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.

brainstorm

22513

visionTw/godot-ai-harness

Skill Claude Code

Guided game concept ideation — from zero idea to a structured game concept document. Uses professional studio ideation techniques, player psychology frameworks, and structured creative exploration.

not rated 2 1mo ago A 36 tokens copy · 83% MIT

sdcorejs-angular

22514

sdcorejs/sdcorejs-agent

Skill Claude Code

Angular Core UI executor for approved implementation in new or existing @sdcorejs/angular and @sd-angular/core apps, covering portal init, CRUD/list/detail/form/action scope, explicit technical prototypes, or approved migration. Optional admin/auth packs require approved scope. Do not use for plain Angular apps or…

not rated 2 changed 28d ago A 86 tokens original MIT

brainstorming

22515

christiansalazar-wk/ai-lore

Skill Claude CodeCodex

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

not rated 2 19d ago A 37 tokens

ddggkkcc/industry-intelligence-researcher

Skill Claude CodeCodex

This skill should be used when conducting evidence-led industry, market, competitive, value-chain, business-model, or investment research across any sector. It converts broad questions into a decision-oriented research brief; combines official statistics, company filings, trade data, expert/participant evidence, and…

not rated 2 1mo ago A 111 tokens original MIT

vibe-coding-guidance

22517

yes999zc/vibe-coding-guidance

Skill Claude CodeCodex

A guide for choosing how carefully to use AI-assisted coding based on the project, the developer’s experience, and the amount of testing required.

not rated 2 5mo ago A 40 tokens original MIT

changelog-formatting

22518

mattppal/shipping-szn

Skill Claude CodeCodex needs its repo

Format changelog content according to Replit's changelog template structure. Use when converting raw changelog content into properly structured documentation with correct frontmatter, sections, and media formatting.

not rated 2 7mo ago A 41 tokens original MIT

kwaa-typescript-taste

22519

kwaa/skills

Skill Codex

Apply kwaa's general TypeScript design and style preferences when writing or refactoring TypeScript or TSX, especially library APIs, reusable utilities, async workflows, and module boundaries.

not rated 2 2mo ago A 43 tokens original MIT

Code Review

22520

DDR187/cursor-howto

Skill Claude CodeCodex

Automatic code review, checking code quality, security, and best practices.

not rated 2 6mo ago A 16 tokens original MIT

quality-gate

22521

Effulgent-Point/paw

Skill Claude CodeCodex

When to use: Reviewing code before merge. Running multiple review agents. Deciding what blocks and what doesn't.

not rated 2 1mo ago A 0 tokens original MIT

uvs-qa

22522

utsavanand/uv-suite

Skill Claude Code

Browser-based QA: exercises the running app via Playwright MCP, captures console errors and visual evidence, optionally fixes source bugs with atomic commits and generates regression tests. Three tiers (quick / standard / exhaustive). Writes uv-out/qa-state.md so /uvs-commit and /ship can detect completion and read…

not rated 2 3mo ago A 71 tokens original MIT

factor-pool-evolution

22523

quantskills/skill-factor-pool-evolution

Skill Codex

Run one round of factor-pool recommendation from an existing stock alpha set. Use when an agent needs to start from user-provided seed factors, prepare mutation and crossover prompt packs for the current model to reason over, then evaluate generated factors by RankIC and RankICIR and output recommended factors for the…

not rated 2 2mo ago A 80 tokens GPL-3.0

clean-code-refactor

22524

menaawed12/clean-code-refactor

Skill Claude Code

Behavior-preserving refactoring, review remediation, and hardening for code in any major language. Use when asked to refactor, clean up, simplify, or review code; fix lint, static-analysis, or duplicate-code findings; extract responsibilities; or improve tests. Prevents security, reliability, and maintainability…

not rated 2 changed 3d ago A 83 tokens original MIT

ndv-bounded

22525

emb715/neurodiveragents

Skill Claude Code

Scope discipline cognitive module. Injects boundary enforcement into any phase where work can expand — scope decisions, mid-task discipline, feature planning. Emergent pattern across all NDV agents.

not rated 2 2d ago A 41 tokens original MIT

qwen-image-gen-python

22526

catherineliaooo/qwen-image-gen

Skill Claude CodeCodex

AI image generation using Alibaba Qwen Image 2.0 Pro (Python version). Supports text-to-image with excellent Chinese and English text rendering. Use when user asks to generate, create, or draw images.

not rated 2 6mo ago C 48 tokens original MIT

ai-agents-ui-skills

22527

SrulyRosenblat/skill-cards

Skill Claude CodeCodex

Comprehensive guide for building AI agents using ToolLoopAgent, workflow patterns, and AI SDK UI components (useChat, generative UIs, tool calling).

not rated 2 3mo ago A 32 tokens

guideline-checker

22528

yunbow/ai-dev-os-rules-typescript

Skill Claude Code

Automatically check whether git diff contents comply with project guidelines after code changes. Run at coding completion or before committing.

not rated 2 5mo ago A 27 tokens original MIT

ccpa-cpra-privacy-rights

22530

vaquarkhan/compliance-agent-skills

Skill Claude CodeCodex

Implements California Consumer Privacy Act (CCPA) as amended by the California Privacy Rights Act (CPRA)—Cal. Civ. Code §1798.100 et seq.—covering consumer rights to know, delete, correct, opt-out of sale/share, and limit use of sensitive personal information, plus DSAR workflows, privacy notices, and service provider…

not rated 2 1mo ago A 173 tokens original MIT

openspec-explore

22532

ZhaoYis/My-Skills

Skill Claude Code

Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.

not rated 2 17d ago A 39 tokens

codeboard

22533

show-board/codeboard

Skill Claude CodeCodex

Syncs AI agent work with the CodeBoard dashboard via HTTP API (sessionstart, tasklist, taskstart/complete, sessioncomplete, memory sync). Use when working in this repository, when .dashboard/project.yaml exists, or when the user mentions CodeBoard, 看板, session sync, or task reporting.

not rated 2 5mo ago A 66 tokens

git-commit-helper

22534

ghostship25/Skilllint

Skill Claude CodeCodex

Writes clear, conventional-commit-style commit messages from staged git diffs, and can split unrelated changes into separate commits.

not rated 2 1mo ago A 29 tokens original MIT

font-aesthetics

22535

Greatbeing/font-aesthetics

Skill Claude CodeCodex

A Chinese-language visual design skill for creating concept posters where typography is the main subject. It turns words and phrases into images through letter shapes, layout, materials, and visual metaphors.

not rated 2 3mo ago A 138 tokens original MIT

algorithmic-art

22536

ferdinandruthben12-dotcom/535-skills

Skill Claude CodeCodex

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright…

not rated 2 1mo ago A 62 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: