123,917 listed
Skills
Skills are folders with a SKILL.md file that an agent loads when a task needs it. These come from public GitHub repositories, with copy commands for Claude Code, Codex and other Agent Skills hosts.
Showing 745–768 of 1,818
- 0.688score
vercel-deploy
openaiOfficial
Deploy applications and websites to Vercel.
SkillDFreshness: D★ 28.3KClaude Code +9 - 0.688score
winui-app
openaiOfficial
Bootstrap, develop, and design modern WinUI 3 desktop applications with C# and the Windows App SDK using official Microsoft guidance, WinUI Gallery patterns…
SkillDFreshness: D★ 28.3KClaude Code +9 - 0.687score
bindings-synchronization
googleOfficial
Guidelines and SOP for synchronizing public C++ API changes (methods, enums, options structs) to Java (Android JNI) and JavaScript/TypeScript (Web/WASM Embind).
SkillAFreshness: A★ 20.6KClaude Code +9 - 0.687score
code-review
googleOfficial
Adversarial systems, concurrency, memory-model, and architecture code review protocol.
SkillAFreshness: A★ 20.6KClaude Code +9 - 0.687score
filament-build-clean
googleOfficial
Clean and build Filament targets for development, debugging, and production.
SkillAFreshness: A★ 20.6KClaude Code +9 - 0.687score
code-explainer
microsoftOfficial
**UTILITY SKILL** - Explain code snippets, functions, and algorithms in plain language.
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.687score
coordinator-init-mode
microsoftOfficial
The complete two-phase Init Mode protocol the Squad coordinator runs when no team exists yet in the current repo.
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.687score
coordinator-response-mode
microsoftOfficial
Selecting WHO handles work is the Routing table; selecting HOW they handle it (Direct, Lightweight, Standard, Full) is Response Mode.
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.687score
coordinator-source-of-truth
microsoftOfficial
The complete file-by-file source-of-truth hierarchy for Squad: which files are authoritative, which are derived/append-only, who may write each one, who may…
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.687score
cross-squad
microsoftOfficial
Coordinating work across multiple Squad instances — discovery, delegation, and disambiguation when the user says 'squad' (the product) vs casual English…
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.687score
iterative-retrieval
microsoftOfficial
Max-3-cycle protocol for agent sub-tasks with WHY context and coordinator validation.
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.687score
squad
microsoftOfficial
Squad's command catalog and interactive menu.
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.687score
squad-commands
microsoftOfficial
Categorized catalog of common Squad operations.
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.687score
waza
microsoftOfficial
**WORKFLOW SKILL** - Evaluate AI agent skills using structured benchmarks with YAML specs, fixture isolation, and pluggable validators.
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.687score
waza-interactive
microsoftOfficial
Interactive workflow partner for creating, testing, and improving AI agent skills with waza.
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.686score
setup-zoom-marketplace-app
zoomOfficial
Use when creating, updating, selecting, or validating a Zoom Marketplace app.
SkillAFreshness: A★ 2Claude Code +9 - 0.685score
ai-audit-account-report
zapierOfficial
Turn account usage data into a concise AI audit outreach package.
SkillCFreshness: C★ 351Claude Code +9 - 0.685score
header-self-containment
googleOfficial
Enforce strict header self-containment so that every header file compiles independently.
SkillAFreshness: A★ 20.6KClaude Code +9 - 0.685score
preprocessor-guard-hygiene
googleOfficial
Enforce preprocessor guard rules and macro-dependent inclusion hygiene in C++.
SkillAFreshness: A★ 20.6KClaude Code +9 - 0.685score
verification-protocols
googleOfficial
Standard verification pipeline to execute after modifying C++ source or header files.
SkillAFreshness: A★ 20.6KClaude Code +9 - 0.685score
mongodb-mcp-setup
mongodbOfficial
Guide users through configuring key MongoDB MCP server options.
SkillCFreshness: C★ 190Claude Code +9 - 0.685score
mongodb-natural-language-querying
mongodbOfficial
Generate read-only MongoDB queries (find) or aggregation pipelines using natural language, with collection schema context and sample documents.
SkillCFreshness: C★ 190Claude Code +9 - 0.685score
gh-address-comments
openaiOfficial
Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not…
SkillDFreshness: D★ 28.3KClaude Code +9 - 0.684score
code-explainer
microsoftOfficial
Explains code snippets in plain English, breaking down what the code does step by step.
SkillAFreshness: A★ 1.4KClaude Code +9
Popular comparisons
- git-guardrails-claude-code vs ai-coding-agent-guardrails
- skill-creator vs skill-creator
- bmad-eval vs agent-evals
- playwright-validation vs playwright-cli
- e2e-cucumber-playwright vs playwright-cli
- obsidian-markdown vs lark-markdown
- protected-vercel-deployments vs vercel-optimize
- vercel-optimize vs vercel-sandbox