ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified

solo-setup

Auto-generate project workflow config (docs/workflow.md) from existing PRD and CLAUDE.md with zero questions. Use when user says "set up workflow", "configure TDD", "wire up dev workflow", or after running /scaffold before /plan. Do NOT use for founder setup (use /init) or project scaffolding (use /scaffold).

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/fortunto2/solo-setup
Or

/setup

Auto-generate project workflow config from existing PRD and CLAUDE.md. Zero interactive questions — all answers extracted from project data that already exists after /scaffold.

When to use

After /scaffold creates a project, before /plan. Creates docs/workflow.md so /plan and /build can work.

MCP Tools (use if available)

  • project_info(name) — get project details, detected stack
  • kb_search(query) — search for dev principles, manifest, stack templates
  • codegraph_query(query) — check project dependencies in code graph

If MCP tools are not available, fall back to reading local files only.

Steps

  1. Detect project root:

    • If $ARGUMENTS is provided, look for a project with that name in the current directory or projects_dir from ~/.solo-factory/defaults.yaml.
    • Otherwise use current working directory.
    • Verify the directory exists and has CLAUDE.md.
    • If not found, ask via AskUserQuestion.
  2. Check if already initialized:

    • If docs/workflow.md exists, warn and ask whether to regenerate.
  3. Read project data (parallel — all reads at once):

    • CLAUDE.md — tech stack, architecture, commands, Do/Don't
    • docs/prd.md — problem, users, solution, features, metrics, pricing
    • package.json or pyproject.toml — exact dependency versions
    • Makefile — available commands
    • Linter configs (.eslintrc*, eslint.config.*, .swiftlint.yml, ruff.toml, detekt.yml)
  4. Read ecosystem sources (optional — enhances quality):

    • Detect stack name from CLAUDE.md (look for "Stack:" or the stack name in tech section).
    • If MCP kb_search available: search for stack template and dev-principles.
    • Otherwise: look for stacks/<stack>.yaml and dev-principles.md in .solo/ or plugin templates directory (if accessible).
    • If neither available: derive all info from CLAUDE.md + package manifest (sufficient).
  5. Detect languages from package manifest:

    • package.json → TypeScript
    • pyproject.toml → Python
    • *.xcodeproj or Package.swift → Swift
    • build.gradle.kts → Kotlin
  6. Create docs directory if needed:

    mkdir -p docs
    
  7. Generate docs/workflow.md: Based on dev-principles (from MCP/KB or built-in defaults):

    # Workflow — {ProjectName}
    
    ## TDD Policy
    **Moderate** — Tests encouraged but not blocking. Write tests for:
    - Business logic and validation
    - API route handlers
    - Complex algorithms
    Tests optional for: UI components, one-off scripts, prototypes.
    
    ## Test Framework
    {from package manifest devDeps: vitest/jest/pytest/xctest}
    
    ## Commit Strategy
    **Conventional Commits**
    Format: `<type>(<scope>): <description>`
    Types: feat, fix, refactor, test, docs, chore, perf, style
    

Metadata

Author@fortunto2
Stars2387
Views0
Updated2026-03-09
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-fortunto2-solo-setup": {
      "enabled": true,
      "auto_update": true
    }
  }
}
Safety NoteClawKit audits metadata but not runtime behavior. Use with caution.

Related Skills

solo-swarm

Launch 3 parallel research agents (market, users, tech) to investigate an idea from multiple angles simultaneously. Use when user says "swarm research", "parallel research", "investigate fast", "3 agents", "team research", or wants faster alternative to /research. Produces research.md. Do NOT use for solo research (use /research) or idea scoring (use /validate).

fortunto2 2387

solo-build

Execute implementation plan tasks with TDD workflow, auto-commit, and phase gates. Use when user says "build it", "start building", "execute plan", "implement tasks", "ship it", or references a track ID. Do NOT use for planning (use /plan) or scaffolding (use /scaffold).

fortunto2 2387

solo-metrics-track

Set up PostHog metrics plan with event funnel, KPI benchmarks, and kill/iterate/scale decision thresholds. Use when user says "set up metrics", "track KPIs", "PostHog events", "funnel analysis", "when to kill or scale", or "success metrics". Do NOT use for SEO metrics (use /seo-audit).

fortunto2 2387

solo-audit

Health check knowledge base for broken links, missing frontmatter, tag inconsistencies, and coverage gaps. Use when user says "audit KB", "check frontmatter", "find broken links", "tag cleanup", or "knowledge base quality". Do NOT use for SEO audits (use /seo-audit) or code reviews.

fortunto2 2387

solo-seo-audit

SEO health check for any URL — analyzes meta tags, OG, JSON-LD, sitemap, robots.txt, SERP positions, and scores 0-100. Use when user says "check SEO", "audit this page", "SEO score", "check meta tags", or "SERP position". Do NOT use for generating landing content (use /landing-gen) or social media posts (use /content-gen).

fortunto2 2387