Use when manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
中文简介正在准备中。当前显示原文说明。
Adds new visual examples to the tdmcp prompt cookbook documentation — both the English and Portuguese versions. Use when asked to: add more cookbook examples, create visual examples for the docs, show more surprising things you can do, add entries to the prompt cookbook, expand the cookbook, or any request to extend the cookbook with new prompts and results. Runs a 3-phase pipeline: curate candidates → write EN → write PT.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Adds new, visually impressive examples to docs/guide/prompt-cookbook.md (EN)
and docs/pt/guide/prompt-cookbook.md (PT).
Execution mode: sub-agents (sequential curation → parallel EN+PT writing).
Before doing anything, check:
_workspace/cookbook_candidates.md already exist?
_workspace/cookbook_candidates_prev.md, re-curate.Spawn the cookbook-curator agent with this prompt:
Read the task description in .Codex/agents/cookbook-curator.md and execute it.
Survey src/tools/layer1/index.ts, src/tools/layer2/index.ts, recipes/*.json,
docs/ROADMAP.md, CHANGELOG.md, and docs/guide/prompt-cookbook.md.
Produce _workspace/cookbook_candidates.md with 15-20 new cookbook candidates.
Wait for it to finish before continuing.
Once _workspace/cookbook_candidates.md exists, spawn two writer agents in parallel:
EN writer:
Read .Codex/agents/cookbook-writer.md for your role and format rules.
Language: English.
Target file: docs/guide/prompt-cookbook.md
Candidates: _workspace/cookbook_candidates.md
Add all candidates marked for EN to the target file, following the exact format.
Write a summary to _workspace/cookbook_write_en.md when done.
PT writer:
Read .Codex/agents/cookbook-writer.md for your role and format rules.
Language: Brazilian Portuguese.
Target file: docs/pt/guide/prompt-cookbook.md
Candidates: _workspace/cookbook_candidates.md
Add all candidates to the target file, translating from the EN prompts in the
candidates file. Match the existing PT file's voice and format.
Write a summary to _workspace/cookbook_write_pt.md when done.
After both writers finish, do a quick consistency check:
src/tools/layer1/index.ts or src/tools/layer2/index.ts./examples/SLUG.mp4 or .png) points to a file that
already exists in docs/public/examples/ under a conflicting name.If any check fails, note it in _workspace/cookbook_qa.md with what needs fixing.
Do not auto-fix — report to the user.
After all phases complete, summarize:
.mp4 / .png) referenced in new entries don't exist
yet — the user should capture them from TD and drop them in docs/public/examples/
(or leave the entries as description-only; the cookbook already has many without media)If candidates and writer summaries already exist and the user wants to add more:
_workspace/cookbook_candidates.md还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Use when manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
中文简介正在准备中。当前显示原文说明。
Use when a hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
中文简介正在准备中。当前显示原文说明。
Reference for how BDB structures autonomous software engineering work — the seven-node dispatcher graph (Architect, TechLead, UI/UX, Engineering, Media/EventTech, Reviewer, Shipping) that /startcycle-graph actually runs. Use when you need the high-level lifecycle framing without inventing your own process.
中文简介正在准备中。当前显示原文说明。
Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling.
中文简介正在准备中。当前显示原文说明。
Harness patterns for coding agents — memory, permissions, context engineering, delegation, skills, hooks, bootstrap.
中文简介正在准备中。当前显示原文说明。
agenttrail: live map of a multi-agent build in the browser: which plan component is being worked on, by which agent or harness, what is done and what is stuck. Use when a multi-agent pipeline starts (/startcycle, /startcycle-graph, /teamwork-preview) or after a plan-canvas approve, when the user asks to see what the agents are doing ("live map", "build board", "who is running now"), or by yourself whenever a multi-agent run is under way — no user prompt needed.
中文简介正在准备中。当前显示原文说明。