openspec
Lightweight specification-driven framework to coordinate human and AI coding collaboration. Core Scenario: When the user wants to initialize a project, manage…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,666 results
zhipu
Integrate Zhipu AI (GLM) for advanced language modeling and image understanding. Core Scenario: When the user wants to use Zhipu's GLM models for chat,…
mcp-builder
MCP (Model Context Protocol) server building principles. Tool design, resource patterns, best practices.
hunt-llm-ai
Hunt LLM/AI feature bugs — prompt injection, indirect injection, exfiltration via tool-use, ASCII smuggling, agentic AI security framework (ASI01-ASI10).…
claude-code-sdk
Claude Code extensibility and configuration reference: plugins, plugin dependencies, hooks, skills, rules, subagents, agent teams, channels, MCP servers,…
multi-agent-orchestration
Use when, and only when, the user explicitly requests multi-agent-orchestration, a multi-agent long-task workflow, subagents, external agents, model diversity,…
claude-review-loop
Iterative Claude review-and-fix loop
dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
cancel-ecomode
Cancel active Ecomode mode
agent-ledger-and-delivery
Use when designing agent_chats or agents_chat records, delivery evidence summaries, linked tasks or commits, validation notes, risks, review notes, or handoff…
audit-agentic-cli
Use skill if you are auditing or designing a CLI for agent/LLM consumption — stable JSON output, exit codes, non-interactive flags, or iterative repair loops…
build-clean-mcp-architecture
Use if structuring or auditing TypeScript mcp-use/server code for Clean Architecture boundaries.
build-mcp-use-apps
Use skill if you are building or modifying an mcp-use app with tools, resources, prompts, widgets, auth, or deployment concerns.
run-issue-plan
Use skill if you are executing a project plan stored as GitHub Issues with sub-issues by reading the tree, dispatching subagents wave-by-wave, and tracking…
codex-subagent
Spawn Codex subagents via background shell to offload context-heavy work. Use for: deep research (3+ searches), codebase exploration (8+ files), multi-step…
aiops
Flow Conductor for the aiops bundle. One entry — infers task type, shows plain-language steps, tracks journey in flow.state.yaml, dispatches skill + agent per…
glm-master-skill
Documentation-only master skill for GLM ecosystem discovery and installation. This skill does not execute scripts or subprocess commands. It provides a curated…
kitaru-insights
Read many recorded Kitaru sessions with the user's own coding agent and subagents, find recurring failure and success patterns that fixed counters miss, and…
lesson-propose
Use at task wrap-up, after a mistake, or on a postmortem to turn the correction journal and observations into review PROPOSALS — classify each candidate lesson…
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…
aisdlc-project-discover-products-aggregation
Use when you need to reverse-engineer business modules (products) from existing code/contracts/data ownership and converge to a governable number (recommended <=6), to avoid loss of control over cognition and maintenance, while providing a stable map for cross-module discussions.
build-zoom-meeting-app
Build or embed a Zoom meeting flow. Use when implementing Meeting SDK joins, web or mobile meeting embeds, meeting lifecycle flows, or when deciding between…
build-zoom-team-chat-app
Reference skill for Zoom Team Chat. Use after routing to a chat workflow when building user-scoped messaging integrations, chatbot experiences, rich cards,…
choose-zoom-approach
Choose the right Zoom architecture for a use case. Use when deciding between REST API, Webhooks, WebSockets, Meeting SDK, Video SDK, Zoom Apps SDK, Zoom MCP,…