implement-and-verify

SKILL开发
开发 未标注权限 许可证不明确

Implement tasks from plans with test-first approach, user-story-centric execution, and AC verification. Use proactively when executing implementation plans. Enforces quality gates, MVP-first delivery, and Article VII story-by-story implementation.

一句话选型结论

按资料字段整理

implement-and-verify是开发类的 Agent Skill,安装方式:GitHub 仓库,权限级别未标注,许可证不明确,没有现成安装命令,需按说明手动放置 SKILL.md。技能本质是给模型读的说明书,效果取决于模型与客户端;装完先用一个小任务验证,再放进正式流程。

分类开发 安装方式GitHub 仓库 权限级别未标注权限 许可证许可证不明确
累计安装 未标注 本周 未标注
GitHub 星标 0 仓库 nextjs-intelligence-toolkit
下载量 未标注 技能市场下载数
权限级别 未标注权限 安装前请确认风险范围
许可证 许可证不明确 未说明

安装

GitHub 仓库
在支持 Skills 的客户端里执行,装完问一句「你有哪些技能」验证
  1. 1
    确认客户端支持

    确认你的客户端支持 Skills(Claude、Codex、Cursor 等),并升级到较新的版本。

  2. 2
    拿到技能文件

    按安装说明或仓库 README,把 SKILL.md 放到客户端的 skills 目录(一般一个技能一个文件夹)。

  3. 3
    刷新技能列表

    重新打开客户端,或刷新技能列表,让新放进来的技能被加载。

  4. 4
    验证是否生效

    问一句「你有哪些技能」,确认列表里出现它,再拿一个小任务试跑。

技能档案

开发
字段来自技能仓库与公开索引,中文说明由本站标注
作者 / 维护方yangsi7仓库 nextjs-intelligence-toolkit · 版本 未标注
宿主客户端未标注技能可被这些客户端加载
安装方式GitHub 仓库安装包 yangsi7/nextjs-intelligence-toolkit
权限级别未标注权限安装前请确认风险范围
许可证未说明许可证不明确,商用前请自行确认条款
仓库可用性available技能仓库当前是否可访问
最近核验未标注上游最后核验时间 · 数据更新 未标注
正文体量11.2 KBSKILL.md 原文大小,越大说明说明书写得越细

典型使用场景

3 类
按分类整理的常见用法,具体以 SKILL.md 为准
写代码与改 bug

按需求补代码、定位并修掉报错。

读仓库与生成改动

让模型读懂项目结构,再给出可落地的改动。

跑测试与排查故障

按现象排查问题,补测试用例并复跑。

选择建议

装之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 基础信息齐全,可以先按说明装一个试试。

先想清楚的地方

  • 没有标注权限级别,实际能做什么要装好后确认。
  • 许可证不明确,商用或二次分发前先到仓库确认条款。
  • 没有现成安装命令,要按安装说明或仓库 README 手动放置。
  • 没有做站内核验,内容以作者仓库为准。
  • 技能只是说明书,实际效果取决于模型与客户端,装完先用小任务试一遍。

更适合

  • 需要在开发场景里给模型补一套做法的人。
  • 愿意先读一遍 SKILL.md、确认它会让模型做什么的人。

不太适合

  • 对许可证要求很严、必须明确可商用的人。
  • 只想装完就自动变强、不打算看说明书的人。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
技能权限级别安装方式累计安装宿主客户端安装命令
implement-and-verify当前 未标注权限 GitHub 仓库 未标注 未标注 无
技能审查员 浏览器控制 ClawHub 市场 877.9 万 OpenClaw 有
Vercel React 最佳实践 浏览器控制 GitHub 仓库 849.1 万 Codex、Claude、Cursor 有
GitHub 代码协作 联网访问 ClawHub 市场 763.3 万 OpenClaw 有
网页设计指南 联网访问 GitHub 仓库 668.6 万 Codex、Claude、Cursor 有
本体论 只读 ClawHub 市场 663.7 万 OpenClaw 有

SKILL.md 全文

11.2 KB
模型实际读到的说明书原文,来自技能仓库

@.claude/shared-imports/constitution.md
@.claude/templates/verification-report.md
@.claude/templates/quality-checklist.md

Implementation & Verification Skill

Overview

This skill executes implementation plans following Specification-Driven Development (SDD) principles: quality gates, test-driven development (TDD), user-story-centric execution, and progressive delivery.

