Token导航 LogoToken导航TokenDH.com
研究检索需要联网github未标认证来源可访问许可证需确认审计通过

slice-the-spec切片规格

Agent Skill

slice-the-spec 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

235

周安装

10

GitHub Stars

6

下载量

82
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:slice-the-spec(切片规格)
来源仓库:https://github.com/kambleakash0/agent-skills
仓库路径:skills/slice-the-spec
安装命令:
npx skills add https://github.com/kambleakash0/agent-skills --skill slice-the-spec
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/kambleakash0/agent-skills --skill slice-the-spec

简介

slice-the-spec 用于查找、检索和筛选相关信息。

  • 适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词或任务场景快速定位候选结果。
  • 通过 npx skills add 命令从指定仓库安装并使用。
  • 安装前需确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。
  • 建议结合原始 README 核验具体用法和功能边界。

SKILL.md

Turn a PRD into Issues

This skill takes a clarified PRD and turns it into a small, sharp backlog of vertically sliced GitHub issues. Each issue should be an independently grabbable “tracer bullet” that cuts through all relevant layers end‑to‑end, flushing out unknown unknowns as early as possible.

When to Use

Use this skill when the user:

  • Has a PRD or similar spec (possibly created via /spec-writer) and now wants concrete issues.
  • Wants to turn “destination” docs into a Kanban board of tasks.
  • Needs to break work down so multiple engineers or agents can work in parallel without stepping on each other.

If there is no PRD yet or the requirements are fuzzy, suggest using /grill-me and /spec-writer first.

Concepts

  • Vertical slice / tracer bullet: A thin, end‑to‑end piece of functionality that goes through all necessary layers (data, domain, API, UI, etc.), not just one layer in isolation.
  • HITL issue: Requires Human‑In‑The‑Loop decisions (design review, stakeholder sign‑off, risky refactor, etc.).
  • AFK issue: “Away‑From‑Keyboard” for the human; safe enough for an autonomous agent to implement and merge without human intervention.

Prefer AFK slices where possible, but mark HITL clearly where human judgment is essential.

Workflow

You may compress or skip steps if the context already provides the answer (e.g., the PRD is already loaded and clearly scoped).

  1. Locate and understand the PRD

- Find the PRD from the conversation or repository (issue, doc, file). - Skim to understand: goals, user stories, functional requirements, and explicit non‑goals. - If multiple PRDs are present, confirm with the user which one to use.

  1. Explore the codebase

- Inspect relevant parts of the repo to understand current architecture, major modules, and likely integration points. - Note any existing patterns you should respect (e.g., existing feature flags, background jobs, notification systems).

  1. Draft vertical slices (tracer bullets)

- Break the PRD into a small set of vertical slices, each of which delivers end‑to‑end value and exercises multiple layers of the system. - Avoid horizontal slices like “set up database tables” or “build all UI components” unless truly necessary; fold those into end‑to‑end slices instead. - For each slice, decide whether it is HITL or AFK, preferring AFK when risk is low.

  1. Define issue structure and dependencies For each slice, define: Identify at least one unblocked issue that can be started immediately.

- Title: Short, descriptive, directly tied to user value. - Type: HITL or AFK. - Description: What this issue will deliver, referencing specific user stories and PRD sections. - Acceptance criteria: Clear, testable criteria including edge cases. - Blocked by: Which other slices must be completed first (if any).

  1. Quiz the user and iterate Present the proposed breakdown as a numbered list of slices with: Ask the user: Refine until the user approves the breakdown.

- Title - Type (HITL/AFK) - Blocked by - User stories covered - Does the granularity feel right (too coarse, too fine)? - Are dependencies correct? - Should any slices be merged or split? - Are the right slices marked as HITL vs AFK?

  1. Generate GitHub‑ready issues

- For each approved slice, generate a GitHub‑ready issue body (Markdown) including: - Context summary - Detailed task description - Acceptance criteria - Links to the PRD and related issues - HITL/AFK flag and any notes for human reviewers - Optionally group them into epics or labels if the repo conventions are clear.

Behavior and Rules

  1. Optimize for few, high‑leverage slices, not dozens of micro‑issues.
  2. Every issue should be implementable by someone who has the PRD and the repo, with minimal additional clarification.
  3. Prefer vertical slices that “light up” a narrow but real path through the system over broad foundational work that shows no user‑visible change.
  4. Always expose and annotate HITL work; do not hide human decisions inside AFK issues.
  5. If the PRD is missing critical details, ask a small number of targeted clarification questions instead of guessing, or suggest returning to /spec-writer.

Example

Input: A PRD describing a new weekly summary email feature for team admins, with detailed user stories and requirements.

You:

  1. Locate the PRD file or issue, skim goals, user stories, and non‑goals.
  2. Explore the repo to find existing notification and email infrastructure.
  3. Propose 3–5 vertical slices such as:

- “Engine for computing weekly admin metrics (AFK)” - “Admin‑configurable summary email template (HITL)” - “Schedule and send weekly summary emails (AFK)” - “Admin UI to preview and enable weekly summaries (HITL)”

  1. Present these with types, dependencies, and mapped user stories; refine based on the user’s feedback.
  2. Emit final GitHub issue bodies for each slice, ready to paste or create via API.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

34.51%
按下载量换算28

Claude

29.9%
按下载量换算25

Cursor

19.74%
按下载量换算16

Gemini CLI

9.58%
按下载量换算8

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills