TudouClaw_new

Use for any multi-step task (3+ steps, or "do A then B then C"). Solves the biggest weakness of small/open-source models vs Claude — finishing ONE sub-task then stopping instead of driving the whole task to completion. Pairs with action-first (which kills narrate-and-stop) by adding the cross-step drive — finish a step then immediately start the next, repeat until ALL done. Uses TudouClaw's own plan_update / task_update / agent_todo tools.

Engineering workflow pack — combined planning, implementation, review, and shipping skills (vendored from obra/superpowers, merged 2026-05-04). Use this when working on any non-trivial dev task: brainstorm → plan → implement (TDD) → debug/verify/review → finish branch.

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Use when executing implementation plans with independent tasks in the current session

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use when implementing any feature or bugfix, before writing implementation code

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Use when you have a spec or requirements for a multi-step task, before touching code

Use when the user asks you to produce a PowerPoint (.pptx) file — presentation, slide deck, report, 产品介绍, 市场分析, 路演, 汇报, 会议纪要, PPT. Write a python-pptx script, run it with bash, and verify the output slide-by-slide. This replaces the declarative create_pptx_advanced tool (which has a silent-blank-slide failure mode). Triggers: 生成PPT, 生成pptx, 做一份PPT, slide deck, presentation, 幻灯片.

Project 级共享上下文数据库 - artifacts/decisions/milestones/handoffs/Q&A. Grants tools sc_query, sc_register_artifact, sc_get_artifact, sc_record_decision, sc_handoff

Use when the user asks to 转换 / 导入 / import a skill from an external URL (ClawHub, GitHub README, raw markdown, generic HTML page) into TudouClaw format. This skill fetches + cleans + validates + writes files; the actual semantic conversion from source markdown → TudouClaw SKILL.md + helpers.py is done by the agent's own LLM reasoning using the CONVERSION_PROMPT template provided. Triggers: 转换skill, 导入skill, import skill from URL, 把 clawhub 这个做成 tudou skill, convert skill.

日期计算、JSON/文本处理工具。 Grants tools: datetime_calc, json_process, text_process

读写文件、搜索、目录遍历 — 基础文件系统能力。 Grants tools: read_file, write_file, edit_file, search_files, glob_files

结构化 baton-pass —— 把任务交给下一个 agent。 Grants tools: emit_handoff, handoff_request, team_create

检索知识库、保存经验、跨 agent 共享。 Grants tools: knowledge_lookup, save_experience, share_knowledge, learn_from_peers, memory_recall

给其他 agent / 频道发消息、收消息。 Grants tools: send_message, ack_message, reply_message, check_inbox

创建提醒、延时任务、cron 定时任务。 Grants tools: task_update

执行 bash 命令、跑测试。需要谨慎,有副作用。 Grants tools: bash, run_tests

向 chat 发送结构化 UI 块 (表格、卡片、图等)。 Grants tools: emit_ui_block

搜索网页、抓取内容。研究类任务必备。 Grants tools: web_search, web_fetch

Use when the user asks about Chinese A-share / 港股 / 美股 stocks — 股票行情、K 线、财报、板块资金流、龙虎榜、两融、指数、或要求"分析/研究/查"某只股票。Wraps the AkShare library via `_akshare_helpers.py` with chart generation + structured analysis report template. Output includes charts (PNG inline in chat) and observation-style analysis (NOT investment advice). Triggers: 分析股票, 看下XXX, 查一下股价, 沪深300, 板块资金流, 龙虎榜, 财报摘要.

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Use for every agent that has tools available. Enforces "act, don't announce" — the single biggest source of wasted turns is an LLM saying "Let me fix it:" and then stopping without calling a tool. This skill gives the agent explicit, unambiguous rules for when to narrate vs when to execute.

Use this skill whenever you are asked to review code changes, a diff, or a pull request. Produces structured, actionable review comments focused on correctness, security, readability, and test coverage — not stylistic nits.

Use whenever a tool produces a file (screenshot, PDF, recording, download, generated asset). All artifacts MUST land under $AGENT_WORKSPACE before being reported as deliverables. TudouClaw's sandbox rejects paths outside deliverable_dir — this skill prevents that failure at the source.

Use when the agent needs to drive a real browser — open a page, read DOM, click/fill/submit, take a screenshot, or save a page as PDF. Wraps the `agent-browser` Node CLI (invoked via Bash). Covers the accessibility-tree + ref-based workflow that makes scripted browsing reliable, and calls out two recurring pitfalls — (1) deliverables landing outside $AGENT_WORKSPACE and (2) multi-URL PDFs with identical pages.

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.

高级PPTX制作技能。当需要制作精美、专业的演示文稿时使用此技能。 支持信息图表、图表、多栏布局、流程图、时间轴等高级元素。 包含完整的制作流程：结构规划→内容填充→审美优化→生成输出。

Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.