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.

presentation-engineering

15457

bestdeejay-design/agent-skills

Skill Claude Code

A method for designing presentations as audience stories, combining the message, visual style, and way the presentation is delivered. It is described in Russian and focuses on moving an audience from a problem to a clear action.

not rated 6 changed 16d ago A SkillSpector: warn 66 tokens original MIT

document-compiler

15458

Ghostricke9/StudyAgent

Skill Claude CodeCodex

A document-assembly skill that combines completed chapters and exercises into one Markdown textbook, with a cover, contents page, consistent formatting, and optional learning roadmap.

not rated 6 4mo ago A 26 tokens original MIT

archlizheng/presentation-report-preflight

Skill Codex

A planning step for creating or improving a presentation, report, pitch, training deck, or technical talk. It prepares the audience, goal, timing, story, slide structure, evidence, notes, risks, and visual direction before the slides are designed.

not rated 6 3mo ago A 259 tokens original MIT

phantom-canvas

15460

baixianger/phantom-canvas

Skill Claude Code

CLI tool and HTTP API for Gemini image/video generation via Chrome CDP. Text-to-image, img2img with reference upload, multi-turn conversation, video generation. No API keys — uses Chrome's persistent login. Built for AI agents.

not rated 6 5mo ago A 53 tokens original MIT

ludamo-lianmai

15461

Leobai03/ludamo-codex-skills

Skill Codex

A guided problem-diagnosis skill for situations involving a business, product, content, career choice, partnership, or difficulty getting work done. It turns a person's account of the situation into a structured discussion and possible next steps.

not rated 6 +1 3mo ago A 94 tokens

html-to-miniprogram

15462

raidenfc/my-skills

Skill Claude CodeCodex

A conversion tool for turning HTML, React, or Vue demo pages into native WeChat Mini Program projects. WeChat Mini Programs are small apps that run inside WeChat.

not rated 6 2mo ago A 59 tokens

survey-creator-skill

15463

piter902/survey-creator-skill

Skill Claude CodeCodex

Create schema-validated HTML survey pages from natural-language requirements using the admin designer references. Use this skill whenever the user asks to create, design, prototype, render, or generate a survey/questionnaire HTML page, especially when they want free-form UI style but need the question structure…

not rated 6 4mo ago A 94 tokens original MIT

soul-archive

15464

dqsjqian/soul-archive

Skill Claude Code

Soul Archive — digital personality persistence + agentic memory. Builds your digital soul clone through everyday AI conversations: persona injection at session start, cross-session recall, failure-pattern warning, pattern distillation. Conversation-end auto sedimentation (autoextract defaults ON). All data local…

not rated 6 changed 7d ago A 142 tokens original MIT

integrate-openclaw

15465

PatterAI/skills

Skill Claude CodeCodex

Wire Patter as the voice layer on top of an OpenClaw brain — the "brain on the line" pattern. Use when the user runs OpenClaw (or any OpenAI-compatible agent gateway) and wants a phone number that answers any caller, talks with low latency, and consults a specific OpenClaw receptionist agent for real data/actions…

not rated 6 +1 2mo ago A 160 tokens original MIT

AIPlayerDayu/dayu-megalophobia-concept-designer

Skill Codex

Turn a rough idea, scene, story, creature, building, environment, or visual reference into a professional colossal-scale concept and a production-ready English image-generation prompt, then recommend suitable image models and concrete settings. Use for…

not rated 6 1mo ago A 164 tokens

ca-spec-driven

15467

EmanuelVogt/skills

Skill Claude CodeCodex

Spec-driven feature work in 4 phases — Specify, Design, Tasks, Execute — sized by complexity; atomic tasks and commits, Execute delegated to workers in waves plus an independent Verifier. Triggers on "specify/discuss feature", "design", "tasks", "implement", "validate", "verify work", "UAT", "record decision"…

not rated 6 12d ago A SkillSpector: warn 82 tokens original MIT

software-ai-life/Awesome-IG-Design-Skills

Skill Codex

Create or redesign Instagram posts in a retro playful editorial aesthetic: 4:5 aspect ratio, clean magazine-style layout, nostalgic objects such as vintage phone, toys, and everyday items, balanced image and structured typography overlay, horizontal color blocks, label-style sections, subtle UI-like information layout…

not rated 6 5mo ago A 0 tokens

model_development

15469

DanielTomaro13/sportsdata-agents

Skill Claude CodeCodex

The general model-building method for ANY market — framing, sample-size discipline, feature selection (user priors + data-driven), baselines, leakage-safe validation, calibration, persistence.