Constitutional Authority: Article III (Test-First), Article V (Template-Driven Quality), Article VII (User-Story-Centric Organization)

Core Principles:
1. Quality Gates First: Validate readiness before implementation (Article V)
2. Story-by-Story: Implement user stories in priority order (Article VII)
3. Test-First: Tests BEFORE implementation, ALL ACs verified (Article III)
4. Progressive Delivery: Each story is shippable when complete (Article VII)

Announce at start: "I'm using the implement-and-verify skill to execute this plan with SDD quality gates."

Quick Reference

Phase Key Activities Output Article
0. Quality Gates Validate spec readiness, check constitution Gate pass/fail Article V
1. Story Selection Load tasks by story (P1, P2, P3) Story tasks Article VII
2. Progressive Delivery Define MVP, plan incremental shipping Delivery plan Article VII
3. Load Tasks Read plan, verify dependencies per story Task selected Article IV
4. Write Tests Create tests from ACs (should FAIL) Test files Article III
5. Implement Write code to make tests pass Implementation Article III
6. Verify Run all tests, lint, build verification-report.md Article V
7. Update Mark complete, handover if needed Updated plan Article V

Templates You Will Use

  • @.claude/shared-imports/constitution.md - Architectural principles (all phases)
  • @.claude/templates/quality-checklist.md - Pre-implementation gates (Phase 0)
  • @.claude/templates/plan.md - Input plan with tasks and ACs (Phase 3)
  • @.claude/templates/verification-report.md - Verification results (Phase 6)
  • @.claude/templates/handover.md - For blocked tasks or agent transitions (Phase 7)

The Process

Copy this checklist to track progress:

SDD Implementation Progress:
- [ ] Phase 0: Quality Gates Validated (constitution check + audit PASS)
- [ ] Phase 1: Story Tasks Loaded (by priority)
- [ ] Phase 2: Progressive Delivery Planned (MVP defined)
- [ ] Phase 3: Tasks Loaded (dependencies verified)
- [ ] Phase 4: Tests Written (from ACs, should FAIL)
- [ ] Phase 5: Implementation Complete
- [ ] Phase 6: Verification Complete (ALL ACs pass)
- [ ] Phase 7: Plan Updated (story marked complete)

Detailed Workflows

Phase 0: Quality Gate Validation

See: @.claude/skills/implement-and-verify/workflows/quality-gates.md

Summary:
- Validate quality checklist (quality-checklist.md)
- MANDATORY: Verify /audit has passed (Article V)
- Audit report must exist
- Status must be PASS or PASS WITH WARNINGS
- Critical Issues must = 0
- Block implementation if gates fail (audit blocking is non-overridable)

Phases 1-2: Story-by-Story Execution & Progressive Delivery

See: @.claude/skills/implement-and-verify/workflows/story-by-story-execution.md

Summary:
- Load tasks by story (P1, P2, P3)
- Implement each story completely
- Auto-invoke /verify --story P# after each story
- Only proceed to next story after current story verification passes
- Each story is independently shippable (MVP = P1 complete)

Phases 3-7: TDD Implementation Workflow

See: @.claude/skills/implement-and-verify/workflows/tdd-implementation.md

Summary:
- Phase 3: Load tasks, verify dependencies, extract ACs
- Phase 4: Write tests FIRST (must FAIL initially)
- Phase 5: Implement minimal code to pass tests
- Phase 6: Verify all ACs (100% coverage required)
- Phase 7: Update plan, generate verification report, create handover if needed


Examples & Patterns

See: @.claude/skills/implement-and-verify/examples/implementation-examples.md

Five concrete examples:
1. Successful implementation (test-first → implement → verify)
2. Failing AC → debug → fix
3. Rollback on breaking change
4. Story-level verification (P1 independent test)
5. Progressive delivery workflow (P1 → P2 → P3)

Key Patterns:
- Test-First Always: Write Test → FAIL → Implement → PASS
- Debug on Failure: AC Fails → Debug → Fix → Re-verify
- Progressive Delivery: P1 Complete → Verify → Ship or Continue


Enforcement & Failure Modes

See: @.claude/skills/implement-and-verify/references/enforcement-rules.md

Three Critical Rules:
1. No Completion Without Passing ACs - Status must be "blocked" if any AC fails
2. Test-First Mandatory - Tests written before implementation (must FAIL initially)
3. 100% AC Coverage - Every AC must have passing test

Common Pitfalls: Implementing before tests, skipping lint/build, marking complete with failures

11 Failure Modes with Solutions: Quality gates skipped, test-first violated, coverage incomplete, false positive tests, story verification skipped, dependency violations, over-engineering, etc.


