Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 375,717 indexed, measured the same four ways as everything else here.
Refine an early idea or creative concept into a coherent, evidence-aware design and durable Markdown master spec/PRD. Use when the user wants to explore, challenge, clarify, or develop an idea before implementation, including related-work research, core-mechanism design, product design, maturity progression, or…
Structured development skills for any project. Provides brainstorming, planning, parallel agent development, browser testing, systematic debugging, and self-improvement workflows.
★not rated 17 3mo agoA
tokens not measured
GPL-3.0
Create flexible annotation workflows for AI applications. Contains common tools to explore raw ai agent logs/transcripts, extract out relevant evaluation data, and llm-as-a-judge creation.
Production-grade engineering gate for writing OR reviewing code. Enforces security, resource safety (memory leaks, unclosed listeners/streams/timers), efficient data access (N+1, pagination/infinite-scroll, over-fetching, backend cost), defensive coding, and evidence-based verification. Use when the user invokes it…
Coding-agent skill for Microsoft Power Platform and Dataverse development. Read a repo, understand model-driven app and solution structure, choose the right development surface, and safely build, validate, and deliver source-controlled changes: plug-ins, PCF controls, web resources, form and ribbon metadata…
★not rated 17 2mo agoA
tokens not measured
originalApache-2.0
Skill "lark-agent-simple" from Interstellar-code/claud-skills, covering lark agent simple skill, architecture, token efficiency design, component roles and when to use this skill.
Audit Waniwani event tracking across an MCP project. Does an in-depth overview check of the whole app (server, flows, tools, widgets, chat embed), verifies that only events defined in the Waniwani taxonomy are sent, and identifies missing events worth adding at each funnel stage (identify, leadqualified, priceshown…
Isolate read-only CCG search, documentation discovery, and analysis by namespace. Use when working across multiple repositories or services, preventing cross-project graph leakage, federating supported reads, or traversing materialized cross-namespace references. Do not use for graph writes or scoped updates; the user…
Collection of example skills demonstrating various capabilities including skill creation, MCP building, visual design, algorithmic art, internal communications, web testing, artifact building, Slack GIFs, and theme styling.
★not rated 17 1mo agoA
tokens not measured
originalApache-2.0
Tactical AI-native SDLC layered on Claude Buddy — Cole Medin's R-PIV loop (Research, Plan, Implement, Validate) for brownfield projects, with epic/story/task decomposition in Jira & Confluence and GitHub as source control via MCP. A complement to buddy: reuses its Foundation, adds a checked-in AI layer (lean CLAUDE.md.
★not rated 17 1mo agoA
tokens not measured
originalMIT
Write GEO/AEO-optimized SEO blog articles end-to-end and publish them to headless WordPress as drafts. One command researches the topic, writes the article, captures real product screenshots, generates a branded featured image, and uploads a Rank Math-ready draft. Invoke with /seo-blog-writer:blog-writer.
★not rated 16▲
+1 3mo 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: