Persistent project planning files with lifecycle hooks that inject selected plan context. Automatic recovery uses project files only. Explicit catchup modes may read same-project local session records to emit aggregate counts or bounded nonce-framed excerpts. Optional gated mode can request continuation on capable…
★not rated 27k▲
+101
changed todayA
tokens not measured
originalMIT
AI Shipping Kit — for PMs and founders accountable for AI-built code. Document a vibe-coded app, review it for correctness, security and performance defects, and produce a reviewer-ready shipping packet.
Claude Code skills based on The Minimalist Entrepreneur by Sahil Lavingia. Frameworks for building a profitable, sustainable business starting from community.
Point it at a codebase and it figures out what's worth doing — bugs, perf, tech debt, what to build next — then writes plans any agent can execute. It can hand the work to a cheaper model and review the result. It never edits your code.
★not rated 9.2k▲
+14 1mo agoA
tokens not measured
originalMIT
The team-architecture factory for Claude Code v2 — a meta-skill that turns a domain description into an agent team and the skills they use. Three native execution modes (Workflow orchestration, persistent named-agent collaboration, sub-agent delegation), six team-architecture patterns, and workflow-native quality…
Sits in front of Claude Code and fixes the brief before the code. An interview scores how vague your request is, and a score above the bar blocks spec generation until you pass force explicitly. When an acceptance criterion defines a verify command or an expected-output assertion, those values are omitted from the…
★not rated 6.2k▲
+36
changed todayA
tokens not measured
originalMIT
Interview the user to design an agentic control loop (sensor, controller, actuator under disturbances) for their codebase, then build it as locally-runnable components plus a scheduled coding-agent workflow.
★not rated 5.3k▲
+126 9d agoA
tokens not measured
originalMIT
A collection of coding-agent skills for practical software engineering, including test-driven development, code review, debugging, design, and specification work.
18 AI personas deliberate your hardest decisions — structured multi-round deliberation (blind analysis, anonymized cross-examination, weighted verdict) with genuine model diversity across providers.
★not rated 4.7k▲
+62 6d agoA
tokens not measured
originalMIT
Parallel divergent ideation for coding agents: fans out isolated branches under different cognitive frames, scores, clusters, prunes traps, and deepens the survivors.
★not rated 4.4k▲
+41 12d agoA
tokens not measured
originalMIT
If you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence. Ported from cursor/plugins/pstack to Claude Code. Original pstack by Lauren Tan (poteto).
★not rated 2.8k▲
+956
changed todayA
tokens not measured
originalMIT
Fourteen guided journeys that orchestrate the whole skill library step by step — create, improve, and grow a business, website, or app, plus improve code quality, remove technical debt, design code architecture, optimize a conversion flow, and optimize an existing codebase for speed and structure. Each metaskill…
★not rated 2.5k▲
+64 1mo agoA
tokens not measured
originalMIT
if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence.
Kubb turns your API spec into type-safe code. Generate TypeScript types, Zod schemas, Axios and fetch clients, React Query and Vue Query hooks, Faker mocks and more from an OpenAPI spec. The commands run the Kubb CLI, and a bundled MCP server adds conversational generation.
★not rated 1.8k▲
+6
changed yesterdayA
tokens not measured
originalMIT
28 eval-informed mental models and critical-thinking skills for Claude Code, GitHub Copilot, Codex, Cursor, and other Agent Skills-compatible tools.
★not rated 1.6k▲
+30 2mo agoA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: