skenetechnologies/skene/plan-growth-loop
Claude Code and agent skill by skenetechnologies/skene
- community
Checking that the SKILL.md file is still in the repository.
Generate prioritized growth loops with implementation roadmaps based on codebase analysis. Use when the user says "plan", "growth loops", "prioritize", "what should I build", or "roadmap".
Install
npx vskill@latest install skenetechnologies/skene/plan-growth-loopSKILL.md
Plan Growth Loop
Generate prioritized growth loops from the Skene CLI. The CLI does the planning, not you.
Agent behavior rules
- Autonomous. Run the CLI, present results, suggest next step. No mid-flow questions unless there's a genuine blocker.
- CLI is the source of truth. If
uvx skene planfails, report the error. Do NOT generate your own growth loops. - User cannot type into agent terminals. Pipe safe defaults for routine prompts. Kill stuck terminals and re-run.
Steps
- Discover CLI options
Run uvx skene plan --help to see available flags. Use only flags that appear in the output.
- Verify analysis exists
ls .skene/analysis/ 2>/dev/null || ls skene-context/ 2>/dev/null || ls skene/ 2>/dev/null If missing: "Run /skene-analyze first." Stop.
- Generate growth plan
Run uvx skene plan with appropriate flags from --help output. If it fails, report error. Do NOT make up growth loops.
- Present CLI output
Read results from .skene/plans/, skene-context/growth-loops/, or skene/growth-loops/ and present loops by priority.
- Help user choose
Ask which loop to implement — this is the one genuine decision point.
- Store selection
Use the appropriate CLI flag from --help to store the selection (e.g. --select). If the command prompts for input, pipe the answer. If no select flag exists, write to .skene/active-loop.json directly.
- Next step
"Run /skene-build to generate the implementation plan."
Error handling
- CLI failure: Report error, suggest fix. Do NOT fabricate growth loops.
- Permission errors: Give user the command for their terminal.
Output
Loops found, selection stored, next step (/skene-build).
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/plan-growth-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/plan-growth-loop)