1,745 tagged agent-skills, measured the same way as everything else here.
Browse within: ai-skills 233agentic-ai 208claude-code-plugin 196skills 180ai-coding 173agentic-workflow 150claude-code-marketplace 127agents 103antigravity 80spec-driven-development 78agentic-systems 75ai-tools 75agentic 74product-management 70
Command Claude Code
Momentum router. Default is BUILD — routes straight to the full-cycle build engine. Strategy rails (idea/pricing/GTM) and stage-resume are opt-in side doors, never a toll. Skip is available at every step.
Command Claude Code
AI-DLC workflow orchestrator (Cursor harness). Start, resume, or manage an AI-driven development lifecycle. Run the deterministic forwarding loop below: ask the engine what to do next, do that one thing, and follow the typed directive returned by each report.
Command Claude Code
Audit Shipshape installation integrity: completeness, freshness, and coherence across channels and scopes. Read-only.
Command Claude Code
Spike a design idea — decode brief/screenshot/figma, scaffold shadcn into /sandbox, optionally layer motion. Default entry point for any design exploration.
Command Claude Code
Run a full autonomous research investigation and return a verified, cited report: plan, search broadly, check primary sources, verify adversarially, and synthesize. Run like an /autoresearch command for a deep, trustworthy answer.
Command Claude Code
Enrich KB routing state for every date since the last run. backfill requests one-time all-scope projection through the knowledge-base skill. Run KB enrichment in the caller session using the installed kb CLI against local runtime state. Do not create a session in, change directory to, or delegate this workflow to the…
Command GitHub Copilot
End-to-end Katalon True Platform testing workflow and lifecycle router. Use when one request spans several stages and no single skill owns all of it, for example analyze a requirement, design and import the cases, build a suite, run it with AI, and report the outcome. Also use to route any testing request across the…
Command Claude Code
Given a company name or domain, find their changelog/release-note sources, add them to Releases, and fetch recent entries. This is the manual, Claude-driven onboarding flow — it uses the releases CLI against the production API and does not dispatch to managed agents. (If you want managed-agent onboarding, use releases…
viacheslav-tronko/claude-code-harness
Command Claude Code
Full bug-fix pipeline — runs /bug-why → /verify(RCA) → /trace(virtual) → ASK USER → /bug-fix → /trace(real) → /verify(FIX) sequentially. Triggers: /bug-full, "full bug pipeline", "fix this bug end-to-end", "RCA + verify + fix + verify", Jira ticket / error wanting entire pipeline. MODIFIES source at step 5 — Two-Stage…
Command Claude CodeCodex
Audit agent configuration files for security vulnerabilities and misconfigurations. Classifies findings as P0 or P1.
Command Claude Code
A project-initialization command that sets up a seven-step development loop in CLAUDE.md, the project's instructions file, and prepares related checks and screenshot storage.
YujxZJCN/teaching-skills-codex
Command Claude Code
TS cohort-analyst cohort-profile mode — analyze student readiness data.
hybridlabor-api/bdb-dev-optimized-agent-skills
Command Claude Code
Complete a security review of the pending changes on the current branch.
Command Claude Code
Define an incremental, reviewable, production-safe implementation plan for the active task and persist it as IMPLEMENTATIONPLAN.md plus a TASKSTATE.md update. Breaks work into the smallest safe slices with objective, exact scope, ordering rationale, key risks, validation approach, exit criteria, and work complexity…
Command Claude Code
Static and dependency audit. Use the Grep tool (not bash grep).
Command Claude CodeCodex
Rebuild an Embedded IDE for VS Code workspace and return a minimal JSON build summary. Use when the user asks to compile, rebuild, or verify a build.
Command Claude Code
Mines an external agent/skill collection and curates keepers into this repo's catalog (agents/, skills/, README links). Use when importing, adapting, or evaluating external agents, skills, or commands for agenticat.
Command Claude Code
When the user asks to "make this codebase cursor compatible", "make it vibe codeable", "set up cursor for this project", or similar requests, help them transform their codebase into a Cursor-optimized workspace.
Command Claude Code
Discover, configure, and run ui-evidence for before/after UI review in this repo.
Command Claude CodeCodex
Resolve reviewer feedback - from GitHub PRs, chat, or any reviewer.
Command Claude Code
Enter explore mode - think through ideas, investigate problems, clarify requirements.
Command Claude Code
You are an expert ABP Framework developer. Given an existing entity, scaffold the complete application layer with all best practices: error codes, localization, FluentValidation, permissions, app service (with proper exception handling), and optional Razor Pages UI.
topprismdata/cultivating-ml-agent
Command Claude Code
Apply /meta-optimize suggestions after cross-model jury approval. Gates memory writes through external review.
Command Claude Code
Effort recommendation only for this task. Shows a narrow ladder of just the effort level, from a lower setting to a higher one, for a model named in the task or else the one you are on.
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: