Token导航 LogoToken导航

Agent Skill · 研究检索

feature-planning(功能规划)

feature-planning 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。

feature-planning 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证为 MIT,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 48,806。

总安装 675周安装 29GitHub Stars 175下载 237核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT

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:feature-planning(功能规划)
来源仓库:https://github.com/nicepkg/ai-workflow
仓库路径:skills/feature-planning
安装命令:
npx skills add https://github.com/nicepkg/ai-workflow --skill feature-planning
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。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/nicepkg/ai-workflow --skill feature-planning

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

feature-planning 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。适用于关键词搜索、任务场景匹配或来源线索梳理等研究检索场景。通过 npx skills add 命令从指定 GitHub 仓库安装并使用该技能。

安装前需确认权限范围、维护状态,以及是否会触发联网或文件读写操作。建议结合原始 README 和仓库路径进一步核验具体用法和功能边界。

来源仓库内路径:skills/feature-planning

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/nicepkg/ai-workflow --skill feature-planning;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

feature-planning 怎么安装?

在终端执行 npx skills add https://github.com/nicepkg/ai-workflow --skill feature-planning。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

feature-planning 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

feature-planning 需要什么权限?

权限级别是只读。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。

feature-planning 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

feature-planning 用的人多吗?

公开数据是累计安装 675 次,近一周安装 29 次,下载 237 次,GitHub 175 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

feature-planning 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
feature-planning

功能规划 · 本页

675175只读MIT通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Feature Workflow: Plan Implementation

YOU ARE READING THIS SKILL RIGHT NOW

STOP. Before doing ANYTHING else:

  1. ☐ Create TodoWrite checklist (see below)
  2. ☐ Mark Step 1 as in_progress
  3. ☐ Read CLAUDE.md first (if exists)

This skill is a WRAPPER that loads Z01 context and invokes superpowers:writing-plans

MANDATORY FIRST ACTION: Create TodoWrite

TodoWrite({
  todos: [
    {content: "Step 1: Load project context (CLAUDE.md if exists)", status: "in_progress", activeForm: "Reading CLAUDE.md"},
    {content: "Step 2: Verify Z01 files exist", status: "pending", activeForm: "Checking research"},
    {content: "Step 3: Read ALL Z01 files", status: "pending", activeForm: "Loading context"},
    {content: "Step 4: Invoke superpowers:writing-plans", status: "pending", activeForm: "Creating plan"},
    {content: "Step 5: Verify Z02 outputs", status: "pending", activeForm: "Validating output"}
  ]
})

After each step: Mark completed, move in_progress to next step.

Why Use This Wrapper?

  • Automates Z01 → Z02 file management
  • Loads CLAUDE.md constraints into planning context
  • Enforces feature-workflow naming conventions (Z02_{feature}_plan.md)
  • Integrates with clarification workflow (Z02_CLARIFY)
  • Maintains consistent file structure

Without this wrapper: You'd manually load Z01 files, pass to superpowers:writing-plans, manage Z02 output paths, check for clarifications.

Workflow Steps

Step 1: Load Project Context (MANDATORY FIRST)

Read CLAUDE.md if it exists.

Extract from CLAUDE.md (if exists):

  • Mandatory patterns that MUST be preserved
  • Forbidden approaches to AVOID
  • Project conventions (naming, structure, etc.)
  • Release workflows and constraints

CRITICAL: If CLAUDE.md exists and contains constraints, these MUST be passed to superpowers:writing-plans so the plan preserves project standards.


Step 2: Verify Z01 Files Exist

Scan for existing Z01 files in common locations (docs/ai/ongoing,.ai/ongoing, docs/ongoing).

If Z01 files found:

  • Note the ONGOING_DIR location
  • Extract feature name from filename (e.g., Z01_metrics_research.md → "metrics")
  • Feature name should already be sanitized snake_case from feature-research

If NO Z01 files found:

  • Ask user if they want to run feature-workflow:feature-researching first
  • Or proceed without research context (suboptimal)

Step 3: Read ALL Z01 Files

Read all Z01 files in ONGOING_DIR:

  • Z01_{feature}_research.md (required)
  • Z01_CLARIFY_{feature}_research.md (if exists)

BLOCKING CHECK - If Z01_CLARIFY exists:

  • Read the file
  • Check if "User response:" fields are empty
  • If ANY empty → STOP, report: "Cannot plan with unanswered questions. Please answer all questions in Z01_CLARIFY_{feature}_research.md first."
  • If all answered → proceed

Extract:

  • Technical research and integration points
  • File paths and line ranges
  • Answered clarifications
  • Security and test requirements

Step 4: Invoke Superpowers Planning

CRITICAL: This skill's primary job is to invoke superpowers:writing-plans with Z01 context. If you skip this invocation, the skill provides no value.

Use Skill tool to invoke superpowers:writing-plans

Provide this instruction:

"Create an implementation plan for the {feature} feature based on the research in Z01_{feature}*research.md and clarifications in Z01_CLARIFY*{feature}_research.md.

MANDATORY CONSTRAINTS from CLAUDE.md: [Include any constraints, patterns, or forbidden approaches from CLAUDE.md here if it exists]

CRITICAL: Save the plan to {ONGOING_DIR}/Z02_{feature}_plan.md (use the detected path, NOT hardcoded docs/plans/).

The plan should be a DIRECTIVE document with:

  • Exact file paths from research
  • Complete code examples
  • Verification steps for each task
  • TDD structure (test-fail-implement-pass-commit)
  • Assumes engineer has minimal domain knowledge

If you discover NEW blocking questions during planning (not already in Z01_CLARIFY), create {ONGOING_DIR}/Z02_CLARIFY_{feature}_plan.md. Otherwise, do NOT create a Z02_CLARIFY file.

When incorporating answered questions: Delete fully-answered CLARIFY files or remove incorporated Q&A pairs if only some were answered."


Step 5: Verify Outputs

When superpowers:writing-plans completes:

Check structure:

  • Z02_{feature}_plan.md must exist in ONGOING_DIR (main directive plan)
  • Z02_CLARIFY_{feature}_plan.md only if NEW questions exist

Report to user:

  • "Plan created: Z02_{feature}_plan.md"
  • If clarifications: "Blocking questions in Z02_CLARIFY_{feature}_plan.md"
  • Next step: "Review clarifications, then use feature-workflow:feature-implementing"

Red Flags - You're Failing If:

  • Proceeded with unanswered questions in Z01_CLARIFY (BLOCKING - must stop)
  • Did NOT read CLAUDE.md first (if exists)
  • CLAUDE.md exists but constraints not passed to planning
  • **Did NOT check for Z01* files**
  • Directly invoked superpowers:writing-plans without loading Z01 context
  • Creating plan files with non-standard names (not Z02_{feature}_plan.md)
  • Saving plans to wrong directory
  • Used SlashCommand /superpowers:write-plan (use Skill tool)
  • Did NOT explicitly specify output path in prompt to writing-plans
  • Skipped reading Z01_CLARIFY (if exists)
  • Using hardcoded paths (detect pattern instead)

Common Rationalizations

ExcuseReality
"Skip path detection, I know it's docs/ai/ongoing"NO. Path assumptions break in non-standard repos. Detect ONGOING_DIR.
"No Z01 files, skip check"NO. Research context critical for quality plans. Check first.
"Superpowers will figure out output structure"NO. Generic plans lack our research integration. Provide explicit Z02* instruction.
"Read only Z01_research, skip Z01_CLARIFY"NO. Missing context = incomplete plan. Read ALL Z01* files.
"Create Z02_CLARIFY even if no questions"NO. Empty files clutter directory. Only create if NEW questions.
"Just invoke superpowers:writing-plans directly"NO. This wrapper loads Z01 context. That's its value.
"Wrapper skill, no need to track steps"NO. Wrapper has critical steps (context loading, invocation). Track with TodoWrite.
"TodoWrite adds overhead, skip it"NO. TodoWrite provides user visibility and prevents skipped steps. MANDATORY.

Success Criteria

You followed the workflow if:

  • ✓ Read CLAUDE.md if exists
  • ✓ Passed CLAUDE.md constraints to superpowers:writing-plans
  • ✓ Checked for Z01* files
  • ✓ Read ALL Z01* files if they exist
  • ✓ Invoked superpowers:writing-plans skill (NOT slash command)
  • ✓ Explicitly instructed output path in prompt
  • ✓ Verified Z02_{feature}_plan.md was created
  • ✓ Reported next steps to user

When to Use

Workflow Position: AFTER feature-research (Z01 files), BEFORE feature-implement

Use when:

  • Z01 research files exist
  • Need to create implementation plan
  • Want automated Z01 → Z02 workflow

Don't use when:

  • No Z01 files exist → Use feature-research first
  • Already have complete plan
  • Simple single-step tasks

平台分布

OpenCode

32.18%
按下载量换算76

Cursor

23.13%
按下载量换算55

Claude Code

17.99%
按下载量换算43

github-copilot

11.76%
按下载量换算28

Gemini CLI

7.39%
按下载量换算18

cline

3.9%
按下载量换算9

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。

继续浏览同类 Skills