Workflow Router

Community

KerberosClaw

workflow-router

Use when the user is unsure which engineering workflow skill to use: discussion, dispatch or code review, a full spec lifecycle, PRD/ADO, ADR, debugging, documentation, QA or release readiness. Choose the smallest applicable route, explain it, then hand off. The router does not author artifacts or execute tasks itself.

Overview

Publisher	KerberosClaw
Repository	`kc_ai_skills`
Skill name	`workflow-router`
Stars	79
Forks	14
Bundled files	1
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
1 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by KerberosClaw on GitHub. Read the source before you install it.

Installation

Install the Workflow Router AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/KerberosClaw/kc_ai_skills/tree/main/workflow-router
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/KerberosClaw/kc_ai_skills.git /tmp/kc_ai_skills
mkdir -p .claude/skills
cp -r /tmp/kc_ai_skills/workflow-router .claude/skills/workflow-router

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Workflow Router in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Workflow Router on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Workflow Router is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

workflow-router — 依現在要做的事選入口

You are a workflow triage router. Choose the smallest route that fits the user's current work, explain why, then hand off. A workflow is a menu, not a mandatory chain of skills.

要看全景才讀流程圖與 skill 地圖；一般分流不載入整包 skill。

1. 判斷目前拿到什麼

目前工作	路由	接下來
先討論、目標或取捨未定	`grill`	查現況、一次一題談到共同理解
已談妥，準備寫派工單交給 agent	main 寫草稿，再 `review-gate`	補必要執行資訊，審查處置完成後依授權交出；不另叫派工作者 skill
已有派工草稿、需求／計畫，想審能不能照做	`review-gate`	採派工／需求判準，保留來源與版本
程式已實作，要審缺陷與回歸	`review-gate`	採程式碼判準；測試與 QA 另依任務執行
要在 repo 完整管理需求、計畫、tasks、實作與驗收	`spec`	需要完整 lifecycle 才選；內部在實作前、實作後接 review-gate
已核准且明確的小任務，要直接執行	原執行流程	沿現有授權做，不重開訪談或補完整 spec
Bug、crash、錯誤輸出、flaky，原因未明	`diagnose`	重現，再驗證假說
需要正式產品 PRD／stakeholder 文件	`prd-create`	寫或修產品文件，不因有 raw notes 就強迫走 PRD
核可 PRD 要拆工項／推 ADO	`prd-breakdown`	vertical slices 與工項關係
已定的重要技術取捨要記理由	`adr`	先過 ADR 判準，記錄／引用後回原流程
UI／使用流程 QA	`doc-qa:qa`	從已核准需求推案例並實跑，保留能力與證據限制
現有文件落後於實作／hotfix	`align`	手動先定觸發範圍或全庫；無人值守沿工單範圍，未指定預設全庫
缺專案技術文件、手冊或維護交接	`doc-qa:project-docs`	依現有 code 補建，不先設計新功能
明確要 GitHub／公開發布整備	`prep-repo`	適用的洩漏、安裝、測試與交付檢查

qa、project-docs 由 doc-qa plugin 提供。依賴／subagent 缺少時如實回報，不把自審當雙 agent，不把單元測試當 UI QA。

2. 只在真的分不出來時問一題

路由清楚就直接說並接續，不請使用者再選一次。必要時一次問一題，建議選項放前面，例如：「你要先把需求談清楚（grill），還是要一路管理到實作驗收（spec）？」

無人值守是執行方式。 「跑一整晚」不新增一顆 skill；需求已定，由 main 寫可交接工單、接 review-gate。已授權的文件或其他工作仍沿原路執行。
grill 不強制接 spec。 常用路徑可直接是討論 → main 工單 → review-gate → 執行與驗收。只有使用者要完整開發生命週期才走 spec。
審查流程只由 review-gate 維護。呼叫方提供專業判準與受審版本；不在 router 複製角色、處置分類或輪數。只需審新增工單內容時，不重審已有效審過的相同需求版本。
PRD／ADO 看交付物，不看是公司或個人、交給人類或 agent。「FR／AC／SD」等縮寫本身不能決定路由。
ADR 記已定取捨，不代替未決需求、規格或變更授權；記完回原流程。
完整開發的實作、AC／測試、程式審查、適用 QA、文件對齊與回報各有用途。已授權完整無人值守任務就接續；缺工具、未驗證或阻塞不能靠下一階段完成洗成成功。正式 PRD、ADR 不因這次新增 review-gate 就自動加審。
QA 依需求推案例，不要求 project-docs 前置。Web 用 Playwright；原生桌面／跨 App 需支援該 driver、具 computer-use 的執行端。查證無 UI 才記不適用；有 UI 卻缺能力仍是未測。版本與出口契約由 QA skill 維護。
align 可獨立執行，不要求先跑 QA；只修授權 repo，跨 repo 可讀查證，修改另依授權。缺文件用 project-docs，不預設兩顆都跑。
既有的執行、訊息、合併與部署授權持續有效；路由不擴大權限，也不新增排程或背景服務。

3. 簡短交棒

用一兩句說「用哪顆、因為什麼」，有能力就載入目標 skill 繼續；否則給可直接用的呼叫方式。需要 main 整理工單時，交回 main 作者職責，router 自己不寫。

goal-engineer 入口已退役。 派工紀律隨 grill 提供，共用審查由 review-gate 負責；歷史候選擇優模板可從 Git 記錄取回，不當成現行入口。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

docs/workflow.md9 KB

Frequently asked questions

What does the Workflow Router AI skill do?

Why use Workflow Router on TypingMind?

Because you install it once and use it with any model. Workflow Router is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Workflow Router in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/KerberosClaw/kc_ai_skills/tree/main/workflow-router. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Workflow Router?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Workflow Router?

As many as you like. As long as a model supports skills, you can use Workflow Router with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Workflow Router AI skill free?

Yes. It is published on GitHub by KerberosClaw under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Claw Score

openclaw

OrganizationPopular

Audit or refresh OpenClaw maturity scorecard docs from root taxonomy, maturity scores, and QA evidence artifacts without using maintainer discrawl data or committed inventory reports.

Clawsweeper

Use for all ClawSweeper work: OpenClaw issue/PR sweep reports, repair jobs, cloud fix PRs, @clawsweeper maintainer mention commands, trusted ClawSweeper-reviewed autofix/automerge, GitHub Actions…

Control Ui E2e

Use when designing, testing, fixing, or extending the OpenClaw Control UI GUI, including UI stress-test galleries with feedback inputs, Vitest + Playwright end-to-end checks, mocked Gateway flows,…

Deslop

Diff-scoped AI-slop cleanup pass: strip comment slop, defensive-check slop, type-laundering, and style drift from the current branch diff before autoreview.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

workflow-router — 依現在要做的事選入口

1. 判斷目前拿到什麼

2. 只在真的分不出來時問一題

3. 簡短交棒

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now