agent-worker

Run agents through a lightweight `agent-browser`-style CLI. Use when another agent needs `agent-run codex|cursor|claude-code|ai-sdk ...` as an immediate direct call, or local send/peek/wait sessions without depending on the daemon.

Use go/setup/audit/goal/design/fact/reframe/close as the stable entrypoint for ordinary agent work. Use when starting or resuming work, choosing autonomous action vs review vs escalation, changing system shape, recording progress, verifying claims, or closing work with a durable record.

Methodology for writing argumentative technical articles — pieces that convince the reader of a specific claim through a chain of reasoning. Use when the user wants a technical article, essay, or book chapter that takes a position — introducing a new idea, challenging an accepted one, or arguing for a particular approach. Triggers on phrases like "write an article/essay/chapter about X," "make the case for X," "argue that Y," or structuring a multi-chapter argument about agents, architectures, systems design, or methodology. Do NOT trigger for tutorials ("how to do X"), reference or API documentation, release notes, changelogs, or pure explainers where no claim is being argued — those need a different framework.

Refactoring existing articles or drafts using a code-refactoring metaphor — extract information units (facts, claims, examples, metaphors) into a neutral inventory, rewrite the skeleton for a new thesis or audience, then inline units with expansion, compression, or transformation. Triggers on "重构这篇文章", "把这几篇合并改写", "用这些素材重写一篇", "这篇骨架我想换但素材想保留", "把旧博客整理重写", "refactor this article", "restructure this draft". Use to restructure existing pieces, merge drafts, repurpose for a different audience, or salvage old writing. Do NOT trigger for writing from scratch (use technical-article-writing) or light polish (use technical-article-writing's `revise`).

Writer voice profile — an MBTI-inspired adaptive assessment that captures a person's cross-genre writing taste and style preferences. Use when the user wants to build or update their writing profile, calibrate AI writing tools to their voice, or find out "what kind of writer am I". Triggers on phrases like "写作画像", "writing profile", "writer type", "我是什么类型的作者", "测一下我的写作风格偏好", "calibrate my writing voice", or any explicit mention of building a writer profile. Produces a file at `~/.claude/writing-profile/profile.md` that downstream writing skills (technical-article-writing, future blog/diary skills) read to adapt AI output to the user's voice.

Run comparative development evaluations: assign the same task to agent-worker team AND claude-code (team subagents), then have an evaluator agent score both and a reviewer agent verify the evaluation. Fully orchestrated — you coordinate all phases, agents notify via channel/callback when done. Use this skill when the user wants to benchmark agent-worker vs claude-code, run a dev eval, compare agent performance, or prove that the workspace team outperforms solo agents. Trigger on phrases like 'dev eval', 'run eval', 'compare performance', 'benchmark', '对比评估', '开发评估', '跑评估', 'eval iteration', '/dev-eval'.

Run web UI performance tests for the agent-worker project. Automates build, daemon restart, cache-bust version bump, Lighthouse audit, and metric reporting — all in one command. Use this skill when the user says "run perf", "check performance", "lighthouse", "perf test", "why is it slow", "check TBT", "性能测试", "跑一下性能", or wants to measure/compare web UI performance. Also trigger after making changes to semajsx/style, render, or any web UI component when performance impact needs verification.

Monitor, inspect, and interact with the agent workspace using the agent-workspace MCP tools. Use this skill when the user wants to check agent status, read workspace channels, send messages to agents, view event logs, inspect the instruction queue, or test how agents behave in the workspace. Trigger on phrases like 'check agents', 'workspace status', 'send message to agents', 'what are agents doing', 'test agent behavior', 'debug workspace', 'monitor agents', 'read channel', 'check queue'.

Write and improve agent prompts using tested principles from Anthropic's constitution, prompt lab experiments, and identity-driven design. Use when creating system prompts, workspace agent instructions, soul definitions, or improving existing prompts. Trigger on phrases like 'write prompt', 'improve prompt', 'craft prompt', 'agent instructions', 'system prompt', 'agent personality'.

Systematically test the @agent-worker/loop and @agent-worker/agent packages against real LLM backends using the aw CLI. A2A tests are interactive, CLI-driven tests — not automated TS scripts. Use this skill when the user asks to test loops, run a2a tests, verify runtime implementations, or check if agent loops work correctly. Trigger on phrases like 'test loops', 'run a2a tests', 'test the runtimes', 'verify loop implementations', 'check if claude/codex/cursor works'.

Run code quality checks: formatting (oxfmt), linting (oxlint), and type checking (tsgo). Automatically fix issues when possible, but only apply fixes that are semantically correct — never suppress errors, add meaningless type casts, or degrade code quality just to pass checks. Trigger on phrases like 'code check', 'check code', 'run checks', 'lint and format', 'typecheck'.

Generate unit tests for a given module using bun:test conventions and existing test patterns. Use when the user asks to generate tests, add test coverage, or create a test file. Trigger on phrases like 'gen test', 'generate tests', 'add tests for', 'write tests', 'test coverage'.