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
Makes a repository AI-native by creating AGENTS.md, .cursorrules, and documentation that helps any AI agent understand the codebase. Follows the WHAT/WHY/HOW framework from best practices. Use when the user asks to "make repo AI-ready", "add cursor rules", "create AGENTS.md", "set up for AI coding", or "make agents…
Skill Codex
A read-only assistant for organizing English email, especially messages from services such as Microsoft 365. It translates messages into Chinese, extracts keywords and deadlines, classifies them, and creates summaries and calendar files.
Skill Claude CodeCodex
Independently verify a formal PR with risk-based QA and record the decision in the PR.
netgrade-digital/shared-agents
Skill Claude CodeCodex needs its repo
Complete guide to the shared-agents shell CLI (sa). Use when the user asks how to run sa, sa help, install, sync, review, pending, unapprove, check, uninstall, status, or any shared-agents terminal command. Also use when explaining setup, wizard, or troubleshooting the CLI after sa install.
Yudai-ASANO/cursor-my-settings
Skill Claude Code
A structured interview for plans and designs, including implementation work, repository changes, documents, and processes.
solkit70/VL_for_AI4PKM_Automation_Features
Skill Claude Code
Format and validate Obsidian wiki links with proper filename, section, and folder conventions. Verify links exist before creation and fix broken links. Use when creating or checking wiki links in markdown files.
Skill Claude CodeCodex
Design or update a specialized Codex harness: define role-specific agents, generate an orchestrator skill and AGENTS.md, and connect work to the shared to-spec/to-issues tracker contract. Use for requests to build a Codex harness, create a Codex agent team, or change an existing harness's roles, workflow, or project…
Skill Codex
Design and build websites with film-inspired visual systems, director-driven art direction, storyboard-first layout planning, and cinematic motion. Use when the user asks for a cinematic site, movie-style landing page, director-inspired UI, film-noir, sci-fi, romance, thriller, action, animation, or a movie-like…
Skill Claude Code
Automated testing execution using OpenTester DSL. Use when the user wants to create tests, run tests, validate test syntax, or manage test projects. Supports CLI testing with a YAML-based DSL.
crcresearch/llm-wiki-memory-template
Skill Claude Code
File experiment results to the wiki following the SCHEMA Ingest procedure. Use after an experiment run produces metrics, ablations, or comparisons worth keeping as durable project memory.
Skill Claude CodeCodex
Professional meeting scheduling and coordination assistant.
hajekim/agentic-design-patterns-skills
Skill Claude CodeCodex
This skill should be used when the user wants to "agent-to-agent communication", "A2A protocol", "inter-agent messaging", "agent network", "agent federation", "cross-agent calls", "distributed agent systems", "agent discovery", "agent cards", "standardized agent communication", "remote agent invocation", "multi-agent…
Skill Claude CodeCodex
Skill "flask" from rishapgandhi/python-skills, covering flask skill, stack, project structure, app factory and app/init.py.
Skill Claude CodeCodex
Write Markdown files that pass markdownlint with zero warnings. Use when creating or editing .md, .mdc, or .mdx files, writing documentation, updating README files, or creating Cursor rules and skills.
Skill Claude CodeCodex
Add persistent, interactive task plan management to your agent. Wingman tracks plans and tasks across a long conversation — Claude creates plans, ticks tasks after completing work, and a live panel renders inline in the chat. Install the MCP server first, then use these tools to manage plans and tasks throughout any…
Skill Claude CodeCodex
Token-efficient web research for AI agents. Fetches, indexes, and queries web content locally via hybrid BM25 + embeddings, returning only the chunks that fit a token budget. Replaces raw webfetch for any task involving more than one source. Use when the user asks you to research, compare, summarize, or fact-check…
Skill Claude CodeCodex
Manage your LinkedIn and Twitter presence with Reepl -- create drafts, publish and schedule posts, manage contacts and collections, generate AI images, create carousels, post to Twitter/X, and maintain your voice profile. Requires a Reepl account (reepl.io).
Skill Claude Code
Frontend design superpower for AI coders. Produces production-quality, non-slop frontends. Use PROACTIVELY when building, revamping, redesigning, or fixing any frontend UI — landing pages, SaaS, e-commerce, portfolios, dashboards, or any web interface. Detects and eliminates AI slop patterns.
Skill Claude CodeCodex
Initialize Threadbase, generate or refresh .ai/generated/context.md, and maintain shared repo memory in Codex.
floytra-dev/ultra-max-token-burner
Skill Claude CodeCodex
Expand concise requests into larger, coherent, manager-visible prompts using controlled procedural overhead.
Skill Claude Code
Remove AI-generated traces from text. Suitable for editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive guide to "AI writing characteristics." Detects and fixes the following patterns: exaggerated symbolism, promotional language, superficial analysis ending in…
Skill Codex
Use when creating Juhuo AI event promotion copy from an activity plan, Word/WPS document, or structured event brief for WeChat Official Account, Xiaohongshu, QQ channel/group/campus-wall reposts, or a full campus AI community promo package.
Skill Claude CodeCodex
Use when the user wants AI project memory, task documentation, decision records, bug history, feature notes, context recovery, or "document everything" behavior without forcing a project structure. This skill keeps engineering context recoverable and only creates project files when the user explicitly asks to…
Skill Claude Code
Retrofit Ma'at documentation onto an existing repository — inventory gaps, interview the developer, derive AGENTS.md content and retrospective ADRs.
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: