Multi-agent AI skill orchestration — 13 skills, 7 lifecycle phases, any AI coding agent.
SkillWeave orchestrates AI-assisted product development from idea to post-release. It works with Claude Code, Codex, Gemini CLI, Cursor, Windsurf, OpenCode, and any agent that reads Markdown or speaks MCP.
Use meta-commands directly:
/skillweave # Where am I? What's next?
/skillweave plan # View Kanban board
/skillweave build # Start/continue building
/skillweave test # Run test pyramid
/skillweave council topic="…" # Get multi-model opinion
/skillweave report # Generate release report
Or go straight to individual skills:
/skillweave-blueprint idea="Your SaaS idea"
/skillweave-promptchain-generate inputs='{"prd": ".skillweave/prds/v1.0/prd.json"}'
/skillweave-releasechain inputs='{"prd": ".skillweave/prds/v1.0/prd.json"}' mode="attended"
Start with /skillweave to see where your project stands. The navigator detects your phase automatically and recommends the next step.
New project:
/skillweave-blueprint idea="Your idea"— Creates PRD/skillweave-promptchain-generate inputs='{"prd": ".skillweave/prds/v1.0/prd.json"}'— Generates execution plan/skillweave build— Executes the plan with testing gates
Existing project:
/skillweave— See current phase- Follow the recommendation
Just type:
/skillweave start
The wizard asks 5 simple questions and starts the right tool for you.
Works with Claude Desktop, Claude Code, Codex, Gemini CLI, Cursor, Windsurf, OpenCode, and more.
brew install capacium/tap/capacium
cap install skillweavegit clone https://github.com/LangeVC/skillweave.git
cd SkillWeave
python3 -m skillweave.installer --interactivepip install skillweaveLayer 0 — Wizard /skillweave start (5 questions, routes to skill)
Layer 1 — Meta-Commands /skillweave plan|build|… (7 commands, maps to skills)
Layer 2 — Direct Skills /skillweave-blueprint … (13 skills, full control)
Discovery → Blueprint → Design → Build → Release → Launch → Post-Release
| Phase | Skills | What it does |
|---|---|---|
| Discovery | discovery, council | Problem definition, user research, empathy mapping |
| Blueprint | blueprint, generate, validate | PRD creation, execution planning |
| Design | design | Design-Thinking Lens, token extraction, evaluation |
| Build | execute, releasechain, observe | Ralph Loop execution with parallel lanes |
| Release | releasechain, observe | Release gates, versioning, code review |
| Launch | launch | Pre-launch checklist, deployment, metrics |
| Post-Release | post-release, repo-health | Retrospective, feedback, iteration |
Global skills (available in any phase): lifecycle, repo-health, observe, council
| Skill | Type | Description |
|---|---|---|
skillweave-lifecycle |
plan | Phase navigation, planning board, testing, wizard, reports |
skillweave-discovery |
plan | Problem exploration, user research, 11 prompts |
skillweave-blueprint |
plan | Structured PRD creation with complexity assessment |
skillweave-design |
mixed | Design-Thinking Lens, brief analysis, token extraction |
skillweave-promptchain-generate |
plan | Execution sequence generation from PRD |
skillweave-promptchain-validate |
plan | Sequence validation for completeness |
skillweave-promptchain-execute |
build | Ralph Loop state machine, batch execution |
skillweave-releasechain |
build | Release pipeline with binary gates |
skillweave-launch |
build | Deployment, announcement, health checks, metrics |
skillweave-post-release |
mixed | Retrospective, feedback collection, iteration planning |
skillweave-repo-health |
plan | Inventory scan, dedup, archive, hygiene report |
skillweave-observe |
plan | Execution reports, events, memory (read-only) |
skillweave-council |
mixed | Multi-model LLM deliberation with web search |
Convene multiple AI models for research, code review, or architecture decisions:
- 3 stages: Independent opinions → anonymous peer review → chairman synthesis
- Profiles: quick (2 models), default (4), deep (6), expert (4 top-tier)
- Web search: DuckDuckGo (free), Serper, Tavily, Brave, SerpApi, Perplexity
- Output: Markdown or structured JSON with consensus score
5-level test pyramid with automatic gate decisions:
Level 5: Evidence/Groundedness (are claims backed by code?)
Level 4: Acceptance (do acceptance criteria pass?)
Level 3: E2E Smoke (does the system start and respond?)
Level 2: Unit (do individual functions work?)
Level 1: Lint (is the code clean?)
Gate decisions: PROMOTE (all pass) | HOLD (minor failures, suggest fix) | ROLLBACK (critical failures, block)
File-based Kanban with YAML frontmatter tickets:
.skillweave/planning/
├── backlog/ # Tickets waiting
├── doing/ # In progress
├── done/ # Completed
└── BOARD.md # Auto-generated board view
Create tickets, move between states, seed from PRD — all via /skillweave plan.
All SkillWeave data lives in .skillweave/ (git-ignored):
.skillweave/
├── config.yaml # Risk mode, tier, feature flags
├── planning/ # Kanban tickets (backlog/doing/done)
├── prds/ # Product requirement documents
├── sequences/ # Execution sequences
├── testing/ # Test config + results
├── handover/ # Skill-to-skill transition signals
├── reports/ # Release reports (yyyy-mm-dd-topic.md)
├── discovery/ # Discovery phase artifacts
├── schemas/ # JSON schemas for validation
└── templates/ # Report/doc templates
| Mode | Behavior |
|---|---|
| conservative | Extra validation, explicit approvals, strict checks |
| medium | Balanced automation with safety checks (default) |
| unicorn | Maximum automation, optimistic assumptions |
Override hierarchy: CLI parameter > env (SKILLWEAVE_RISK_MODE) > project config > global config > default.
SkillWeave ships in two formats depending on agent capabilities:
| Format | Agents | How it works |
|---|---|---|
| SKILL.md (Markdown skills) | Claude Code, Codex, Gemini CLI, Qwen Code | Agent reads skill instructions as context |
| MCP Server | Claude Desktop (via Capacium), Cursor, Windsurf, Zed, OpenCode | Agent calls SkillWeave tools programmatically |
Both formats use the same Python core (src/skillweave/). SKILL.md is the universal baseline; MCP provides richer tool-based interaction for agents that support it.
SkillWeave is Forever Free — all 13 skills, all 7 phases, no limits.
SkillWeave Studio (coming soon) adds advanced and team features:
| Free | Studio |
|---|---|
| 13 skills, 7 phases | Everything in Free |
| Testing pyramid | Webhook/event hooks |
| Planning board | Team collaboration |
| Wizard + meta-commands | Analytics dashboard |
| Council deliberation | Priority support |
| Reports + documentation | Custom skill authoring |
Apache 2.0 — Copyright 2026 LangeVC.com. See LICENSE.