capture-rule
Capture a reusable, non-obvious project insight into the rules home where it will auto-inject in future sessions. Use when investigation or implementation…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-08 00:04
Agents & models
25,887 results
openspec-explore
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through…
setup-project-context
Scaffold or show the .claude/project-context.json file that the engineering hooks read to inject project context, target-repo guidance, and optional post-edit…
setup-rules-ex
Scaffold the rules-ex extended-rules infrastructure (.claude/rules/rules-ex-authoring.md and .claude/rules-ex/README.md) required by the engineering plugin's…
serena-skills
Standalone Serena MCP tools for code intelligence - symbol search, file ops, memory, editing, config, workflow helpers, and shell execution without MCP server
copilot-agents-ff15-openspec-non-mcp-sync
Sync GitHub Copilot agents for FF15-inspired OpenSpec workflow (non-MCP version). Team includes Noctis (orchestrator + OpenSpec creator), Iris (issue…
copilot-agents-ff15-openspec-serena-sync
Sync GitHub Copilot agents for FF15-inspired OpenSpec workflow. Team includes Noctis (orchestrator + OpenSpec creator), Iris (issue management), Gladiolus…
global-prompts-sync
Synchronizes prompt files (agents, rules, commands) from the skill's prompts directory to both GitHub Copilot and OpenCode global configuration directories.…
local-skill-loader
Loads (copies) a skill from a local source directory into the current project's skill library (.claude/skills). Use this when the user wants to import or copy…
prompt-engineer
Expert in designing effective prompts for LLM-powered applications. Masters prompt structure, context management, output formatting, and prompt evaluation. Use…
herdr
Control herdr from inside it. Manage workspaces and tabs, split panes, spawn agents, read output, and wait for state changes — all via CLI commands that talk…
claude-review
"Those who write don't review, those who review don't write" multi-model code review workflow (pure Claude version). The main Claude writes code, while simultaneously dispatching three independent subagents to review in parallel from different dimensions; the main Claude consolidates and fixes, looping until there are no new issues, then commits. Does not depend on Codex / GPT; trigger this skill after completing code implementation.
skill-evo
Interactive Claude Code skills for forging project-specific skills, with built-in self-evolution capability. Scan project → plan → Q&A → generate. Can be run repeatedly, getting better the more it's used. Trigger words: 初始化 skills, init skills, skill-evo, 锻造 skill, 优化 skill, 进化 skill, 审查 skill, skill review.
llm-fine-tuning-skill
Run a staged LLM fine-tuning workflow from bootstrap through investigation, requirements and success criteria, implementation planning, implementation plus…
checkpoint
Inspect Check Point security policies, threat intelligence, gateways, and SASE through its MCP integrations. Use for Check Point platform questions or…
equinix-fabric-operations
Inspect and operate Equinix Fabric connections, ports, Cloud Routers, routing, filters, service profiles and telemetry through the official MCP.…
jev-answer-review
Judge a proposed operational answer against the human request and retrieved evidence with freshly authored Jev questions. Use before Border delivers an…
memory
NetClaw's native persistent memory (spec 033) — structured facts with temporal validity, semantic search across past sessions, decision logging, and entity…
worldlabs-topology-viz
Turn a real network topology into a free, no-cost themed prompt preview, and optionally (after explicit confirmation) generate an explorable, AI-generated 3D…
explore
Answer "how does X work", "where is X defined", or "trace through Y" questions about a codebase using parallel subagent searches with cited summaries.
new-skill
Write a new SKILL.md to teach yourself a procedure for a recurring task. Use when asked to "write a skill", "create a skill", "add a skill", "remember how to…
substack-post
Publishes a local blog file (markdown) to Substack using Playwright MCP browser automation. Trigger when the user says anything like "publish to Substack",…
template-skill
Replace with a description of the skill and when the agent should use it. Write this as a trigger condition: 'Use this skill when...'
subagents-discipline
Invoke at the start of any implementation task to enforce verification-first development