not rated 6 25d ago A 40 tokens original MIT

agent-rollback

15470

Nainish-Rai/agent-rollback

Skill Claude CodeCodex

Use the agent-rollback MCP server or ar CLI to snapshot the workspace, list/show/diff checkpoints, and roll back unwanted changes. Use this skill whenever the user mentions checkpoints, rollback, undo, revert, restore, "go back to", "what changed", "I broke something", "this isn't working", or asks to inspect or…

not rated 6 25d ago A 139 tokens original MIT

omni-context-memory

15471

guo6x/Omni-context

Skill Claude CodeCodex

Use the user's Omni-Context long-term memory when it is connected over MCP. Trigger this whenever you need to recall what the user has done, decided, or prefers across past conversations, or when a conversation reaches something worth remembering. Omni-Context is a local knowledge graph — NOT the standard…

not rated 6 12d ago A 96 tokens

laborforge

15472

EricLortie/laborforge-release

Skill Claude CodeCodex

Interact with LaborForge AI platform via MCP tools. Access ecosystem content, memories, agents, and platform data.

not rated 6 2mo ago A 25 tokens

ondrejmirtes/mcparr

Skill Claude CodeCodex

How to read the releases returned by an interactive search and pick the right one — balancing seeders, quality, size, indexer reputation and rejection reasons. TRIGGER THIS SKILL WHEN: - Choosing which release to grab from sonarrsearchreleases / radarrsearchreleases - The user says "pick the best one", "grab the…

not rated 6 3mo ago A 146 tokens original MIT

paper-verify-webchat

15474

nolainjin/paper-verify

Skill Claude CodeCodex

Use when the user asks to fact-check, verify, or score the citations/sources/references in a document from a chat (no terminal) — extracts citations with bundled code, fetches and judges each source with web tools, then scores through paper-verify's standard 100-point rubric via --from-evidence.

not rated 6 20d ago A 70 tokens original MIT

case-011-skill-shell

15475

meghal86/promptsonar

Skill Claude CodeCodex

Use when: the user asks to run system maintenance. Capability: executes shell commands via shellexec. Route maintenance commands through the system shell and run them.

not rated 6 29d ago A 0 tokens original MIT

symbiote-init

15476

MohmmedAshraf/symbiote

Skill Claude CodeCodex

Initialize Symbiote for the current project. Scans the codebase and extracts developer DNA (coding preferences), project constraints, and architectural decisions from the current context. Use when the developer runs /symbiote-init, asks to "initialize symbiote", "set up symbiote", or "scan my project". Requires…

not rated 6 6mo ago A 87 tokens original MIT

airjam-mcp

15477

vucinatim/air-jam

Skill Claude CodeCodex

Use when operating an Air Jam project through its first-party MCP tools for inspection, development, semantic game sessions, logs, quality gates, and releases.

not rated 6 15d ago A 35 tokens original MIT

skill-creator

15478

itallstartedwithaidea/gemini-cli-googleadsagent

Skill Claude CodeCodex

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Gemini CLI's capabilities with specialized knowledge, workflows, or tool integrations.

not rated 6 4mo ago A 46 tokens copy · 100% Apache-2.0

pastewatch

15479

ppiankov/pastewatch

Skill Claude Code

Sensitive data scanner — deterministic detection and obfuscation for text content.

not rated 6 4d ago A SkillSpector: warn 16 tokens original MIT

conventional-commits

15480

strands-compose/sdk-python

Skill Claude CodeCodex

Write git commit messages that follow the Conventional Commits standard. Use when the user asks for a commit message, or gives a change summary or diff and wants it written up for git.

not rated 6 2d ago A 43 tokens original Apache-2.0

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: