跳到正文
cccskills
免费在 GitHub 公开

task-track

[Project Management] Use for explicit project-owned tracker guidance (--mode=guide), or portable-engine work records, placement, linked concerns, lifecycle, evidence, acceptance and local status. Existing engine modes and bare inspect remain supported.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(30)

  • SKILL.md2.8 KB
  • assets/app.js239.2 KB
  • assets/favicon.svg365 B
  • assets/fonts/OFL-red-hat-display.txt4.4 KB
  • assets/fonts/OFL-red-hat-mono.txt4.4 KB
  • assets/fonts/OFL-red-hat-text.txt4.4 KB
  • assets/fonts/red-hat-display-latin-ext-wght-normal.woff213.7 KB
  • assets/fonts/red-hat-display-latin-wght-normal.woff230.0 KB
  • assets/fonts/red-hat-mono-latin-ext-wght-normal.woff211.4 KB
  • assets/fonts/red-hat-mono-latin-wght-normal.woff221.9 KB
  • assets/fonts/red-hat-text-latin-ext-wght-normal.woff213.4 KB
  • assets/fonts/red-hat-text-latin-wght-normal.woff229.4 KB
  • assets/fonts/SOURCE.txt574 B
  • assets/index.html2.5 KB
  • assets/style.css80.0 KB
  • lib/browser-launch.cjs5.1 KB
  • lib/package-setup.cjs7.9 KB
  • lib/report-view.cjs136.6 KB
  • lib/shared-snapshot.cjs15.9 KB
  • lib/terminal-launch.cjs6.4 KB
  • lib/workspace-server.cjs17.1 KB
  • package-lock.json1.7 KB
  • package.json280 B
  • references/engine-protocol.md26.7 KB
  • references/integration-guide.md21.7 KB
  • references/manual-operations.md73.5 KB
  • references/project-guide.md3.1 KB
  • scripts/task-track.cjs20.7 KB
  • tests/browser-support.cjs12.3 KB
  • tests/workspace-browser.test.cjs416.6 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Quick Summary

Goal: Support the selected project's tracker conventions or the portable work engine through one explicit entry point. Read only the selected route's reference before acting. These modes are skill purposes, not CLI flags; never pass --mode=guide to the engine command.

InvocationRead and follow
--mode=guideProject guide: discover the selected checkout's root-linked work-tracking instruction and use its documented mechanism
Bare invocation, or --mode=inspect|maintain|link|lifecycle|verify|accept|report|serveEngine protocol: preserve the bare inspect default and existing operation safeguards
Any other modeRefuse without an operation

Choose by the invocation, never by the presence of a tracker folder, root pointer or configured engine. When both exist, explicit guide uses project instructions; an old mode still uses the engine protocol. Project prohibitions and unsupported engine capabilities remain binding; never switch routes to bypass a refusal. Guide mode does not initialize, enroll or migrate a tracker, and does not require portable-engine configuration.

Honor the active host's Run/Skip and disabled-selection controls. This skill remains manual-only; a named authorized invocation remains usable. Invocation supplies guidance, not permission for assignment, acceptance, publication or other actions beyond the user's request.

Project customization

For engine command recipes, read manual operations when the selected engine route needs exact requests, placement or refusal recovery. Read the integration guide when recording an actual saved producer checkpoint or interpreting exact linked concerns. These are engine references; project-guide mode keeps the selected project's own guide and mechanism.

Read the selected checkout's root instructions (CLAUDE.md or AGENTS.md) when resolving its work-tracking guide. The project owns its guide path, storage, lifecycle, placement, evidence, acceptance and checks. Change those at the project owner; keep them out of this portable skill. Additive project overlays may add steps, but cannot replace either route's requirements or waive an authority or verification gate.

Closing reminders

Select the route explicitly; read its reference before acting; preserve project rules and actual human authority. Report only checks and outcomes observed.

评价

还没有评价。欢迎分享你的使用感受。

评论

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。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

[Documentation] Use when generating, smart-merging or refactoring the root AI context (CLAUDE.md, AGENTS.md) and its Claude/Codex projections. Config file only: project-config.

中文简介正在准备中。当前显示原文说明。

duc01226/EasyPlatform122026年10月18日 更新

[Code Quality] Use when a workflow step or the user asks for AI code or plan review: LLM calls, prompts, agents, RAG, evals and guardrails. --mode={code|plan}; --report-only is read-only.

中文简介正在准备中。当前显示原文说明。

duc01226/EasyPlatform122026年10月18日 更新

[Architecture] Use when a workflow step or the user asks for architecture design, compliance review, scalability grading or whole-project audit via --mode={design|review|scalability|full}.

中文简介正在准备中。当前显示原文说明。

duc01226/EasyPlatform122026年10月18日 更新

[Content] Use when a workflow step or the user asks for product/feature ideation with ranked opportunities and validation tests. --mode={roadmap|scope}.

中文简介正在准备中。当前显示原文说明。

duc01226/EasyPlatform122026年10月18日 更新

[Content] Use when a workflow step or the user asks for business viability: Business Model Canvas, financials, risks and go-to-market recommendation.

中文简介正在准备中。当前显示原文说明。

duc01226/EasyPlatform122026年10月18日 更新

[Code Quality] Use when a workflow step or the user asks for a focused code-change review: staged, unstaged, branch diff or simple pull request. --fix-loop fixes and re-reviews. Complex pull request: workflow-review-changes; rationale: why-review.

中文简介正在准备中。当前显示原文说明。

duc01226/EasyPlatform122026年10月18日 更新

查看 duc01226 的全部技能

报告此技能的问题