Skills

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.

ai-partner-chat

3985

eze-is/ai-partner-chat

Skill Claude CodeCodex

A personalised chat tool that uses a user profile and vectorised notes, meaning notes indexed so related ideas can be found by meaning. It uses earlier thoughts and notes to shape replies.

not rated 213 9mo ago A 55 tokens

search

3986

QuantClaw/QuantClaw

Skill Claude CodeCodex

Web search with automatic provider fallback (Tavily → DuckDuckGo).

not rated 213 3mo ago A SkillSpector: pass 17 tokens original Apache-2.0

renderdoc-gpu-debug

3987

rudybear/renderdoc-skill

Skill Claude Code

GPU frame debugging with RenderDoc via rdc-cli. Use this skill when the user mentions: GPU debugging, .rdc files, RenderDoc, shader issues, pipeline state, rendering artifacts, frame capture, shadow problems, visual glitches, draw calls, render targets, pixel history, texture inspection, depth buffer, blend state…

not rated 213 +1 8mo ago A 200 tokens original MIT

quality-control

3988

aronprins/paperclip-company-playbook

Skill Claude CodeCodex

A mandatory verification skill for CEO agents. Ensures every deliverable is personally verified before reporting to the Founder.

not rated 213 +1 7mo ago A 0 tokens

inspect

3989

Ataraxy-Labs/inspect

Skill Claude CodeCodex

Entity-level code review for Git. Scores changes by risk and groups them by logical dependency.

not rated 213 +3 yesterday A 0 tokens

setup

3990

atomgit-atomcode/atomcode

Skill Claude Code

Analyze a codebase and recommend AtomCode automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their AtomCode setup, mentions improving AtomCode workflows, asks how to first set up AtomCode for a project, or wants to know what AtomCode…

not rated 213 +3 changed 17d ago C 71 tokens original MIT

team-building

3991

markus-global/markus

Skill Claude CodeCodex

Design and create AI team packages — manifest format, member structure, directory layout.

not rated 214 today A SkillSpector: warn 18 tokens original Apache-2.0

diagramar

3992

igoruehara/spec-driven

Skill Claude Code needs its repo

Use no discovery para desenhar a arquitetura de ALTO NÍVEL em Mermaid — diagrama de contexto (C4 L1), containers (C4 L2) e o mapa de bounded contexts (DDD). Lê vision, context-map, design e assessment, e gera/atualiza docs/architecture/diagrams.md. Mantém alto nível, sem detalhe de implementação. Acione com /diagramar.

not rated 212 3mo ago A SkillSpector: pass 88 tokens original MIT

meihua-yishu

3993

muyen/meihua-yishu

Skill Claude CodeCodex

A skill for Meihua Yishu, a Chinese form of I Ching divination that uses hexagrams, including character-based readings. It responds to requests for fortune telling and related readings.

not rated 212 +1 3mo ago A 0 tokens

pr-triage

3994

OutThisLife/brooklyn-skills

Skill Claude CodeCodex

Maintainer triage on OTHER people's PRs/MRs — verdict of approve, supersede, or close, salvage with credit, close the cluster. Use for a review batch, a pasted Discord thread with a PR, or salvage/supersede/close asks. Not for your own PR (that's pr-ready).

not rated 213 +1 changed 1mo ago A SkillSpector: pass 69 tokens original MIT

release

3995

dylanroscover/Embody

Skill Claude Code needs its repo

MUST READ before preparing a release commit or GitHub release -- the blocking GitHub preflight (dev/releasepreflight.py), project.save() versioning, changelog, README, template sync verification, fresh-install smoke, and the post-push GitHub release procedure (references/github-release.md).

not rated 213 +1 changed 6d ago A SkillSpector: warn 63 tokens original MIT

zeroid

3996

highflame-ai/zeroid

Skill Claude Code

MANUAL TRIGGER ONLY: invoke only when user types /zeroid. Identity infrastructure for AI agents — register identities, issue tokens, delegate to sub-agents, revoke credentials, and manage credential policies via the Zeroid REST API.

