superdesigndev/loopany/loopany-core
Claude Code and agent skill by superdesigndev/loopany
- community
Checking that the SKILL.md file is still in the repository.
Artifact lifecycle for loopany — the agent brain. Use when creating, modifying, or querying any artifact (task, signal, learning, skill-proposal, mission, person, note, brief, journal). Read this SKILL.md first for routing, then the relevant kind's Playbook. Triggers: any artifact CRUD, 'create a task', 'write a signal', 'dismiss signal', 'flip to done', 'what kind should this be', choosing a relation verb.
Install
npx vskill@latest install superdesigndev/loopany/loopany-coreSKILL.md
loopany-core — artifact operations
Read this first when working in a loopany workspace. Routes you to the right kind playbook for any artifact operation.
Bootstrap
No active mission → run onboarding first (see ONBOARDING.md).
Kind routing
Each kind file has schema (Frontmatter, Status machine) AND operational guide (§ Playbook). Read the kind file before creating or modifying.
| Trigger | Read | |
|---|---|---|
Committing to work, [change] / [incident] | kinds/task.md | |
| Writing Outcome, flipping task status | kinds/task.md § Playbook | |
| Noticed something, can't act now | kinds/signal.md | |
| Dismissing / upgrading a signal | kinds/signal.md § Playbook | |
| Writing a learning | kinds/learning.md | |
| Writing a skill-proposal | kinds/skill-proposal.md | |
| Creating / updating a mission | kinds/mission.md | |
| Writing a brief | kinds/brief.md | |
| Recording a person entity | kinds/person.md | |
| Anything else | kinds/note.md | |
| What was created today (read-only) | kinds/journal.md |
Decision rule
| State | Artifact | |
|---|---|---|
| Acting now / committed | task | |
| Deferred / unverified | signal | |
| Pattern-backed belief | learning (via loopany-reflect) | |
| Belief implies skill edit | skill-proposal (via loopany-reflect) | |
| Long-running pursuit | mission | |
| Point-in-time summary | brief | |
| Human entity | person | |
| Nothing unresolved | nothing, or note if rationale matters | |
| Duplicate | append evidence; don't fork |
Pass --slug for anything you'll cite later
The slug IS the id, and it's what shows up in [[citations]]. Pass one whenever the artifact has a natural name (q2-cac-spike, alice-chen). Omit only for batch ingestion — the auto-derived id is fine but ugly.
Conventions
- Relations (
conventions/relations.md) — 6 canonical verbs forrefs add. - Taxonomy (
conventions/taxonomy.md) — note vs kind vs domain decision tree.
Related skills
| Need | Skill | |
|---|---|---|
| First-read routing for any loopany interaction | loopany-resolver | |
| Self-improvement (reflect → learning → proposal) | loopany-reflect | |
| Periodic reviews (daily / weekly / monthly) | loopany-review | |
| Auto-capture after work concludes | loopany-capture |
Anti-patterns
- ❌ Acting without reading the kind playbook.
- ❌ Skipping anti-patterns sections — failure modes live there.
- ❌ Creating an artifact without checking this routing table first.
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
- SKILL.md in the repositoryCheckingskills/loopany-core/SKILL.md
Popularity
- 7-day trend score
- 0
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/superdesigndev/loopany/loopany-core)