Feature lifecycle management with state, search, epic dispatch, and review gates. Capture ideas, plan, and ship as files (idea.md → plan.md → shipped.md) with orthogonal state (active/paused/replaced/abandoned). Single-feature autopilot and parallel-wave epic dispatch — every subagent in its own worktree, with a local CI-parity preflight gate before every push. Per-feature review override (external Gemini/Codex CI / internal subagent / skip). Auto-generated DASHBOARD.md with Paused, Epics, and Validation Warnings sections. Multi-repo workspaces: an aggregated cross-repo dashboard, cross-repo epics, contract-edit warnings, and coordinated producer-first deploy.
18 skills · 12 agents · hooks
Guided workflow to deploy Node.js/Express apps to AWS serverless architecture. Analyzes your app, scaffolds infrastructure, and deploys with CDK — all with step-by-step explanations for beginners.
9 skills · 1 agent · 2 MCP servers
Write, revise, and push blog posts to a Ghost site from Claude Code — a Ghost Admin API MCP plus a plan→draft→revise→push skill set.
7 skills · 1 MCP server
Evergreen engineering standards I hold code to — the judgment layer that AI-slop resistance needs on top of the mechanical quality stack. Project-structure conventions (consistent layout + naming so every repo looks the same), worktree isolation (every line of work in its own tree so parallel work never collides), and GitHub API discipline (zipball over per-file, rate-limit backoff), with automation-auth (GitHub App vs PAT) and hook-escape conventions on the way. Pure advisory skills that fire when the situation matches — no tooling, no setup, safe to leave enabled for a project's whole life. Backed by lessons from real incidents.
6 skills
Sprint planning and team coordination. Triage backlogs by deadline, assign work with self-service specs, audit feature specs for completeness, and generate team communication. Designed for small teams with mixed experience levels.
5 skills
Sister to feature-workflow for code-quality findings. Surfaces, triages, and resolves static-analysis output (skylos for Python, fallow for TS/JS) with the same backlog-and-epic discipline. User-invocable skills: /quality-verify-hook self-tests pre-commit hooks against known-bad fixtures (catches the silently-misconfigured-hook class of bug), /quality-audit produces fingerprinted snapshots + NEW/RESOLVED/PERSISTING delta (suppressed findings excluded from active counts), /quality-unblock triages failing hooks with playbook-driven fix/suppress/defer proposals and refuses bare suppressions. Plus the language-agnostic suppression-discipline standard (every ignore carries an inline rationale). Day-1 playbooks for 13 skylos + 12 fallow rule_ids.
4 skills