Claude Code AI Skills
AI skills built for Anthropic's terminal-native coding assistant
Claude Code runs directly in your terminal with full project context. Skills integrate as MCP tools, giving Claude deep understanding of your codebase for code generation, refactoring, testing, and documentation - all through natural conversation.
Top Claude Code Skills
token-guard
Stop wasting tokens and money on oversized context. Token-Guard measures what you are about to send, flags the biggest offenders, and tells you what to trim, summarize, or drop before the call. Includes budget thresholds, per-file cost estimates, hard-limit gates, and a report you can act on. Pairs with lean-context and context-offload-hint.
aeo-citation-auditor
Get cited by AI answer engines. Audits a page for AEO/GEO readiness: entity clarity, answer-shaped structure, schema.org JSON-LD, llms.txt, crawler directives, and quotable claims. Returns a scored report with P0/P1/P2 fixes and copy-paste schema blocks. Built for teams who want ChatGPT, Perplexity, and AI Overviews to quote them.
sop-architect
Turn a messy process into an agent-ready SOP. Interviews you about a workflow, then produces a structured spec with roles, inputs, steps, decision points, failure paths, and acceptance checks that an AI agent can execute or automate. Includes templates, a gap analysis, and a validation checklist.
local-review-responder
Turn customer reviews into revenue. Drafts on-brand, policy-safe responses to Google, Yelp, and marketplace reviews, routes negative reviews with an escalation path, and extracts recurring themes into a short action list. Includes tone guardrails, review-bombing handling, and approved-response templates.
What Claude Code skills can do for you
Terminal-Native Workflow
Skills run directly in your terminal alongside your existing tools. No context switching - ask Claude to use a skill and it executes inline with your project.
Deep Codebase Understanding
Claude Code reads your entire project structure, so skills operate with full context. Generate tests that match your patterns, docs that reflect your architecture.
MCP Tool Integration
Skills integrate as Model Context Protocol tools, extending Claude's capabilities natively. Install once and they're available in every session.
Claude Code Skills
token-guard
Stop wasting tokens and money on oversized context. Token-Guard measures what you are about to send, flags the biggest offenders, and tells you what to trim, summarize, or drop before the call. Includes budget thresholds, per-file cost estimates, hard-limit gates, and a report you can act on. Pairs with lean-context and context-offload-hint.
aeo-citation-auditor
Get cited by AI answer engines. Audits a page for AEO/GEO readiness: entity clarity, answer-shaped structure, schema.org JSON-LD, llms.txt, crawler directives, and quotable claims. Returns a scored report with P0/P1/P2 fixes and copy-paste schema blocks. Built for teams who want ChatGPT, Perplexity, and AI Overviews to quote them.
sop-architect
Turn a messy process into an agent-ready SOP. Interviews you about a workflow, then produces a structured spec with roles, inputs, steps, decision points, failure paths, and acceptance checks that an AI agent can execute or automate. Includes templates, a gap analysis, and a validation checklist.
local-review-responder
Turn customer reviews into revenue. Drafts on-brand, policy-safe responses to Google, Yelp, and marketplace reviews, routes negative reviews with an escalation path, and extracts recurring themes into a short action list. Includes tone guardrails, review-bombing handling, and approved-response templates.
data-pipeline-agent
Design and document data pipelines end to end. Turns a business question into a source-to-destination plan: sources, ingestion, transformations, quality checks, scheduling, and failure handling. Produces a runnable spec with schema notes, validation rules, and a monitoring plan. For analysts and engineers who need pipelines that survive production.
outreach-writer
Draft buyer-facing outreach that gets replies. Reads a job brief, a prospect, or a product, then writes a short, specific, non-spammy message with a clear ask and a follow-up. Includes angle selection, personalization slots, tone control, and a checklist to avoid spam triggers. Works for freelance bids, cold email, and warm follow-ups.
lean-context
Cut token spend in long coding sessions. lean-context detects oversized context before you paste it (logs, JSON, big diffs, long docs) and gives concrete ways to split or offload it, then scopes code review to changed files with line counts and token estimates. Pairs with Token-Guard and context-offload-hint.
SKILL.md Snippet Generator
Generate a minimal, valid SKILL.md from a one-liner: frontmatter plus Triggers, Inputs, Procedure, Report, and Example. Designed to feed straight into skl-validator.
Common questions about Claude Code skills
How do I install skills in Claude Code?
Run npx @agentpowers/cli setup to auto-configure MCP for all your AI tools, then ask Claude to install any skill. Or install directly with npx @agentpowers/cli install skill-name --code YOUR-LICENSE-CODE. Legacy CLI (pip install agentpowers) also works. Skills are available immediately in your next session.
Are Claude Code skills compatible with other platforms?
Most skills on AgentPowers work across multiple MCP-compatible platforms. Check the platform badges on each skill listing to see full compatibility.
Do Claude Code skills require a paid Claude plan?
Claude Code requires a Claude API subscription. Skills from AgentPowers are purchased separately and work with any active Claude Code installation.
Connect AgentPowers to Claude Code
Ready to supercharge your
Claude Code workflow?
Browse verified skills and agents compatible with Claude Code. One-command install, instant results.