onboard-dev-agent
Use when a dev is new to the project, asks for an overview, or wants to get oriented quickly. Fills graph gaps then runs a guided codebase interview.
git clone --depth 1 https://github.com/wednesday-solutions/ai-agent-skills /tmp/onboard-dev-agent && cp -r /tmp/onboard-dev-agent/skills/agents/onboard-dev ~/.claude/skills/onboard-dev-agentSKILL.md
# Dev Onboarding Agent ## When to use - "I'm new to this project, where do I start?" - "Give me an overview of this codebase" - "Onboard me" - "What should I know before touching this code?" ## What to do 1. **brownfield-fix** — Before answering anything, check for high-risk files with low graph coverage: - Run `wednesday-skills fill-gaps --min-risk 60` - This ensures the graph is reliable for the onboarding session - Report any gaps that were filled 2. **brownfield-chat** — Run a structured onboarding interview using the graph: Answer each of these in order, citing sources: - "What does this project do?" — reads MASTER.md overview - "What are the main modules and what does each do?" — summaries.json - "What are the highest-risk files and why?" — dep-graph.json safety-scores - "What changed in the last 30 days?" — git log - "What are the architecture rules I must not break?" — PLAN.md boundaries or MASTER.md danger zones - "Which areas have low test coverage?" — dep-graph.json coverage data 3. Finish with: "Which area would you like to explore first?" ## Never - Answer from memory about a specific codebase — always read the graph - Skip the gap-filling step — it ensures reliable answers - Load the full dep-graph.json — query only relevant nodes
Use when asked to audit a module, check its health, or assess whether it should be refactored. Runs structural query, risk check, and test generation automatically.
Full PR review orchestrator. Use when asked to review a PR or check if it is ready to merge. Runs blast radius + drift check on changed files, then hands off to pr-review for comment triage and fixes. Do NOT use pr-review directly for full reviews — use this.
Enforces architecture boundaries defined in PLAN.md. Use when a PR crosses module/service boundaries, when the dev asks "are we following the architecture?", or as a scheduled architecture health check. Not for querying what a module does — use brownfield-chat for that.
Unified codebase intelligence. Handles all questions about structure, logic, risk, and dependencies. Combines natural-language Q&A with deterministic lookups and pre-edit blast radius checks.
Pre-deploy and post-deploy checklist skill. Ensures env vars, migrations, CI, rollback plan, smoke tests, and monitoring are verified before and after every deployment.
Parallel persona planning for new projects. Research agent runs first to build domain context, then Architect, PM, and Security agents run in parallel. Synthesis agent combines all perspectives into a detailed GSD-style PLAN.md with Tensions section.
Fix engine for PR review comments. Fetches review comments (Gemini bot or human), categorizes by impact, posts a prioritized fix queue, and applies fixes on dev approval. Called directly for quick fixes, or internally by pr-review-agent as part of full PR review.
Unified development and design standards. Enforces code quality (complexity < 8), strict naming conventions, and the mandatory use of approved UI component libraries.