superdesigndev/loopany/loopany-review
Claude Code and agent skill by superdesigndev/loopany
- community
Checking that the SKILL.md file is still in the repository.
Periodic review for loopany — daily, weekly, or monthly. Triggers: 'what's due today', 'what am I forgetting', 'what's slipping', 'weekly check', 'is the workspace healthy', 'is this still the right mission?', 'anything structural?', session start, daily/weekly/monthly cadence.
Install
npx vskill@latest install superdesigndev/loopany/loopany-reviewSKILL.md
loopany-review — parameterized periodic check
One skill, three frequencies. Each adds scope; all share the same closure gate.
Frequency routing
| Freq | Scope | Trigger | Read | |
|---|---|---|---|---|
| daily | checkAt = today | "what's due today", session start | references/daily.md | |
| weekly | overdue + parking lots + doctor | "what's slipping", "weekly check" | references/weekly.md | |
| monthly | mission alignment + structural drift | "right mission?", "anything structural?" | references/monthly.md |
Don't mix scopes. One week of overdue is a pattern; one day isn't.
Unified flow (all frequencies)
1. Query
Frequency-specific — see the reference file.
2. Classify
Read each: loopany artifact get <id>
- A. Silently resolvable — extend
checkAtwith a one-line reason. - B. Needs the user — requires judgment or data only user has.
- C. Defer — push
checkAtforward with a reason.
For learnings: loopany trace <learning-slug> --direction backward
3. Surface
Only bucket B. One line per item:
Empty → say so and stop.
4. Dispatch
Route to kind playbooks in loopany-core:
- Task →
../loopany-core/kinds/task.md § Playbook - Learning →
../loopany-core/kinds/learning.md § Playbook - Signal →
../loopany-core/kinds/signal.md § Playbook - Mission →
../loopany-core/kinds/mission.md § Playbook
5. Close (the gate)
Every surfaced item must end the session in one of:
- Resolved — state transition written.
- Deferred —
checkAtpushed with reason. "Not yet" isn't a reason. - Retired —
checkAtremoved with note.
No zombie items. A digest without state changes is noise.
Anti-patterns
- ❌ Daily runs overdue → weekly's job.
- ❌ Weekly runs daily → nothing stagnates in 24h.
- ❌ Monthly runs weekly → 1 week can't detect drift.
- ❌ Defer without reason → items rot.
- ❌ Surface without closing → worse than no digest.
- ❌ Manufacture content when empty → quiet is fine.
- ❌ Dump raw JSON → your job is judgment.
Quick reference
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-review/SKILL.md
Popularity
- Repository stars
- 140
- Repository forks
- 17
- 7-day trend score
- 0
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/superdesigndev/loopany/loopany-review)