analyze-codebase
Run comprehensive PLG analysis on a codebase to detect tech stack, existing growth features, and revenue opportunities. Use when the user says "analyze", "scan", "audit codebase", or "find growth opportunities".
pinned to #e2173a9updated 2 weeks ago
Ask your AI client: “install skills/analyze-codebase”.
Requires the metahub MCP server installed in your client. Set up MCP.
mh install skills/analyze-codebasemetahub onboarded this repo on the author's behalf.
If you own github.com/SkeneTechnologies/skene on GitHub, claim the listing to take over publishing. Your claim preserves the existing eval history and badges; only the curator label is replaced with verified-publisher on your next publish.
Stars
120
Last commit
2 weeks ago
Latest release
published
- #ai-tools
- #anthropic
- #automation
- #cli
- #cli-tool
- #code-documentation
- #codebase-analysis
- #developer-tools
- #gemini
- #growth-hacking
- #llm
- #mcp
- #mcp-server
- #openai
- #plg
- #product-led-growth
- #pydantic
- #python
- #python3
- #tech-stack-detection
About this skill
Pulled from SKILL.md at publish time.
Run the Skene CLI to analyze the codebase. **The CLI does the analysis, not you.**
Evaluation report
WarningsAutomated checks the publisher passed at publish time — structure, docs, safety, and whether the artifact behaves as claimed.e2173a9· 2 weeks ago
Kind-specific
31Skill: SKILL.md present
found at cursor-plugin/skills/analyze-codebase/SKILL.md · frontmatter source: SKILL.md
Skill: body content present
252 words · 1,654 chars · 5 sections
Skill: triggers declaredwarn
No `trigger` phrases in SKILL.md frontmatter
Add `trigger:` lines so Claude knows when to activate this skill — e.g. `when building MCP servers` or `for diagram creation`.
Skill: allowed-tools scope
no allowed-tools restriction (Claude may use anything)
Release history
1- releasecurrente2173a9warn2 weeks ago
Contents
Run the Skene CLI to analyze the codebase. The CLI does the analysis, not you.
Critical rule
Do NOT substitute your own PLG analysis, findings, or guesses if the CLI fails. Run the CLI, present its output on success, report the error on failure. That's it.
Agent behavior rules
- Autonomous. Run the CLI, present results, suggest next step. No mid-flow questions.
- User cannot type into agent terminals. The agent handles all CLI input. Pipe safe defaults for routine prompts. Kill stuck terminals and re-run with piped input.
Steps
-
Discover CLI options Run
uvx skene analyze --helpto see available flags. Use only flags that appear in the output. -
Verify configuration
ls .skene.config 2>/dev/null— if missing: "Run/skene-initfirst." Stop. -
Run analysis Default to project root. Choose appropriate flags based on --help output.
uvx skene analyze .Tell the user: "Running analysis, this may take a few minutes."
-
Handle result
- Success: Read results from
.skene/analysis/,skene-context/, or legacyskene/and present them. Suggest/skene-plan. - Failure: Report the exact error, suggest a fix, stop. Do NOT generate your own analysis.
- Success: Read results from
Error handling
- 429 / quota: "LLM provider quota error. Check billing, then re-run."
- Permission errors: Give user the command to run in their own terminal.
- Timeout: "Try a smaller directory."
- Any other error: Report verbatim.
Output
Success: CLI results + "Run /skene-plan next."
Failure: Error + fix suggestion. No substitute analysis.
Reviews
No reviews yet. Be the first.
Related
Gpt Researcher
An autonomous agent that conducts deep research on any data using any LLM providers
Browser Use
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
Frontend Slides
Create beautiful slides on the web using Claude's frontend skills
mh install skills/analyze-codebase