/adapter-manifest.json" --platform-session-id <current-session-id> --json. If the runtime does not expose its session ID, stop with the returned continuation brief. When the route requires attach, run the corresponding worktree session attach command and rerun the route. Continue only when the route returns allow`; never bypass dirty-primary recovery or silently rebind an existing session.
- Use the CLI command that matches the request:
project-orrery scaffold --target <repo> --title <title> --dry-runproject-orrery validate --target <repo>project-orrery check-update --target <repo>
- Keep Plugin installation separate from target-project scaffolding,
Observatory tool upgrades, and authored-document migration.
- Never claim that an accepted decision is implemented, that an installed
scaffold is integrated, or that Agent self-report proves files were read.
For established repositories, inspect existing documentation roles and review the dry-run before any mutation. Never silently overwrite authored documents. Only use --upgrade-tools when the user explicitly requests managed Observatory updates and has reviewed the planned backups.
After implementation or validation work, update the authority layers required by the target repository's own AGENTS.md. Do not create a parallel state summary in Claude-specific files.
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 repositoryCheckingadapters/claude-code/skills/project-orrery/SKILL.md
Popularity
- Repository stars
- 47
- Repository forks
- 1
- 7-day trend score
- 19
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/itismixian/orrery/project-orrery)