Token导航 LogoToken导航

Agent Skill · 研究检索

specification-executor(规范执行者)

specification-executor 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。

specification-executor 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,权限为需要联网;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 38,175。

总安装 1,599周安装 68GitHub Stars 5下载 560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:specification-executor(规范执行者)
来源仓库:https://github.com/qodex-ai/ai-agent-skills
仓库路径:skills/specification-executor
安装命令:
npx skills add https://github.com/qodex-ai/ai-agent-skills --skill specification-executor
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/qodex-ai/ai-agent-skills --skill specification-executor

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。

specification-executor 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。它可辅助 Agent 从文档、代码库或知识库中提取匹配内容,并按相关性排序返回。

通过 npx skills add 命令从指定仓库安装,具体用法需结合原始 README 进一步确认。安装前建议核实权限范围、维护状态,以及是否会触发联网、命令执行或文件读写操作。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。

来源仓库内路径:skills/specification-executor

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/qodex-ai/ai-agent-skills --skill specification…;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

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

specification-executor 怎么安装?

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

specification-executor 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。

specification-executor 需要什么权限?

权限级别是需要联网。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。

specification-executor 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。

specification-executor 用的人多吗?

公开数据是累计安装 1,599 次,近一周安装 68 次,下载 560 次,GitHub 5 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。

specification-executor 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
specification-executor

规范执行者 · 本页

1,5995需要联网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

Spec to Implementation

Transforms specifications into actionable implementation plans with progress tracking. Fetches spec documents, extracts requirements, breaks down into tasks, and manages implementation workflow.

Quick Start

When asked to implement a specification:

  1. Find spec: Use Notion:notion-search to locate specification page
  2. Fetch spec: Use Notion:notion-fetch to read specification content
  3. Extract requirements: Parse and structure requirements from spec
  4. Create plan: Use Notion:notion-create-pages for implementation plan
  5. Find task database: Use Notion:notion-search to locate tasks database
  6. Create tasks: Use Notion:notion-create-pages for individual tasks in task database
  7. Track progress: Use Notion:notion-update-page to log progress and update status

Implementation Workflow

Step 1: Find the specification

1. Search for spec:
   - Use Notion:notion-search with spec name or topic
   - Apply filters if needed (e.g., created_date_range, teamspace_id)
   - Look for spec title or keyword matches
   - If not found or ambiguous, ask user for spec URL/ID

Example searches:
- "User Authentication spec"
- "Payment Integration specification"
- "Mobile App Redesign PRD"

Step 2: Fetch and analyze specification

1. Fetch spec page:
   - Use Notion:notion-fetch with spec URL/ID from search results
   - Read full content including requirements, design, constraints

2. Parse specification:
   - Identify functional requirements
   - Note non-functional requirements (performance, security, etc.)
   - Extract acceptance criteria
   - Identify dependencies and blockers

See reference/spec-parsing.md for parsing patterns.

Step 3: Create implementation plan

1. Break down into phases/milestones
2. Identify technical approach
3. List required tasks
4. Estimate effort
5. Identify risks

Use implementation plan template (see [reference/standard-implementation-plan.md](reference/standard-implementation-plan.md) or [reference/quick-implementation-plan.md](reference/quick-implementation-plan.md))

Step 4: Create implementation plan page

Use Notion:notion-create-pages:
- Title: "Implementation Plan: [Feature Name]"
- Content: Structured plan with phases, tasks, timeline
- Link back to original spec
- Add to appropriate location (project page, database)

Step 5: Find task database

1. Search for task database:
   - Use Notion:notion-search to find "Tasks" or "Task Management" database
   - Look for engineering/project task tracking system
   - If not found or ambiguous, ask user for database location

2. Fetch database schema:
   - Use Notion:notion-fetch with database URL/ID
   - Get property names, types, and options
   - Identify correct data source from <data-source> tags
   - Note required properties for new tasks

Step 6: Create implementation tasks

For each task in plan:
1. Create task in task database using Notion:notion-create-pages
2. Use parent: { data_source_id: 'collection://...' }
3. Set properties from schema:
   - Name/Title: Task description
   - Status: To Do
   - Priority: Based on criticality
   - Related Tasks: Link to spec and plan
4. Add implementation details in content

See reference/task-creation.md for task patterns.

Step 7: Begin implementation

1. Update task status to "In Progress"
2. Add initial progress note
3. Document approach and decisions
4. Link relevant resources

Step 8: Track progress

Regular updates:
1. Update task properties (status, progress)
2. Add progress notes with:
   - What's completed
   - Current focus
   - Blockers/issues
3. Update implementation plan with milestone completion
4. Link to related work (PRs, designs, etc.)

See reference/progress-tracking.md for tracking patterns.

Spec Analysis Patterns

Functional Requirements: User stories, feature descriptions, workflows, data requirements, integration points

Non-Functional Requirements: Performance targets, security requirements, scalability needs, availability, compliance

Acceptance Criteria: Testable conditions, user validation points, performance benchmarks, completion definitions

See reference/spec-parsing.md for detailed parsing techniques.

Implementation Plan Structure

Plan includes: Overview → Linked Spec → Requirements Summary → Technical Approach → Implementation Phases (Goal, Tasks checklist, Estimated effort) → Dependencies → Risks & Mitigation → Timeline → Success Criteria

See reference/standard-implementation-plan.md for full plan template.

Task Breakdown Patterns

By Component: Database, API endpoints, frontend components, integration, testing By Feature Slice: Vertical slices (auth flow, data entry, report generation) By Priority: P0 (must have), P1 (important), P2 (nice to have)

Progress Logging

Daily Updates (active work): Add progress note with completed items, current focus, blockers Milestone Updates (major progress): Update plan checkboxes, add milestone summary, adjust timeline Status Changes (task transitions): Update properties (In Progress → In Review → Done), add completion notes, link deliverables

Progress Format: Date heading → Completed → In Progress → Next Steps → Blockers → Notes

See reference/progress-tracking.md for detailed patterns.

Linking Spec to Implementation

Forward Links: Update spec page with "Implementation" section linking to plan and tasks Backward Links: Reference spec in plan and tasks with "Specification" section Bidirectional Traceability: Maintain both directions for easy tracking

Implementation Status Tracking

Plan Status: Update with phase completion (✅ Complete, 🔄 In Progress %, ⏳ Not Started) and overall percentage Task Aggregation: Query task database by plan ID to generate summary (complete, in progress, blocked, not started)

Handling Spec Changes

Detection: Fetch updated spec → compare with plan → identify new requirements → assess impact Propagation: Update plan → create new tasks → update affected tasks → add change note → notify via comments Change Log: Track spec evolution with date, what changed, and impact

Common Patterns

Feature Flag: Backend (behind flag) → Testing → Frontend (flagged) → Internal rollout → External rollout Database Migration: Schema design → Migration script → Staging test → Production migration → Validation API Development: API design → Backend implementation → Testing & docs → Client integration → Deployment

Best Practices

  1. Always link spec and implementation: Maintain bidirectional references
  2. Break down into small tasks: Each task should be completable in 1-2 days
  3. Extract clear acceptance criteria: Know when "done" is done
  4. Identify dependencies early: Note blockers in plan
  5. Update progress regularly: Daily notes for active work
  6. Track changes: Document spec updates and their impact
  7. Use checklists: Visual progress indicators help everyone
  8. Link deliverables: PRs, designs, docs should link back to tasks

Advanced Features

For additional implementation patterns and techniques, see the reference files in reference/.

Common Issues

"Can't find spec": Use Notion:notion-search with spec name/topic, try broader terms, or ask user for URL "Multiple specs found": Ask user which spec to implement or show options "Can't find task database": Search for "Tasks" or "Task Management", or ask user for database location "Spec unclear": Note ambiguities in plan, create clarification tasks "Requirements conflicting": Document conflicts, create decision task "Scope too large": Break into smaller specs/phases

Examples

See examples/ for complete workflows:

平台分布

Claude Code

27.18%
按下载量换算152

trae

23.13%
按下载量换算130

Codex

17.88%
按下载量换算100

Antigravity

13.7%
按下载量换算77

windsurf

8.04%
按下载量换算45

github-copilot

3.24%
按下载量换算18

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。

继续浏览同类 Skills