Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 372,591 indexed, measured the same four ways as everything else here.
Recommend a small set of candidate skills or artifact-generation pipelines for an open-ended task, then compare their outputs so the user can decide what actually helps. Use when the user is unsure if a particular skill would improve their output, when comparing 2+ skills for the same task, when they naturally ask to…
Conducts a structured technical deep-dive to gather detailed requirements, constraints, and decisions from the user. Use when starting a complex feature or when the user wants to be asked structured clarifying questions before implementation.
A strict editorial reviewer that checks writing principles inspired by George Orwell's "Politics and the English Language" rules and Matthew Butterick's Practical Typography. Use this skill whenever the user says "red pen", "check my prose", "edit this for clarity", "typography check", "tighten this up", "review this…
Provides concise spoken alerts and digests through the mcp-tts MCP server. It should be selected proactively for significant AI and DevOps transitions: a substantial plan is ready, a long build/test/deploy/release/monitoring phase changes state, a major task completes, a terminal blocker or exhausted retry budget…
Be a design director, grounded in OpenDesign (opendesign.cc) — a curated library of 1,400+ real, machine-readable design systems, each with an 11-layer token spec extracted from the live site and verified against actual computed styles. Use whenever someone wants to design or build a website, landing page, dashboard…
Agent skills for 37signals products, each driving its product's CLI. Bundles the Basecamp skills today; HEY and Fizzy join as their CLIs publish here (see the README).
★not rated 72▲
+3
changed 6d agoA
tokens not measured
Determine whether AI is appropriate for a specific e-commerce task. Use when evaluating if a problem has enough data, the right tools, or acceptable risk for AI automation. Answers 'should I use AI for X?' with boundary-aware reasoning.
★not rated 72▲
+3 3d agoASkillSpector: pass53 tokens
originalCC0-1.0
Edit the thurbox TUI — add, change or remove a pane of the running interface, which is Lua files in the thurbox interface directory (not this repository). Use whenever the user asks to change how thurbox itself looks or behaves on screen — a new pane or panel, a different layout or arrangement, a keybinding, a status…
Build, launch, screenshot, and drive the wenlan-app Tauri desktop app in dev mode on macOS (WKWebView) or Windows (WebView2). Use when asked to run or start the app, verify a UI change in the real running app (not just tests), or take a screenshot of it.
Clarify-first discipline for Claude Code: the chair asks every question a job raises at the start, in rounds, and records the answers under ## Clarified in a Requirements Ledger before anything is delegated. Guard hooks enforce it mechanically — serious delegation is denied until the record exists, the first turn-end.
★not rated 72
changed 9d agoA
tokens not measured
originalMIT
The precise design and UI vocabulary used on index.how/to/articulate — covering typography, color, iconography, layout, interaction, motion, accessibility, information architecture, copywriting, tools, analysis, and components. Use when reaching for the exact word for a design concept ("what's the term for the space…
Adversarial reviewer for auth boundaries, secret handling, injection paths, and privilege escalation. Use proactively before merging any change that touches auth, privileged access, external input parsing, CI workflows, or agent-facing surfaces.
MCP server "co-reading-kit" as configured in Youxuuuuu/co-reading-kit. Runs locally from the co-reading-kit npm package.
★not rated 72 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: