Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 389,611 indexed, measured the same four ways as everything else here.
Skills for engineering custom Buildkite plugins and designing scalable, secure, dynamic pipelines. For plugin developers and DevOps/platform engineers.
★not rated 2 3mo agoA
tokens not measured
originalMIT
Codebase analysis, reverse engineering, and development orchestration — 32 skills covering reconnaissance, deep investigation, TDD, debugging, planning, and code review.
★not rated 2 7mo agoA
tokens not measured
originalMIT
A general spec-driven software development workflow for Claude Code: detect project domain/conventions, research, weigh solution options, plan, implement in reviewed phases (code review every phase; a security scan whenever a phase touches a sensitive surface), and run a final cross-phase security audit. Stops for…
★not rated 2
changed 10d agoA
tokens not measured
originalMIT
Ferramentas de manipulação de imagens — split/separação de elementos, remoção de background, remoção de watermark, redimensionamento, rotação, flip, crop, trim, padding, ajustes visuais e conversão de formato.
★not rated 2 14d agoA
tokens not measured
originalMIT
Skills for COMP4020/COMP8020 Agentic Coding Studio students: setting up the course environment, tracking budget and deadlines, and getting each week's deliverable started, checked and shipped. Ships no hooks; the optional status line lives in the companion comp4020-statusline plugin.
Adds GLaDOS as an external observer who occasionally interjects with a short, passive-aggressive footer. Claude remains Claude; GLaDOS is a guest voice, always tagged [GLaDOS]:.
★not rated 2 5mo agoA
tokens not measured
originalMIT
Claude Code skills for building reliable day trading bots: event-driven architecture, order execution integrity, position reconciliation, risk management, market data pipelines, backtesting, and fail-closed engineering practices. Encodes hard-won lessons from production trading bot failures.
Captures and retrieves the decisional context behind code changes — constraints, choices, and reasoning — so future agents don't repeat mistakes or lose established patterns across sessions.
★not rated 2 5mo agoA
tokens not measured
originalMIT
Enterprise-grade software development agents covering the complete SDLC lifecycle. Includes expert-level specialists (frontend, backend, algorithm, QA, etc.) and VP-level coordinators for cross-team orchestration.
Comprehensive documentation toolkit with specialized agents for bulletproof software documentation across backend, frontend, API, database, architecture, tests, user guides, compliance, and mobile domains.
★not rated 2
changed 28d agoA
tokens not measured
originalMIT
★not rated 2 4mo 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: