Autopilot for spec-driven development. The human signs off and merges; planwright flies the spec. Scales to a multi-spec fleet: an agentic software factory on Claude Code primitives.
★not rated 4▲
+1
changed todayA
tokens not measured
originalMIT
AI coaching skills for PM business acumen — metrics design, unit economics, P&L translation, business models, and ROI modeling. Each skill coaches you through the thinking with scoring rubrics, real coaching exchanges, and pushback on weak reasoning.
★not rated 4▲
+1 19d agoA
tokens not measured
originalMIT
A read-only plugin that maps the locations, progress stages, and dependencies of seven related projects. A dependency is a link showing that work in one project affects or precedes work in another.
A plugin for beginner “vibe coders”—people who build software by directing an AI with natural-language prompts. It provides a plan-first workflow, simple review, and safety defaults for Claude Code and Codex.
★not rated 4▲
+3
changed 6d agoA
tokens not measured
Awesome professional skills for Consultants, Trainers, Coaches, and Facilitators, enhanced with McKinsey, Training from the Back of the Room, ORID, and NLP methodologies.
★not rated 4 4mo agoA
tokens not measured
originalMIT
Thought refinement workflow with clarification and Socratic examination. Orchestrates brain dump clarification through rigorous but honest intellectual exploration.
★not rated 4 yesterdayA
tokens not measured
originalMIT
Development workflow skills for the jackin project: spec-driven feature workflow, pull requests, research, release management, validation, and changelog generation.
★not rated 3 9d agoA
tokens not measured
originalApache-2.0
Keel — an AI fractional-CTO advisor for product builders who don't have a senior technical voice in the room. Eight skills across the founder journey: first-build-scope, feature-decision, tech-evaluation, architecture-review, deep-review (repo-aware four-lens flagship), enterprise-ready, estimate-check…
★not rated 3 1mo agoA
tokens not measured
originalMIT
Loop engineering wizard for Claude Code. Answer 3 questions and Claude orchestrates a self-assembling, fully autonomous 8-agent team until your goal is met — for any domain, not just code.
Finds the engineering controls your repository does not have — CI that never runs on pull requests, a check target that quietly rewrites files, a migration with nothing in front of it — and hands back a numbered plan. Advisory: it changes nothing until you pick.
★not rated 3 15d agoA
tokens not measured
originalMIT
An operating system for cognition: 135 composable Agent Skills that encode transferable thinking procedures (reasoning, decision-making, research, analysis, forecasting, creativity, communication, collaboration, learning, metacognition, ethics), routed through a better-thinking dispatcher backed by a machine-readable…
★not rated 3▲
+1 28d agoA
tokens not measured
originalMIT
Lateral-thinking skill for AI coding agents. Breaks debugging tunnel vision by surfacing end goals, solution horizons, and goal-appropriate alternatives across three tiers: Grounded, Balanced, and Wild.
★not rated 3 1mo agoA
tokens not measured
originalMIT
AI-assisted product development framework. Guides from vague idea to technical spec through structured UX research, hypothesis formation, and prototype planning.
★not rated 3 7d agoA
tokens not measured
originalApache-2.0
Skills that add lifecycle gates around planning and building with Claude Code: ground a plan in reality, verify a finished diff with fresh eyes, audit injected context, set up per-repo permissions so you can run auto mode with confidence, and turn a non-technical colleague's bug report into a well-formed issue written.
★not rated 3 9d agoA
tokens not measured
originalMIT
A collection of artificial-intelligence skills for structured thinking, decision reviews, debates, writing, product work, design, and engineering leadership.
★not rated 3 3mo agoA
tokens not measured
originalApache-2.0
Long-running autonomous coding harness with Planner-Generator-Evaluator architecture and Sprint decomposition. Builds complete applications from simple descriptions.
★not rated 3 1mo 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: