A task-planning stage that turns an approved software design into a TASK.md file containing smaller implementation tasks. It uses structured task data and checks that earlier planning stages are complete.

Use it to prepare implementation plans for API, user-interface, and other software changes, including task slices, dependencies, files to edit, and completion checks.

It removes the ambiguity between a design and the concrete work needed to build it. File boundaries, dependencies, estimates, and verification requirements are recorded before development starts.

taiyi-task — Skill for Claude Code and Codex by Dong90

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add Dong90/oh-my-taiyiforge --skill taiyi-task

Clone the repo

git clone --depth 1 https://github.com/Dong90/oh-my-taiyiforge

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dong90/oh-my-taiyiforge/taiyi-task/github.svg)](https://agentmods.dev/skills/dong90/oh-my-taiyiforge/taiyi-task)

Your own site

<a href="https://agentmods.dev/skills/dong90/oh-my-taiyiforge/taiyi-task"><img src="https://agentmods.dev/badge/skills/dong90/oh-my-taiyiforge/taiyi-task/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/dong90/oh-my-taiyiforge/taiyi-task"><img src="https://agentmods.dev/badge/skills/dong90/oh-my-taiyiforge/taiyi-task.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,522 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 3 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium MCP Rug Pull · line 17
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]
medium MCP Rug Pull · line 199
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]
medium MCP Rug Pull · line 155
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00024	$0.02522
Opus 5	$0.00012	$0.01261
Sonnet 5	$0.00005	$0.00504
Haiku 4.5	$0.00002	$0.00252

Measured 11d ago against content hash 40770f85939d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

taiyi-task scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/taiyi-task/SKILL.md · 243 lines

How it starts

The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.

taiyi-task — 任务拆解

进入本阶段前请优先读 .taiyi/changes/<slug>/PHASE-CONTEXT.md（~500 tokens），不要全量加载上游工件。

框架集成

本阶段使用以下框架：

框架	用途	何时加载
Harness	阶段门禁与推进（`status` → `continue`；legacy：`npx taiyi complete`）	全程
OMO	任务切片遵循 OMO 垂直切片规范	T1 任务拆解步骤

Superpowers / GStack / OpenSpec / Spec-Kit 在本阶段不涉及。

前置门禁（Pre-flight）

0.1 上游确认

ui-design 已过关（如有 UI 层；skippedPhases 含 ui-design 时可跳过）；design 已过关

0.2 Profile 判定

Profile	TASK.md 要求
`full`	完整：T0X 逐层检查 + 入口预设 + 任务拆解 + 估算 + Scope Break + 全局 Resources
`api/ui`	同 full
`lite`	简化版：可跳过 T0X 和 Scope Break
`micro/spike`	可跳过本阶段
`nano`	跳过

0.3 前置检查清单

上游阶段已过关（DESIGN；需 UI 时含 ui-design，以 engineTruth.skippedPhases 为准）
理解 DESIGN.md 中两个方案的取舍理由

步骤

工件契约

层	路径	职责
语义真源	`task.json`	Zod（`src/schemas/task.ts`）
生成视图	`TASK.md`	hbs（`src/templates/task.hbs`）
流程	本 Skill	T0.x 检查、切片、write_files 边界

工作流：编辑 json → scripts/taiyi-forge.sh render <slug> task → status → continue。

详见 docs/taiyi/artifact-contract.md。

json 字段（Zod 摘要）

字段	要求
`title`	任务拆解标题
`slices`	≥1 切片；`id` / `description` / `write_files` / `dependencies` / `test_command`
`waves`	可选；执行波次与 slice 分组
`slice_risks` / `slice_rollbacks`	可选；风险与回滚
`scores` / `completeness_score`	可选；自评 0–10
`evolutionSuggestions`	可选；架构沉淀

切片字段对齐下文 T1 主任务拆解 六要素（Level → time_estimate、Verify → test_command / verification）。

写作指引（填入 json，render 生成 TASK.md）

入口预设（写在 TASK.md 顶部）

# TASK: <slug 描述性标题>

## Engineer Context
- 本 change 在 TaiyiForge 第 5 阶段（task）
- UI-DESIGN.md 与 DESIGN.md 确认了方案
- 你只能从 TASK 任务池中挑选，**不实现未列出的功能**
- **不修改**非 write_files 清单中列出的文件

T0X 逐层检查（T0.1 - T0.7）

每层检查结果为 ⛔（阻止）/ ⚠️（需更新）/ ✅（通过）：

### T0.1 技术栈决策确认
- [ ] 语言版本（TS 5.x / Python 3.12+）
- [ ] 框架（Express / Next.js / Gin）
- [ ] 组件库（Shadcn / MUI / BYO）
- [ ] 测试框架（Vitest / Pytest / Jest）
- [ ] 样式方案（Tailwind / CSS Modules / CSS-in-JS）
- [ ] 所有项通过 ✅ → 继续

### T0.2 文件分析
前置：grep/glob 扫描项目文件结构。
- [ ] 新文件路径不与现有文件冲突
- [ ] 修改已知文件时已在项目中找到
- [ ] 无依赖遗漏（如缺少的 npm 包）

### T0.3 影响与兼容
- [ ] 没有改到公共 API 签名（如有需在 TASK 中声明）
- [ ] 没有引入破坏性 DB 迁移
- [ ] 改 schema 时同时有 up + down 迁移

### T0.4 测试兼容
- [ ] 知道已有测试的 runner 命令和配置文件路径
- [ ] 新增测试定位遵循项目模式（unit / integration / e2e）
- [ ] 已有测试不因本 change 而需要重构

### T0.5 设计兼容
- [ ] 新代码沿用 DESIGN.md 约束（如 Modest vs Bold 方案）
- [ ] 没引入 DESIGN 未讨论的新抽象/模式

### T0.6 UI 兼容（仅 UI 层 change）
- [ ] 色值/字体/间距引用 UI-DESIGN.md 或 project tokens
- [ ] 组件路径不与已有组织冲突

### T0.7 遗留决策记录

Notion	Decision	Alternate	Consequences	T0.X 检查


---

### T1. 主任务拆解

每个任务格式相同的 6 字段节：

Read the full file on GitHub · 243 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

11d ago First seen · 243 lines · 24 tokens per session scan A 40770f85939d

Subscribe to this mod's changes

taiyi-task is a skill published in the GitHub repository Dong90/oh-my-taiyiforge (888 stars, last pushed 4d ago), licensed MIT. It adds 24 tokens to every session and 2,522 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Code Generation LLM Planning ai automation developer-tools plugin

review

Use when the user wants code assessed rather than changed — "review PR 88", "is this branch ready to merge?", "look over my changes", "any problems with this diff?", "give me a code review", "what do you think of this PR?", "sanity-check this branch", "ship it?". Applies to a pull request or the current branch when…

The01Geek/prflow · 123 tokens

fix

PRFlow's code-review reception skill (formerly receiving-code-review), used by the review-and-fix loop and available directly. Use when addressing review feedback already posted on a pull request — verifying findings before applying them — as distinct from /prflow:review-and-fix, which runs the review itself and then…

The01Geek/prflow · 82 tokens

review-and-fix

Use when the user wants problems in a pull request or the current branch both found AND corrected — "review my changes and fix what's wrong", "clean up whatever the review turns up", "address the review feedback on this branch", "tidy this PR up before merge", "find and fix the issues here". Requires explicit fix…

The01Geek/prflow · 88 tokens

create-issue

Transitional alias — prefer /prflow:specs, which runs the same issue-drafting pipeline. Use when a rough user story, bug report, feature idea, piece of feedback, or an implementation plan should be recorded as a GitHub issue rather than built right now. This command name is retained so existing /prflow:create-issue…

The01Geek/prflow · 89 tokens

neurolink-guide

Guide for using the NeuroLink SDK and CLI. Invoke when users ask how to use neurolink, integrate AI providers, add MCP tools, configure RAG, set up memory, deploy servers, or work with multimodal content. Covers SDK, CLI, providers, tools, and enterprise features.

juspay/neurolink · 65 tokens

docs-sync-internal

Use when code changes on the current branch need matching internal or developer documentation — "update our internal docs", "the architecture docs are stale after this change", "document what I just changed", "do the dev docs still match the code?" — or as a pre-push check that developer docs track the code. Narrower…

The01Geek/prflow · 105 tokens