.claude/skills/project-stage-detection/SKILL.md
Detect project maturity stage (new/early/mid/mature) from file structure and route to appropriate onboarding workflow
npx skillsauth add oimiragieo/agent-studio project-stage-detectionInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Detect the maturity stage of a software project by analyzing its file structure, configuration files, documentation, and test coverage. Route to the appropriate onboarding or initialization workflow based on the detected stage.
Skill({ skill: 'project-stage-detection' });
Invoke when:
| Stage | Description | Indicators |
| -------- | --------------------------------------------------- | ------------------------------------ |
| new | Freshly initialized, no meaningful content | Only boilerplate files, no src/ |
| early | Has core structure but missing key components | src/ exists, no tests or CI |
| mid | Functional codebase, gaps in quality infrastructure | Tests exist, no CI/CD or sparse docs |
| mature | Full-featured with CI/CD, tests, docs, linting | All quality gates present |
Command:
node .claude/skills/project-stage-detection/scripts/main.cjs --dir <project_root>
Expected output: JSON with stage, confidence, indicators, and recommendations.
Verify: Exit code 0 and valid JSON with a stage field.
The script checks for these indicators, scoring each:
| Indicator | Weight | Checked Path(s) |
| ----------------------------- | ------ | ---------------------------------------- |
| Source directory exists | HIGH | src/, lib/, app/ |
| Tests exist | HIGH | tests/, test/, spec/, __tests__/ |
| CI/CD pipeline configured | HIGH | .github/workflows/, .gitlab-ci.yml |
| Package.json / pyproject.toml | MED | package.json, pyproject.toml |
| README exists and non-trivial | MED | README.md (>500 bytes) |
| Linting configured | MED | .eslintrc*, .ruff.toml, pylintrc |
| Documentation directory | LOW | docs/, .claude/docs/ |
| Changelog present | LOW | CHANGELOG.md, CHANGELOG.rst |
| Dependencies locked | LOW | package-lock.json, pnpm-lock.yaml |
| Score Range | Stage |
| ----------- | -------- |
| 0–2 | new |
| 3–5 | early |
| 6–7 | mid |
| 8–9 | mature |
Command to verify score:
node .claude/skills/project-stage-detection/scripts/main.cjs --dir . --json | node -e "const d=require('fs').readFileSync('/dev/stdin','utf8');const r=JSON.parse(d);console.log('Stage:',r.stage,'Score:',r.score,'Confidence:',r.confidence)"
Based on the detected stage:
| Stage | Recommended Action |
| -------- | ----------------------------------------------------- |
| new | Invoke project-onboarding skill to bootstrap |
| early | Invoke gap-detection to find missing infrastructure |
| mid | Invoke gap-detection then proactive-audit |
| mature | Invoke gap-detection as health check only |
Routing command:
// After detection
if (result.stage === 'new') {
Skill({ skill: 'project-onboarding' });
} else {
Skill({ skill: 'gap-detection' });
}
Output location: .claude/context/reports/backend/project-stage-report-YYYY-MM-DD.md
Report format:
# Project Stage Detection Report
**Date:** {{date}}
**Project:** {{project_root}}
**Detected Stage:** {{stage}}
**Confidence:** {{confidence}}%
## Evidence
{{indicators_table}}
## Recommendations
{{recommendations_list}}
See schemas/output.schema.json for the full structured output contract.
Input validated against schemas/input.schema.json before execution.
Output contract defined in schemas/output.schema.json.
planner — uses on task start to calibrate workflow complexityarchitect — uses for brownfield assessment before redesigndeveloper — uses to determine onboarding steps for new reposmaster-orchestrator — uses to route to correct initialization workflowBefore starting:
Read .claude/context/memory/learnings.md for any previously detected stage for this project. If the stage was recently detected (within 7 days), skip re-detection and use cached result.
After completing:
Append to .claude/context/memory/learnings.md:
## Project Stage Detection — {{date}}
- Project: {{project_root}}
- Stage: {{stage}} (confidence: {{confidence}}%)
- Key gaps: {{gap_summary}}
- Recommended next action: {{next_action}}
mature for a project with no tests — tests are a required mature indicator..claude/ subdirectories — scan the project root only.existsSync checks.tools
Comprehensive biosignal processing toolkit for analyzing physiological data including ECG, EEG, EDA, RSP, PPG, EMG, and EOG signals. Use this skill when processing cardiovascular signals, brain activity, electrodermal responses, respiratory patterns, muscle activity, or eye movements. Applicable for heart rate variability analysis, event-related potentials, complexity measures, autonomic nervous system assessment, psychophysiology research, and multi-modal physiological signal integration.
tools
Comprehensive toolkit for creating, analyzing, and visualizing complex networks and graphs in Python. Use when working with network/graph data structures, analyzing relationships between entities, computing graph algorithms (shortest paths, centrality, clustering), detecting communities, generating synthetic networks, or visualizing network topologies. Applicable to social networks, biological networks, transportation systems, citation networks, and any domain involving pairwise relationships.
data-ai
Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML.
development
Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.