semantius-architect
Produces and maintains semantic blueprints: entity-level specs of entities, roles, relationships, lifecycle states, and permissions, with no field-level detail…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-28 00:17
Agents & models
24,968 results
agent-package-sync
Pre-upload synchronization workflow for company-internal agent/expert result packages. Used to check result package changes, synchronize AGENTS.md naming, repackage only updated skill zips based on git changes, exclude caches, and output an upload manifest; does not execute git commit or push.
manage-skills
Discover, list, create, edit, toggle, copy, move, and delete AI agent skills across 11 tools (Cursor, Claude, Agents, Windsurf, Copilot, Codex, Cline, Aider,…
langgraph-state-management
Design state schemas, implement reducers, configure persistence, and debug state issues for LangGraph applications. Use when users want to (1) design or define…
retro
Analyze one or more completed or paused agent runs and preserve an evidence-backed retrospective for improving future work. User-invoked only; produce a…
skill-guide
Explain available skills, compare their boundaries, or recommend what the user should invoke next. User-invoked only; provide guidance and example prompts…
optimize-prompt
Prompt optimization consultant for AI system prompts and custom instructions. Supports Claude API, OpenAI API, Gemini API, CLAUDE.md, ChatGPT, and n8n. Use…
gimbal-workflows
Design and author Gimbal workflows as ordinary Go. Covers workflow structure, agent roles, context and handoffs, adaptive planning, supervision, independent…
chips
Run the project's suggested-task ledger, the chips. /chips alone brings every open task up to date: it applies what the ledger helper says, settles stale and…
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent,…
building-llm-backed-features
Builds application features on top of an LLM API in Python — prompt surfaces that drift apart, structured outputs, context budgeting, model/config wiring,…
copy-link
Copy and print the current Claude Code or Codex session's link, preferring Claude's existing Remote Control HTTPS URL.
yzr-llm-wiki-management
Use this skill when the user interacts with a local, single-user, compound-interest Markdown personal wiki (Karpathy 'LLM owns wiki' mode)—covering: initial setup, batch ingestion of raw/ materials (papers / articles / clippings / external code repo symlink integration), cross-page synthesis / comparison / contradiction reconciliation / answer archiving back…
claude-computer-use-advanced
Advanced computer use patterns for UI automation, application control, and multi-step workflows using Claude's computer use tool. Use when automating desktop…
boltzgen
All-atom protein design using BoltzGen diffusion model. Use this skill when: (1) Need side-chain aware design from the start, (2) Designing around small…
skill-builder
Use when creating new skills, optimizing existing skills, or auditing skill quality. Guides skill development following Claude Code official best practices.
bootstrapping-agent
Wires up an Airbyte connector for use in a PydanticAI, Claude SDK, or other agent. Generates auth config, connector initialization, prebuilt connector tools,…
building-multi-connector-agent
Builds a complete agent with multiple Airbyte connectors using PydanticAI or Claude SDK. Scaffolds project structure, wires up connectors, composes tools, and…
handoff
Create a compact handoff document so another agent can continue the current conversation. Use when the user asks for a handoff to another agent or a checkpoint…
altinity-profiler-clickhouse
Profile a ClickHouse cluster via MCP and emit a per-cluster "analyst" Skill the user can save in claude.ai. Activate when the user asks to "profile this…
mav
Use MAV, the Mobile Agent Verifier CLI, to validate iOS and macOS apps through deterministic simulator/device/mac actions, configurable launch recipes,…
ai engineer
Focuses on LLM application development, covering RAG and LangChain architecture.
botlearn
BotLearn — AI Agent capability platform CLI. **Core value: `learn`** — run the 5-stage learning loop (Read → Distill → Engage → Discover → Report) end-to-end…
grill-with-docs
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.