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
Install or update OwnMem in the current repository. Use when the user asks to set up OwnMem, add local project memory for coding agents, or refresh an existing OwnMem installation after a version bump.
Skill Claude Code
Take a Flutter project to an iPhone or the App Store with Odevio - build, sign and publish iOS apps from Windows, Linux or macOS with no Mac and no Xcode. Handles Apple setup, certificates, provisioning profiles, code signing, the .ipa, TestFlight, App Store submission, the App Store listing and its screenshots …
TheSyart/claude-agent-examples
Skill Claude CodeCodex
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Skill Claude CodeCodex
Example skill loaded from resourcesdiscover.
Skill Claude CodeCodex
A tool for setting up and maintaining project engineering rules stored in .ai-rules files, and checking code against them.
Skill Claude CodeCodex
Create, synthesize, and iteratively improve agent skills following the Agent Skills specification. Use when asked to "create a skill", "write a skill", "synthesize sources into a skill", "improve a skill from positive/negative examples", "update a skill", or "maintain skill docs and registration". Handles source…
Skill Claude CodeCodex
Grade a periodic outbound flow as c2, suspicious, or benign-periodic. Read this when rawdata shows a repeating connection and you must separate a beacon from NTP, an update check, a monitoring agent, or telemetry.
Skill Claude CodeCodex
Build and maintain a Markdown guide that helps humans understand a repository through real behavior, concepts, and evidence. Use when a user asks to understand a repo, generate or update repo-docs, answer repo-architecture/onboarding questions, seed docs for a new project, sync docs after code changes, or delete…
Skill Claude Code
Deep persona design for Agentforce agents with 50-point scoring. TRIGGER when: user designs agent personas, defines agent personality/identity, creates persona documents, encodes persona into Agentforce Builder fields or Agent Script, translates brand guidelines to agent voice, or asks about agent tone/voice/register.…
Skill Claude CodeCodex
Connect any AI agent to MCP servers through mcptoon — one config synced everywhere, one stdio gateway, 99.2% fewer tokens on tool discovery.
Skill Claude CodeCodex
Classify and format resources from temp.md into tempentries.md; insert staged entries into section/.md only on explicit request. Use for staging or landing new knowledge-base entries, not restructuring sections or refreshing generated lists.
Skill Claude CodeCodex
Analyzes and safely cleans up local Git branches. Categorizes branches by merge status, staleness, and remote tracking. Provides interactive selection with safety guards. Use when the user wants to clean up branches, delete old branches, organize Git branches, or asks about which branches can be safely deleted.
amanattar/caveman-claude-skill
Skill Claude CodeCodex
Ultra-compressed communication mode. Cuts token usage 75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or…
HuangYuChuh/ComfyUI_Skills_OpenClaw
Skill Claude CodeCodex
Run registered ComfyUI workflows through the fast comfyui-skill CLI, and use the official local Comfy MCP for live template, node, model, validation, and orchestration capabilities. Use this Skill when: (1) The user requests to "generate an image", "draw a picture", or "execute a ComfyUI workflow". (2) The user has…
Skill Claude CodeCodex ✓ vendor
Add existing screenshots or screen recordings to a GitHub pull request as a before/after or preview block. Use when a PR needs visual media attached to its description. Browser navigation and capture belong to agent-browser.
Skill Claude CodeCodex
Convert long-form Markdown (plan, spec, system design, RFC, runbook, postmortem, brainstorm, notes) into a single self-contained HTML page with Mermaid diagrams, step timelines, callouts, sidebar TOC. Claude-orange light+dark theme. Multi-language. Portable across Claude Code / Codex / Antigravity / any AI agent.
Skill Claude CodeCodex
Write programs in the Vera programming language. Use when asked to write, edit, debug, or review Vera code (.vera files). Vera is a statically typed, purely functional language with algebraic effects, mandatory contracts, and typed slot references (@T.n) instead of variable names.
Skill Claude CodeCodex
Compatibility entry for the moved Codex ReHome Skill. Read CalebYcj/codex-rehome-skill before performing migration work.
Dominic789654/awesome-deepseek-harness
Skill Claude CodeCodex
A bounded research workflow that repeats four steps: planning, searching, reading, and combining findings. It records each step and its sources so the work can resume after an interruption.
Skill Claude CodeCodex
Use the existing Aholo Lux3D MCP server to check balance, quote and create 3D or image tasks, and retrieve results.
Skill Claude CodeCodex
Podcast knowledge workflows powered by Podwise CLI: search podcasts and episodes by keyword, monitor followed shows for new releases, find popular episodes, ask questions and extract insights from transcript content, process Podwise episode URLs, YouTube videos, Xiaoyuzhou links, and local audio or video files to…
Skill Claude CodeCodex
Produce an implementation plan at .turbo/plans/ .md. Use when the user asks to "draft a plan", "draft the plan", "write an implementation plan", "plan this change", "create an implementation plan", or needs a first-draft plan file before refinement.
sssmmmwww/wxmini-security-audit
Skill Claude CodeCodex
A complete static security-audit workflow for WeChat Mini Programs, using several specialised agents and preliminary scripts.
Skill Claude Code
A guide for creating interactive visual components with HTML. These components can respond to user actions, animate ideas or display data.
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: