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.

shift-notes

18577

agentdecksdk/agentdeck

Skill Claude CodeCodex

How to write a handover note when closing out a shift - use before filing one.

not rated 4 3d ago A 24 tokens original MIT

threejs-development

18578

robcost/gameforge

Skill Claude CodeCodex

Three.js TypeScript 3D game development patterns including scene architecture, geometry, manual physics, input handling, camera, lighting, and HUD. Use when implementing or modifying a Three.js 3D game.

not rated 4 7mo ago A 46 tokens original MIT

qwen-mm-plugins-api

18579

ShuiHan268/dsh-qwen-mm-plugins

Skill Claude CodeCodex

Cloud MCP tools for understanding media, by model family. VL model: visionchat (caption/VQA), ocr, grounding (detect/locate objects). Omni model (reads frames + audio together): timestamped captioning, ASR (plain / controllable / multi-speaker diarized), temporal grounding, event counting, music captioning. Plus…

not rated 4 1mo ago A 110 tokens copy · 100% Apache-2.0

agentic-actions-auditor

18580

ASK191225/bugbounty-kit

Skill Claude CodeCodex

Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches AI agents running in CI/CD pipelines, including env var intermediary patterns, direct…

not rated 4 1mo ago A 105 tokens

devices-mcp-home

18581

sandraschi/devices-mcp

Skill Claude CodeCodex

Live inventory of the user's smart home on this devices-mcp installation — cameras, Hue lights, Tapo P115 plugs, Netatmo weather, Ring, Nest Protect, Shelly sensors, and robots. Use when the user asks what devices they have, what's online, or wants a status summary before controlling hardware.

not rated 4 +1 today A 69 tokens original MIT

lizard-core

18583

lizard-build/lizard-cli

Skill Claude Code

Core Lizard CLI usage guide. Read this before running any lizard commands. Covers the full app lifecycle (login, init, link, add, up, redeploy, logs, events, status, scale, restart, secrets, domains, run, ssh, metrics), the workspace → project → service model, managed addons (postgres, redis, s3 with auto-public…

not rated 4 changed 4d ago A 248 tokens original MIT

peer-agent

18584

panbergco/pi-peer-agent

Skill Claude CodeCodex

Manage resident peer agents: long-running monitors that live inside the pi session, tick on minute intervals, watch the main agent's work, and push findings back mid-turn. Use when the user asks to launch/stop/ask a peer, watcher, monitor, observer, sentinel, or auditor; wants standing review, drift/scope watching…

not rated 4 6d ago B 124 tokens

pf-replan

18585

turvodnik/pf-workflow

Skill Claude CodeCodex

A change-of-direction skill for projects that are already being built. It traces a new decision through the specification, work items, and completed or unfinished work.

not rated 4 1mo ago A 103 tokens original MIT

birdilsss-byte/ai-creative-subagent-framework

Skill Claude Code

A workflow for producing AI-assisted film and video concepts with separate roles for directing, visual design, cinematography, brand review, and AI execution. It breaks a script into storyboards and develops the visual plan in stages.

not rated 4 3mo ago A 228 tokens original MIT

managing-skills

18587

sernst/skills

Skill Codex

Manage reusable agent skills with the installed skill-manager CLI. Invoke only when the user explicitly asks to "manage skills" or clearly asks for help managing their agent skills, or when the user invokes $managing-skills. Do not invoke for requests that merely mention a skill or independently ask to install…

not rated 4 7d ago A 79 tokens original Apache-2.0

prd-reviewer

18588

aakashg/pm-github-workflow-repo

Skill Claude CodeCodex

Reviews a PRD against a completeness checklist and flags gaps before a human reviews it. Use when asked to "review this PRD" or for a "PRD review".

not rated 4 3mo ago A 39 tokens original MIT

my-skill-name

18589

fmwarriors/skills

Skill Claude CodeCodex

A clear description of what this skill does and when to use it. Include specific keywords that help agents identify when this skill is relevant.

not rated 4 28d ago A 32 tokens

svgator-motion-design

18590

SVGator/skills

Skill Claude CodeCodex

The craft layer for authoring standalone SVG assets through the SVGator MCP — designing the artwork, directing the motion, and wiring the interaction. Turns a prompt ("animate this logo", "make a loading spinner", "an icon that reacts on hover") into an art-directed, well-composed piece, then hands off to the MCP's…

not rated 4 2mo ago A 177 tokens

microsoft/opentelemetry-distro-dotnet

Skill Claude CodeCodex ✓ vendor

Set up Microsoft.OpenTelemetry distro in a new .NET application. Use when adding observability to an agent, ASP.NET Core app, console app, or Agent Framework project. Covers package installation, exporter configuration, token resolver setup, baggage context, and instrumentation options.

not rated 4 yesterday A 62 tokens

bootstrap

18592

joi-fairshare/agentic-workflow

Skill Claude Code

Analyze a repo's documentation coverage against the Pivot doc standard (17 planning docs + AGENTS.md + per-provider rules + design language), then generate any missing docs adapted to the codebase. Optionally reference external product documentation (SharePoint, Confluence, Dropbox, shared drives) when generating…

not rated 4 +2 changed yesterday A 64 tokens

snowflake

18593

aemcoder/skills

Skill Claude Code

Convert an AI-generated static HTML page (Stardust, Mobirise, Relume, Lovable, v0, Figma-derived hand-coded, etc.) into an Adobe Edge Delivery Services page that preserves the original DOM byte-for-byte while making the text and image content authorable in Document Authoring. Triggers on "convert this page to EDS"…

not rated 4 27d ago A 94 tokens original Apache-2.0

jsdoc-authoring

18594

Netcracker/qubership-ai-packages

Skill Claude CodeCodex

Load before writing, editing, or reviewing a doc comment or inline comment in JavaScript or TypeScript: a TSDoc block on an exported declaration, a @param type in a checked .js file, the it string of a test just added, a regression test that names the old defect, a method that overrides a base class or implements an…

not rated 4 changed 20d ago A 221 tokens original Apache-2.0

api-error-handler

18595

luqiang-code/claude-code-skills

Skill Claude Code

Add consistent error handling to API routes. Creates standardized error responses, logging, and error classes. Triggers on "add error handling", "error handling", "standardize errors".

not rated 4 +2 4mo ago A 40 tokens original MIT

senior-frontend

18596

EmersonBraun/skills

Skill Claude CodeCodex

The ultimate frontend design and development skill. Creates production-ready, pixel-perfect web interfaces with Next.js + Tailwind + shadcn/ui. Combines design thinking, UX best practices, accessibility, animation, and real design system patterns inspired by the best sites on the web. Invoked explicitly via…

not rated 4 5mo ago A 168 tokens original MIT

checkin

18597

jstoobz/session-kit

Skill Claude CodeCodex

Register the current Claude Code session under Session Kit and pre-allocate the durable archive + ledger that other session-kit skills depend on. Use when the user says "/checkin", "register this session", "set up session kit here", "start a session", or starts working in a scratch / unfilled cwd and wants explicit…

not rated 4 2mo ago A 120 tokens

angle-writer

18598

kelpi-ai/meta-ads-skills

Skill Claude CodeCodex

Write 5-6 genuinely different ad angles for one offer (different who, different pain, different promise), each ready to become its own Meta ad. Use when launching, or when testing has killed your current angles.

not rated 4 3mo ago A 48 tokens original MIT

enhancer-loop

18599

RichardHightower/reliable-agentic-lab

Skill Claude Code

One poll-and-act step for the ticket enhancer. Enhances every open draft ticket that still needs work. A human LGTM is the only comment that marks a ticket ready. Use when invoked as /enhancer-loop, typically from task run or wrapped in /loop for repeated polling.

not rated 4 3d ago A 63 tokens

deepen

18600

dswh/relay-crm-stdd

Skill Claude Code

The shared vocabulary and discipline for designing deep modules. Use when shaping a module's interface, placing a seam, making code testable or AI-navigable, or when another skill needs the deep-module vocabulary.

not rated 4 +1 3mo ago A 45 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: