Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
Skill Claude CodeCodex
Use this skill for long tasks, multi-step coding tasks, batch fixes, refactoring, productization, requirement refinement, task planning, handoff, final verification, preventing missed requirements, and continuing interrupted work.
alentodorov/findskill-meta-skill
Skill Claude CodeCodex
A meta skill that teaches AI agents how to discover, install, and use skills from the findskill.md ecosystem. Use when you need to extend capabilities by finding specialized skills, when a user asks to perform tasks that would benefit from specialized skills, or when explicitly asked to find or install skills.
adrunkhuman/marimo-opencode-skill
Skill Claude CodeCodex
Author interactive reactive Python notebooks with marimo. Covers interactive cell execution, reactive UI, SQL, state management, deployment, and export. For interactive notebooks, NOT Cell.run() API.
Skill Claude CodeCodex
Automate airline check-in via local CDP-controlled Chrome. Handles KTN, loyalty, baggage, and survey popups. Resilient to anti-bot WAFs that block cloud browser agents.
tanglele110-hash/zhongguose-ppt-skill
Skill Codex
A presentation-making system inspired by traditional Chinese colours and layouts, with Chinese-led bilingual content and interactive HTML or PowerPoint output.
BaiTianHaoNian/feishu-classmate
Skill Claude CodeCodex
An automated weekday stand-up process for a laboratory. It gathers yesterday's progress, today's plans, and blockers, then posts a summary to the lab's group chat at 09:30.
Skill Claude Code
Generate DeepWiki-style repository analysis reports. Deeply analyze codebase architecture, module dependencies, and core systems, outputting structured documentation with Mermaid diagrams, source file references, and tables.
Skill Claude Code
Run parallel multi-agent code review via Solo MCP — replicates the counselors tool (https://github.com/aarondfrancis/counselors) without depending on claude -p. Use when the user asks for "counselors", "second opinion", "panel of experts", "parallel review", or "multi-agent analysis" — fan the same task out to several…
Skill Claude CodeCodex
Codex-first multi-agent production pipeline for non-trivial implementation work. Uses spawnagent to run Spec, Plan, Architecture, Execution, Review, and Doc subagents, persists artifacts in .pipeline-workspace/, and loops Execution and Review until the change passes. Use when the user wants a feature, refactor, or…
Skill Claude CodeCodex
Ingest and analyze content from YouTube, podcasts, blogs, PDFs, and audio files. Extract structured insights using parallel agent teams. Generate Show Notes and Cheat Sheet HTML variants. Use /research-extract when you want to analyze any content source and extract key insights, quotes, themes, challenges, solutions…
paranoiaccc/figma-fidelity-guard
Skill Codex
Audit and recover incomplete Figma design evidence before fidelity-sensitive implementation or review. Use when design context is truncated, depth-limited, sparse, inconsistent with the rendered result, or missing nested layers, styles, assets, variables, effects, variants, or responsive behavior. Do not use for…
anthony-at-pieces/pieces-mcp-playbook-skill
Skill Claude CodeCodex
Connect to the Pieces MCP server (StreamableHTTP or SSE) and interact with the full Pieces data plane -- work-history retrieval via searchmemory/askmemory/askpiecesltm, targeted full-text and vector search across workstream events/summaries/conversations/annotations/tags/websites, batch snapshot retrieval, browser…
Skill Claude CodeCodex
Local test harness only — points brain-trust-cli at materialized assets.
lijiawei255/agent-edu-reviewkit
Skill Claude CodeCodex
A course-material workflow that turns extracted text and images from PDF, PowerPoint, or Word teaching files into HTML study and exam-prediction documents.
Skill Claude CodeCodex
Join and interact with CrabSpace - the MySpace-style social network for AI agents. Use when creating a profile, customizing appearance, managing friends, or posting on comment walls. Handles registration, tweet verification, profile updates, and social features.
Skill Claude CodeCodex
Intelligent code security scanner with hybrid local-cloud detection. Fingerprints packages, runs static behavioral analysis, and consults cloud threat intelligence (enabled by default, can be disabled) for confidence scoring.
Skill Claude CodeCodex
Helps users create new Dataverse business skills by converting natural-language descriptions of business processes into well-structured skill definitions and saving them to the environment. Use when user says "create a new skill", "I want to build a skill", "help me define a skill", "add a business skill", "make a…
tmdgusya/hermes-skill-kimi-cli
Skill Claude CodeCodex
Delegate coding tasks to Kimi CLI (Moonshot AI's coding agent). Use for building features, fixing bugs, refactoring, PR reviews, and batch processing. Supports non-interactive print mode, session management, and subagents. Requires kimi-cli installed and authenticated.
Skill Claude CodeCodex
Organize, categorize, deduplicate, and clean up browser bookmarks using Chrome's native Bookmarks API via AppleScript. Use when the user asks to organize bookmarks, clean up bookmarks, sort bookmarks, find duplicate bookmarks, or manage their browser bookmark collection.
Skill Claude CodeCodex
Manage Zilliz Cloud vector databases via zilliz-cli. Use when the user wants to: (1) set up zilliz-cli (install, login, configure), (2) manage clusters (create, list, describe, suspend, resume, delete, modify), (3) manage collections, indexes, partitions, databases, or aliases, (4) perform vector operations (search…
Skill Claude CodeCodex
Use when the user asks to search Perplexity, query Perplexity through the web UI, perform web research with Perplexity, save a Perplexity answer as Markdown, or retrieve a Perplexity answer through browser automation.
Skill Claude CodeCodex
Single entry point that routes any Stripe billing, subscription, MRR, churn, payment failure, dunning, Radar fraud, checkout, invoice, payout, webhook, or pricing question to the correct specialist skill. Use FIRST when the user mentions Stripe, MRR, ARR, subscriptions, churn, past due, failed payment, Radar…
Skill Claude CodeCodex
A workflow for grading exams through a conversation with the coding agent. It can process folders of exam files, calculate scores, and export grading results.
Skill Claude CodeCodex
Use only when the user explicitly says ZOOT or explicitly asks to use the research vault setup skill to set up a new lightweight Obsidian-first research vault. Do not use for ordinary Markdown, Obsidian, wiki, process-log, research, derivation, coding, hook-maintenance, or summarization tasks.
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: