enhance-plugins
Use when analyzing plugin structures, MCP tools, and plugin security patterns.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-22 00:14
Agents & models
24,472 results
Ask-Samin
Answer Claude Club questions the way Samin Yasar teaches them. Use when the member asks how Samin approaches something, Claude Club / Skool lessons,…
autoresearch-skill
[Hyper] Use this skill when optimizing an existing Codex skill through baseline-first experiments, binary evals, Guard checks, and one-mutation-at-a-time…
first-run
Guide a new user through their first computer-use agent run (env check, safe browser-only task, then open the trajectory viewer).
damage-control
Recovers broken agent state via crash recovery, context overflow, and merge conflict protocols. Use when an agent session fails or a worktree is corrupted.
discover-product-domain
Generate, remix, and rank product or app names, then verify their exact standard-price .com domains. Use when naming an app or product, remixing name fragments…
qmd
Search the vault using QMD semantic search. Use PROACTIVELY before reading files. Preference order: (1) MCP tools — mcp__qmd__query, mcp__qmd__get,…
brainstorm-with-file
Interactive brainstorming with documented thought evolution, multi-perspective analysis, and iterative refinement. Serial execution with no agent delegation.
airtable-automation
Automate Airtable tasks via Rube MCP (Composio): records, bases, tables, fields, views. Always search tools first for current schemas.
dsh-pre-push-checks
Use before pushing, force-pushing, marking ready for review, or claiming checks pass on a deepseek-harness branch, and immediately after gh stack sync…
context-compression
Use when compressing agent context, implementing conversation summarization, reducing token usage in long sessions, or asking about "context compression",…
blender-mcp-integration
Choose, configure, and use Blender MCP integrations for live scene control or deterministic asset evaluation. Use when connecting Codex or Claude Code to an…
iskron
Iskron's door and session start: /iskron and in your own words. "Start" — first, before readiness: graph and role, iskron_stand only on watch, greeting to the person. Catches…
token-optimization
Token Optimization is the systematic reduction of token expenditure across agent operations without sacrificing output quality.
dispatching-parallel-agents
Dispatches one subagent per independent domain to parallelize investigation/fixes. Use when you have 2+ unrelated failures (e.g., separate failing test files,…
agents-md-generator
Generate hierarchical AGENTS.md structures for codebases. Use when user asks to create AGENTS.md files, analyze codebase for AI agent documentation, set up…
memory
Manages cross-session knowledge persistence. Triggers on "remember", "recall", "what did we", "save this decision", "todo", or session handoff.
eval-faq
Answers AI agent evaluation methodology questions with practical, opinionated guidance grounded primarily in Microsoft's agent evaluation ecosystem (MS Learn,…
infinite-gratitude
Multi-agent research skill for parallel research execution (10 agents, battle-tested with real case studies).
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when…
scout
Investigate real-system best practices, production archetypes, and failure modes before architectural commitment.
prompt-engineer
Prompt engineering. Craft, analyze, harden, convert, design tool prompts, and build PromptOps/eval plans. Use for system, agent, tool, RAG prompts. NOT for…
skillsmp
Search Agent Skills on SkillsMP (an index of 1.6M+ public SKILL.md files, covering Claude Code / Codex / ChatGPT), filter by keyword, category, occupation, and language, and specifically dig up those obscure Skills that are "well-written but nobody knows about." When the user says find a skill, is there a ready-made skill, search for...
prompt-engineering
Engineer effective LLM prompts using zero-shot, few-shot, chain-of-thought, and structured output techniques. Use when building LLM applications requiring…