not rated 212 +2 changed 24d ago A SkillSpector: warn 51 tokens original Apache-2.0

agent-inspect

3997

rajudandigam/agent-inspect

Skill Claude CodeCodex

Local evidence debugger and trajectory-test toolkit for TypeScript AI agents. Use when capturing framework-faithful traces, asserting TraceContract/TraceFacts, packaging Evidence v2, or inspecting local runs over read-only MCP (gettracefacts).

not rated 211 +43 4d ago A SkillSpector: warn 52 tokens original MIT

annas-to-notebooklm

3998

zstmfhy/annas-to-notebooklm

Skill Claude CodeCodex

A tool that downloads a book from Anna’s Archive, an online book collection, and uploads it to Google NotebookLM, a service for asking questions about supplied documents. It supports PDF and EPUB files and can create a NotebookLM notebook.

not rated 211 +1 9mo ago A 38 tokens original MIT

luamake

3999

actboy168/luamake

Skill Claude CodeCodex

A Lua-based build system that generates Ninja build files for compiling C, C++, Lua modules, libraries, and programs. Build files describe how source code is turned into runnable software.

not rated 211 changed 11d ago A SkillSpector: pass 219 tokens original MIT

mobilevc-installer

4000

JayCRL/MobileVC

Skill Claude CodeCodex

An installation workflow for MobileVC, a tool that lets you use Claude Code from an iOS or Android phone while your development computer runs the work. The phone connects to the computer over a local network or through a relay service.

not rated 211 +2 13d ago A SkillSpector: pass 222 tokens original MIT

whatsapp

4001

Enriquefft/openclaw-kapso-whatsapp

Skill Claude Code

Send WhatsApp messages via Kapso (outbound to third parties on owner instruction).

not rated 211 7mo ago A 20 tokens original MIT

unit-converter

4002

agentjido/jido_ai

Skill Claude Code

Converts between common units of measurement including temperature, distance, and weight.

not rated 211 changed 2mo ago A SkillSpector: pass 19 tokens original Apache-2.0

clawmem

4003

yoloshii/ClawMem

Skill Claude Code

ClawMem operational reference for agents at query time — the 3-rule escalation gate, MCP tool routing, the 4 query-optimization levers, pipeline behavior (query vs intentsearch), composite scoring, and memory lifecycle (pin/snooze/forget). Use when tuning retrieval, troubleshooting recall quality, or any ClawMem…

not rated 211 +2 changed 1mo ago B 120 tokens original MIT

wp-block-development

4004

Automattic/agent-skills

Skill Claude CodeCodex

Use when developing WordPress (Gutenberg) blocks: block.json metadata, registerblocktype(frommetadata), attributes/serialization, supports, dynamic rendering (render.php/rendercallback), deprecations/migrations, viewScript vs viewScriptModule, and @wordpress/scripts/@wordpress/create-block build and test workflows.

not rated 211 9mo ago A Socket: passSnyk: pass 67 tokens archived

rep1-failed

4005

adrianco/retort

Skill Claude CodeCodex

This skill implements a complete REST API service for managing a book collection in Python with Flask and SQLite database.

not rated 212 +1 yesterday A SkillSpector: warn 0 tokens original Apache-2.0

agent-browser

4006

nexxeln/opencode-config

Skill Claude Code

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…

not rated 210 5mo ago A 108 tokens

video-copy-analyzer

4007

ALBEDO-TABAI/video-copy-analyzer

Skill Claude CodeCodex

A Chinese-language tool for downloading online videos, turning speech into text, correcting transcripts, and analyzing the wording and appeal of short videos. It supports platforms including Bilibili, YouTube, and Douyin.

not rated 211 +1 2mo ago A 114 tokens original MIT

Dicklesworthstone/meta_skill

Skill Claude CodeCodex

Build terminal UIs with Charmbracelet (Bubble Tea, Lip Gloss, Gum). Use when: Go TUI, shell prompts/spinners, "make CLI prettier", adaptive layouts, async rendering, focus state machines, sparklines, heatmaps, kanban boards, SSH apps.

not rated 210 +2 2d ago A 65 tokens

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: