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
Helps you use the /btw (or /qq) side-conversation workflow. Use when you want to think in parallel, ask side questions without interrupting ongoing work, or inject a side thread back into the main agent.
Skill Claude CodeCodex
Six-player Werewolf rules for a permanent Agent host, with the user choosing to join the randomized player pool or spectate.
Skill Codex
Bootstrap a team's Context Tree from readable source repos — for an onboarding "build / set up the Context Tree" task on a tree that has no domain structure yet: either no tree exists (creates and binds it) or a bound-but-empty tree (fills it). Supports clean explicit-Team invocation without a Workspace manifest…
bozhouDev/video-skills-toolkit
Skill Codex
A design workflow for creating or revising cover images for Douyin, WeChat Channels, Xiaohongshu, and other short-video content. It focuses on readable titles, clear layouts, and a recognisable creator identity.
benjiyaya/Minimax-H3-Prompt-AgentSkill
Skill Claude CodeCodex
Use when making MiniMax H3 video prompts from media + ideas.
Skill Claude CodeCodex needs its repo
Conduct deep OSINT research on individuals. Build full digital footprint, psychoprofile (MBTI/Big Five), career history, social graph with confidence scores. Recursive self-evaluation until completeness threshold is met. Includes internal intelligence (Telegram history, email, vault contacts) before going external.…
Skill Claude CodeCodex
Supervised authorized pentest: scope, route, validate, report.
Skill Claude CodeCodex
Independent IVTR peer-reviewer role. The Validator is spawned by a Lead AFTER a Worker reports an implementation candidate to verify that every Acceptance Criterion is satisfied by programmatic evidence. The Validator MUST be a different agent instance from the Worker who built the change — same-agent self-attestation…
Skill Claude CodeCodex
Use when building vulnerability-based trust through quarterly team exercises from the EOS Trust Builders toolbox.
maplibre/maplibre-agent-skills
Skill Claude CodeCodex
Six places where MapLibre Native (Android, iOS) and MapLibre GL JS differ, release by release — custom URL schemes (addProtocol), globe projection, 3D terrain, interpolate-hcl and interpolate-lab, the color-relief layer, and PMTiles — with the Native release that closed each gap, the tracking issue for each still…
davidYichengWei/agentic-engineering-framework
Skill Claude CodeCodex
A requirements-clarification workflow that defines the problem, goals, requirements, success measures, and non-goals before design begins.
tech-shrimp/agent-skills-examples
Skill Claude CodeCodex
A Chinese-language workflow for converting SRT subtitle files into Markdown notes. SRT is a subtitle format containing timed lines of text.
Skill Claude CodeCodex
Installs and wires Mnemo Cortex (local-first persistent memory) into OpenClaw and other MCP-capable agents. Use for cross-session recall, decision history, or multi-agent shared memory.
Skill Claude Code
Full browser E2E + UX/UI audit of newly developed 1C objects in the live web client — discover the new interface, exercise complete user flows, evaluate UX/UI quality, analyze the browser run (screenshots/console/network), and report PASS/WARN/FAIL.
chengwesley/taiwan-stock-analysis
Skill Claude CodeCodex
A financial-analysis tool for companies listed in Taiwan. It collects statements such as income, balance-sheet, and cash-flow reports, then creates an interactive three-section HTML dashboard.
Skill Claude CodeCodex
Judges whether a user's input suits the Vibe Creating style of video-prompt writing, and when it does, distills single-scene prompts, multi-shot descriptions, emotional imagery, or mixed input into prompts that are easier for a video model to generate from — while preserving any user-specified dialogue, voiceover…
sruthir28/enterprise-ai-skills
Skill Claude CodeCodex needs its repo
Multi-agent pipeline that builds a polished presentation deck from a single topic. Four agents work in sequence — Strategist defines the narrative, Builder creates the deck, Critic reviews it like a McKinsey EM, Fixer applies the top fixes. Use when you need a presentation that survives senior audiences.
Skill Claude Code
Expose HybridClaw as a custom Alexa skill and prepare guarded Alexa smart-home/device control payloads without exposing Amazon credentials.
Skill Claude CodeCodex
Detect PII, credentials, and corporate sensitive data in API responses, source code, files, headers, and database extracts.
Skill Claude CodeCodex
A guide to recommended practices for Remotion, a React library for creating videos with code.
Skill Claude CodeCodex
How to save, update, and organize what you learn about the user and the work — user.md, memory.md, pastsessions archive.
Open-Document-Alliance/PDF-Tools
Skill Claude CodeCodex
Read and search PDFs, turn selected pages into Markdown, fill PDF forms, and create new copies with selected, reordered, rotated or merged pages. Reports source coverage and extraction gaps.
Skill Codex
Review an AEGIS PR, commit, branch or working-tree diff for concrete defects, requirement gaps and project-rule violations. Read-only unless fixes are requested; use audit-check for broad repository readiness checks.
Skill Claude CodeCodex
Order a private phone number in any country over the API, receive the SMS verification code, and hand the number back. Use when an agent has to pass a phone check during signup, login or account recovery, or needs a TOTP second factor computed locally.
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: