skenetechnologies/skene/validate-loop
Claude Code and agent skill by skenetechnologies/skene
- community
Checking that the SKILL.md file is still in the repository.
Check if growth loop requirements are actually implemented in the codebase. Use when the user says "validate", "check status", "skene status", "is it done", or "verify implementation".
Install
npx vskill@latest install skenetechnologies/skene/validate-loopSKILL.md
Validate Loop Implementation
Check implementation status via the Skene CLI.
Agent behavior rules
- Autonomous. Run the CLI, present results, suggest next step. No mid-flow questions.
- CLI is the source of truth. If
uvx skene statusfails, report the error. Do NOT fabricate your own checklist. - User cannot type into agent terminals. Pipe safe defaults for routine prompts. Kill stuck terminals.
Steps
- Discover CLI options
Run uvx skene status --help to see available flags. Use only flags that appear in the output.
- Check for growth loops
ls .skene/active-loop.json 2>/dev/null || ls skene-context/growth-loops/ 2>/dev/null || ls skene/growth-loops/ 2>/dev/null If missing: "No growth loop found. Run /skene-plan first." Stop.
- Run status check
Run uvx skene status with appropriate flags from --help output (e.g. path argument, --context if needed). If it fails, report error. Do NOT build your own checklist.
- Present CLI output
Present the engine status table from CLI output. For action features, Detail uses Found in: <newest migration> (+N) when the same trigger exists in multiple SQL files (+N = additional files beyond the one shown).
- Suggest next step
- All done → "Growth loop implemented. Run
/skene-deployfor telemetry." - Gaps remain → "Remaining: [items]. Run
/skene-buildto continue."
Error handling
- CLI failure: Report error, suggest fix.
- Permission errors: Give user the command for their terminal.
Output
Status summary (done/partial/missing), what's left, next step.
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 repositoryCheckingcursor-plugin/skills/validate-loop/SKILL.md
Popularity
- Repository stars
- 120
- Repository forks
- 13
- 7-day trend score
- 24
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/skenetechnologies/skene/validate-loop)