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

start-feature启动功能

Agent Skill

start-feature 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

264

周安装

11

GitHub Stars

15

下载量

88
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:start-feature(启动功能)
来源仓库:https://github.com/leeovery/claude-technical-workflows
仓库路径:skills/start-feature
安装命令:
npx skills add https://github.com/leeovery/claude-technical-workflows --skill start-feature
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/leeovery/claude-technical-workflows --skill start-feature

简介

start-feature 用于查找、检索和筛选功能启动相关的信息,适合在项目开发初期快速定位资源。

  • 适用于需要根据关键词或任务场景在 Codex、Claude、Cursor、Gemini CLI 中获取候选结果的场景。
  • 通过 npx skills add 命令从 GitHub 仓库安装,需确认权限范围与是否触发联网操作。
  • 建议结合原始 README 核验具体用法,并注意维护状态与潜在的文件读写行为。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

Start a new feature and route it through the pipeline: Discussion → Specification → Planning → Implementation.

⚠️ ZERO OUTPUT RULE: Do not narrate your processing. Produce no output until a step or reference file explicitly specifies display content. No "proceeding with...", no discovery summaries, no routing decisions, no transition text. Your first output must be content explicitly called for by the instructions.

Instructions

Follow these steps EXACTLY as written. Do not skip steps or combine them.

CRITICAL: This guidance is mandatory.

  • After each user interaction, STOP and wait for their response before proceeding
  • Never assume or anticipate user choices
  • Even if the user's initial prompt seems to answer a question, still confirm with them at the appropriate step
  • Complete each step fully before moving to the next

Step 0: Run Migrations

This step is mandatory. You must complete it before proceeding.

Invoke the /migrate skill and assess its output.

If files were updated: STOP and wait for the user to review the changes (e.g., via git diff) and confirm before proceeding to Step 1. Do not continue automatically.

If no updates needed: Proceed to Step 1.


Resuming After Context Refresh

Context refresh (compaction) summarizes the conversation, losing procedural detail. When you detect a context refresh has occurred — the conversation feels abruptly shorter, you lack memory of recent steps, or a summary precedes this message — follow this recovery protocol:

  1. Re-read this skill file completely. Do not rely on your summary of it. The full process, steps, and rules must be reloaded.
  2. Identify the topic. Check conversation history for the topic name. If unknown, check .workflows/discussion/ for recently modified files via git log --oneline -5.
  3. Determine current step from artifacts:

- No discussion file exists → resume at Step 1 - Discussion exists with status: in-progress → resume at Step 3 (re-invoke technical-discussion) - Discussion exists with status: concluded → resume at Step 4 (phase bridge)

  1. Announce your position to the user before continuing: what step you believe you're at, what's been completed, and what comes next. Wait for confirmation.

Do not guess at progress or continue from memory. The files on disk and git history are authoritative — your recollection is not.


Step 1: Gather Feature Context

Load gather-feature-context.md and follow its instructions.

→ Proceed to Step 2.


Step 2: Topic Name and Conflict Check

Based on the feature description, suggest a topic name:

*Output the next fenced block as a code block:*
Suggested topic name: {suggested-topic:(kebabcase)}

This will create: .workflows/discussion/{suggested-topic}.md
*Output the next fenced block as markdown (not a code block):*
· · · · · · · · · · · ·
Is this name okay?

- **`y`/`yes`** — Use this name
- **`s`/`something else`** — Suggest a different name
· · · · · · · · · · · ·

STOP. Wait for user response.

Once the topic name is confirmed, check for naming conflicts:

ls .workflows/discussion/

If a discussion with the same name exists, inform the user:

*Output the next fenced block as markdown (not a code block):*
· · · · · · · · · · · ·
A discussion named "{topic}" already exists.

- **`r`/`resume`** — Resume the existing discussion
- **`n`/`new`** — Choose a different name
· · · · · · · · · · · ·

STOP. Wait for user response.

If resuming, check the discussion status. If concluded → skip to Step 4. If in-progress → proceed to Step 3.

→ Proceed to Step 3.


Step 3: Invoke Discussion

Before invoking the processing skill, save a session bookmark.

*Output the next fenced block as a code block:*
Saving session state so Claude can pick up where it left off and continue the feature pipeline if the conversation is compacted.
.claude/hooks/workflows/write-session-state.sh \
  "{topic}" \
  "skills/technical-discussion/SKILL.md" \
  ".workflows/discussion/{topic}.md" \
  --pipeline "This session is part of the feature pipeline. After the discussion concludes, load and follow the phase bridge at skills/start-feature/references/phase-bridge.md for topic '{topic}'."

Load invoke-discussion.md and follow its instructions.

CRITICAL: When the discussion concludes (status becomes "concluded"), you MUST proceed to Step 4 below. Do not end the session — the feature pipeline continues to specification via the phase bridge.


Step 4: Phase Bridge

Load phase-bridge.md and follow its instructions.

The bridge will enter plan mode with instructions to invoke continue-feature for the topic in the next session.

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

37.65%
按下载量换算33

Claude

28.5%
按下载量换算25

Cursor

19.14%
按下载量换算17

Gemini CLI

8.5%
按下载量换算7

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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