Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 387,694 indexed, measured the same four ways as everything else here.
Search trusted local private or team Agent Skill collections when reusable instructions may exist outside the active skill catalog. Resolve only the selected SKILL.md instead of loading every skill into agent context.
Turns vague "act as an expert" requests into fully-specified expert engagements. Builds a precise expert persona — specific role and seniority, industry and domain context, named methodologies, real operating constraints, and a required output format — then executes the task in that mode, or produces a reusable expert…
A positioning operator for builders who can ship the thing but still need the market to understand why it matters. Diagnoses the customer, substitute, proof, timing, and sacrifice before writing copy, pressure-tests you against rivals' real copy, won't ship claims you can't prove, and always ends with your next move.…
Use when the user provides any kind of feature spec (rough notes / system design / partial spec / canonical PRD) and wants it implemented end-to-end autonomously on the Kimi Code CLI (AgentSwarm-engined), or invokes /kimi-mp-implement.
Write and structure high-quality Open Knowledge Format (OKF) concepts for a librocat library. Use when creating or editing knowledge with the librocat MCP (ingest/update): choosing a concept type, writing a one-sentence summary, adding cross-links, and applying progressive disclosure. Trigger when the user asks to…
Fast browser automation CLI for AI agents. Chrome/Chromium via CDP, no Playwright or Puppeteer dependency. Accessibility-tree snapshots with compact @eN refs let agents interact with pages in 200-400 tokens instead of parsing raw HTML.
Audit and fix performance on live WordPress sites across whatever stack they actually run — page builders, caching layers, CDNs and managed hosts. Fingerprints the stack, separates origin from edge TTFB, and applies fixes only under a guarded write loop with a rollback for every change.
Distinctive, production-grade frontend design with bold aesthetic direction, curated palette/typography/layout presets, and a structured design-direction flow. Use whenever building or refining UI (landing pages, product surfaces, marketing sites, dashboards) — especially when the brief is visual, broad, or "make it…
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
Intelligent Agent-Skill dependency butler: discover, security-audit, and install Agent Skills into your project. Scans tech stack, plans a vetted combination, audits each skill, and installs per-agent.
★not rated 2 5mo agoA
tokens not measured
originalMIT
A systematic engineering methodology for coding agents. Teaches where to look when researching a codebase, how to plan before coding, how to verify work instead of assuming it is done, how to debug from evidence, and how to sustain long autonomous tasks across sessions without losing state. Use when writing or…
Explain a concept, feature, ticket, or implementation in plain language, grounded in verified source — separating how it works today from what it's meant to become, and flagging assumptions instead of guessing.
★not rated 2
changed 27d agoA
tokens not measured
originalMIT
Reference for the Ada Diamonds public REST API (https://www.adadiamonds.com/api/v1) covering every endpoint, self-serve API keys and OAuth 2.1 scopes, the public sandbox key, rate limits, error shapes, versioning, and working curl examples. Use when integrating with Ada Diamonds over HTTP, generating client code…
Workspace setup and organization assistant for ClawPad users. Triggers on: (1) First-time setup - "just set up ClawPad", "new workspace", "help me organize" (2) Project creation - "new project", "create folder structure" (3) Workspace maintenance - "reorganize", "clean up workspace", "where should I put" (4) Document…
Hybrid prompt linter — deterministic Node detector for 18 of 20 rules plus an LLM model layer for PR003, PR009, and semantic cases of PR002, PR005, and PR010. Lint, don't rewrite. Markdown or JSON output, suppression comments, baseline mode, conformance corpus (25 cases), CI recipes. Never imposes a framework, never…
★not rated 2 6mo agoA
tokens not measured
originalMIT
A planner for finding social-media content topics, headline ideas, and outlines based on an account's focus and audience. Xiaohongshu is a Chinese social lifestyle platform.
Use when the user wants a build or architecture idea stress-tested before they commit to building it — "help me plan/design this app", "design the architecture for X", "review my architecture before I build", "is my mental model of X sound", "I want to build Y because Z — poke holes in it". For the still-articulating…
A document-publishing workflow for planning, creating, converting, checking, and preparing reports, proposals, manuals, white papers, and brand documents for release.
★not rated 2 2mo agoA49 tokens
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: