MCP App StoreMCP App StoreSKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags
crucible
Adversarial review skill: iteratively attack artifacts (designs, plans, code, docs) and surface fatal/significant issues until clean or escalation.
solana-vibes-kit
Controlled change-management for large codebase modifications: guided brief → analysis → mapping → phased execution to avoid regressions and missed impacts.
paperclip
Run a product-focused forensic investigation on stalled or looping issue trees, produce a root-cause write-up and an approval-gated remediation plan without shi
claude
Break complex systems into components, map relationships, and reconstruct optimized configurations to identify bottlenecks, failure points, and redesign opportu
compozy
Interactive skill to create Product Requirements Documents through structured research and user-driven brainstorming.
sd0x-dev-flow
Problem-space requirements analysis: 5-Why decomposition, stakeholder scan, FR/NFR structuring and a lifecycle 1-requirements.md output to inform tech specs.
ris-claude-code
Run a structured weekly retrospective: gather facts from repos and tools, interview the founder, and turn decisions into canonical files and issues.
ask_why
A planning skill that turns vague requests into traceable decision rounds, producing PLAN.md, DECISIONS.md and FINAL_PLAN.md to guide complex, iterative work.
swarms
Facilitator-focused procedure to close stuck review findings by requiring concrete evidence or concession, enforcing finality once decided.
ai-driven-development
A structured "thinking OS" for rigorous problem decomposition, decision-making, and cross-disciplinary reasoning using bounded contexts, trust scoring, and mult
marketplace
TDD-driven workflow patterns and phase-checkpoint protocol for Conductor-style task tracks: tests-first, checkpoints, git commit conventions, and verification s
claude-code-maestro
Governance protocol that turns an agent into an architecture-focused conductor, enforcing init checks, planning, and verification for complex code tasks.
neurofoo
Run a Start-Stop-Continue retrospective to identify actions to start, stop, and continue for a project or period.
x-cmd
Interactive process viewer for the shell with fzf integration, AI-powered filtering, and CSV/JSON/TSV output for pipelines.
galyarder-framework
Dispatches a focused code-review subagent and provides a template-driven process to request reviews before merges, feature completion, or risky changes.
gstack-ko
Interactive, designer-eye review of design plans: rates dimensions, finds gaps, and edits the plan to add missing UI decisions and interaction states.
claude-skill-registry
Designs high-performing team structures using organizational psychology, maps skills and roles, and creates new skills on-the-fly to fill capability gaps.
dots
Absorb external signals (articles, observations, ideas, failures) into the global agent harness: extract insights, map gaps, apply fixes, and measure absorption
skills
Design, optimize, and execute repeatable workflows — onboarding, content production, support triage, and more. Natural-language to structured process plans.
galyarder-framework
Compatibility/adapter skill that maps legacy `remotion-engineer` capability names to the modern runtime and enforces the framework’s operational protocols.
use-case-writer
Generate structured Use Case specifications in English Markdown using the 13-field IT BA template; enforces scoping rules and a 20-point quality checklist.
book2skills
Guides creators to overcome blocks, ethically remix influences, and build a sustainable daily creative practice using Austin Kleon's principles.