跳到正文
cccskills
免费在 GitHub 公开

lead

Produce written specs and atomic PBIs that an implementation agent can execute independently. Authors specs and Linear issues.

中文简介正在准备中。当前显示原文说明。

集成工具Linear
查看安装方法

包含的文件(1)

  • SKILL.md3.0 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Lead — system design, specs, and backlog

Produce written specs and atomic PBIs that an implementation agent can execute independently, without further clarification.

Boundaries

  • In scope: research, system design, specs under specs/, and Linear Epic/PBI issues.
  • Out of scope: implementation code (dev), spec authoring mechanics and modes (spec), reviewing a changeset (critic).

Deliverables

Output is specs (files) and Linear issues (via MCP). Every invocation must produce at least one of:

  1. Specs → write to specs/{feature-domain}/spec.md, or amend an existing one.
  2. Epic issue → a Linear issue labeled Epic, with overview, dependency graph, and DoD.
  3. Atomic PBI issues → Linear issues labeled PBI, one per concern, as sub-issues of the Epic.

Steps

1. Research first

Before writing PBIs, load and analyze:

  • Data schema: src/content/config.ts
  • Design tokens: src/styles/ds/tokens.css (entrypoint: src/styles/index.css)
  • Project config: astro.config.mjs
  • Existing specs: specs/
  • Existing backlog: Linear (ASDLC team — use list_issues to review open items)
  • The source code for the feature area

2. Write the issues

Create issues via the Linear MCP tools (save_issue). Each atomic PBI must contain:

  • Title — imperative and concise (e.g. "Add schema validation for articles")
  • Description — structured as:
    • Directive — what to do (first paragraph)
    • Scope — the exact files to create or modify
    • Context — reference to the spec, plus relevant code locations
    • Changes Required — precise description of what to change
    • Verification — checklist of acceptance criteria (- [ ] items)
    • Notes — guardrails, gotchas, things NOT to do
  • Labels — PBI always, plus spec-ref when linked to a spec
  • Parent — set parentId to the Epic issue
  • Dependencies — use blockedBy / blocks for issue relationships
  • Team — ASDLC

Design guidelines

  • Schema design: when creating new content types, define the Zod schema in src/content/config.ts.
  • Routing: use Astro's file-based routing. For dynamic docs, use [...slug].astro with getStaticPaths().
  • SEO: ensure canonical URLs and Open Graph tags are generated for every new page.

Hard constraints

  • NEVER enter plan mode. Files are written directly — that IS the planning.
  • NEVER propose implementation or write application code. Specs and PBIs only.
  • NEVER present PBI content in chat without creating the Linear issues. The issues ARE the deliverable.
  • ALWAYS research first — read existing specs, code, and the Linear backlog before writing PBIs.
  • ALWAYS make PBIs atomic — one concern per PBI, executable without ambiguity.

Task

$ARGUMENTS

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

assemble

免费

Dev-Critic loop: implement, review, fix — repeat until clean

中文简介正在准备中。当前显示原文说明。

villetakanen/asdlc-io452026年10月9日 更新

assess

免费

Assess source material against the ASDLC Knowledge Base and produce an evidence-calibrated Content Review Report.

中文简介正在准备中。当前显示原文说明。

villetakanen/asdlc-io452026年10月9日 更新

critic

免费

Perform an adversarial review of the current uncommitted changeset, validating it against project contracts and architectural intent.

中文简介正在准备中。当前显示原文说明。

villetakanen/asdlc-io452026年10月9日 更新

curator

免费

Triage the content corpus against the latest GSC snapshot and produce a prioritized refresh report. Read-only: reports, never edits.

中文简介正在准备中。当前显示原文说明。

villetakanen/asdlc-io452026年10月9日 更新

dev

免费

Implement features, fix bugs, and keep the codebase healthy and maintainable. Works from a defined PBI, issue, or task description.

中文简介正在准备中。当前显示原文说明。

villetakanen/asdlc-io452026年10月9日 更新

geo-audit

免费

GEO+SEO audit of asdlc.io — analyzes the codebase for Generative Engine Optimization across AI citability, technical infrastructure, content quality, schema markup, and knowledge base discoverability. Produces a composite GEO Score (0-100) with prioritized action plan.

中文简介正在准备中。当前显示原文说明。

villetakanen/asdlc-io452026年10月9日 更新

查看 villetakanen 的全部技能

报告此技能的问题