SCENARIO / LEVEL 2
Skill与智能体开发 Skills
Agent Building
编写 Skill、MCP 服务与智能体工作流
Skill与智能体开发 的 Skills 39464
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
agent-host-logs
Analyze Agent Host debug log exports. Use when given an ah-logs or ahp-logs zip/folder, an Export Agent Host Debug Logs bundle, events.jsonl, AHP JSONL transport logs, Agent Host.log, remote-agenthost.log, or copilot-logs.
agent-host-e2e-tests
Use when writing, recording, updating, validating, or troubleshooting Agent Host end-to-end and real-provider integration tests under src/vs/platform/agentHost/test/node/e2e and providerIntegration. Covers adding a cross-provider test, re-recording fixtures after an SDK bump, required cross-platform Azure validation, gating non-deterministic or platform-specific tests, and diagnosing replay cache misses.
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
autoplan
Auto-review pipeline — runs the CEO, design, eng (architecture, edge cases, failure modes, tests) and DX reviews (lean run: one reviewer), auto-deciding. (gstack)
write-skill
Write a new agent skill or improve one without bloat: the edit ladder, levels, drift and size checks, full diets. (gstack)
sync-gbrain
Keep gbrain current with this repo's code and refresh agent search guidance in CLAUDE.md. (gstack)
setup-gbrain
Set up gbrain for this coding agent: install the CLI, initialize a local PGLite or Supabase brain, register MCP, capture per-remote trust policy. (gstack)
pair-agent
Pair a remote AI agent with your browser. (gstack)
land-and-deploy
Land and deploy workflow. (gstack)
benchmark-models
Cross-model benchmark for gstack skills. (gstack)
gstack
Router for the gstack skill suite. (gstack)
ui-tests-pipeline-ci
Microsoft FTE-only completion workflow for PowerToys UI-test implementation: automatically continue after successful local VM suites, commit and push scoped changes, queue CI, wait synchronously, and stabilize through Azure CLI and Azure DevOps REST APIs. No separate push/run-CI request is needed for create, migrate, or stabilize tasks unless the user limited scope. Also use for explicit UITests CI, setup preflight, 401/403 diagnosis, build reuse, recordings/artifacts, and the three-run limit. Keywords: FTE, az, Azure CLI, Azure DevOps, pipeline, UI Test Automation, UITests CI, commit, push, local-to-CI handoff, buildNow, specificBuildId, uiTestModules, CI flake.
skill-installer
Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).
skill-creator
Create or update a Codex skill with appropriately scoped instructions and any needed supporting resources.
review-agent
Perform a read-only, defect-first review of a specified code change and return every actionable finding. Use when another agent delegates review of uncommitted changes, a base-branch diff, a commit, or custom review instructions.
openai-docs
API first-timers, Codex/Work Q&A. If the user already has an OpenAI API integration, skip this skill for API questions and use the developer docs. Read this skill before answering how Codex or ChatGPT Work behaves, where to find a feature, or how to configure or troubleshoot this app or coding agent. This includes conversation history, model and cache behavior, instruction precedence, permissions, and tool availability. Use for API onboarding only when the user is connecting to the OpenAI API for the first time. Skip action requests, such as scheduling an automation, and tasks fully answered by supplied text or data.
playwright-dev
Explains how to develop Playwright - add APIs, MCP tools, CLI commands, and vendor dependencies.