Agent Integration & Related Workflows

See: @.claude/skills/implement-and-verify/references/integration.md

Executor Agent Execution:
- Triggered by: User runs /implement plan.md
- Agent: executor-implement-verify
- Receives: plan.md, tasks.md, spec.md, constitution
- Returns: Implemented code, verification reports per story, handovers if blocked

Supporting Agents:
- Code Analyzer: For understanding existing code before modification
- Debugger: For test failures (via debug-issues skill)

Handover Protocols:
- To Planner: If requirements unclear
- To Orchestrator: If blocked by external dependency

Verification Workflow:

implement-and-verify skill (completes story P1)
    ↓ auto-invokes
/verify plan.md --story P1 (SlashCommand tool)
    ↓ produces
verification-P1.md (PASS/FAIL report)

Prerequisites

Before using this skill:
- ✅ tasks.md exists (Article IV: tasks before implementation)
- ✅ plan.md exists with ≥2 ACs per user story
- ✅ spec.md exists with user stories and priorities
- ✅ All [NEEDS CLARIFICATION] markers resolved (or override approved)
- ✅ Audit has passed (or CRITICAL issues resolved) - MANDATORY
- ⚠️ Optional: quality-checklist.md validated (Article V quality gate)
- ⚠️ Optional: Test framework set up (for TDD)

Dependencies

Depends On:
- specify-feature skill - Provides spec.md with user stories
- create-implementation-plan skill - Provides plan.md with ACs and tech stack
- generate-tasks skill - MUST run before this skill (Article IV)
- /audit command - Should have passed before implementation starts

Integrates With:
- debug-issues skill - Use when tests fail or ACs don't pass
- analyze-code skill - Use when understanding existing code before modifying
- /verify command - Automatically invoked after each story completes

Tool Dependencies:
- Read, Write, Edit tools (code implementation)
- Bash tool (running tests, builds, linters)
- Grep, Glob tools (finding files and code patterns)

Next Steps

After implementation completes, automatic workflow progression per story:

Automatic Chain (per User Story):

implement-and-verify (implements story P1)
    ↓ (auto-invokes /verify)
/verify plan.md --story P1 (validates P1 independently)
    ↓ (if PASS)
Ready for P2 OR ship MVP
    ↓ (if user continues)
implement-and-verify (implements story P2)
    ↓ (auto-invokes /verify)
/verify plan.md --story P2 (validates P2 independently)
    ↓ (if PASS)
Ready for P3 OR ship enhancement
    ↓ (continues for all stories)

User Action Required:
- After P1 verification passes: Decision to ship MVP or continue to P2
- After any story passes: Can ship incrementally (Article VII progressive delivery)
- If verification fails: Debug with debug-issues skill, fix, re-verify

Outputs Created (per story):
- YYYYMMDD-HHMM-verification-P#.md - Story verification report
- YYYYMMDD-HHMM-handover-*.md - If blocked or transitioning agents
- Updated tasks.md with completed tasks marked
- Test files (created before implementation per Article III)

Commands:
- /verify plan.md --story P# - Automatically invoked after each story
- /bug - If tests fail and debugging needed
- /analyze - If existing code analysis needed

Related Skills & Commands

Direct Integration:
- specify-feature skill - Provides spec.md with user stories (workflow start)
- create-implementation-plan skill - Provides plan.md with ACs (workflow predecessor)
- generate-tasks skill - Provides tasks.md with task breakdown (required predecessor)
- debug-issues skill - Use when tests fail or blockers occur
- analyze-code skill - Use when existing code needs understanding
- /implement command - User-facing command that invokes this skill
- /verify command - Automatically invoked after each story (per P1, P2, P3)

Workflow Context:
- Position: Phase 4 of SDD workflow (final execution phase)
- Triggers: User runs /implement plan.md after audit passes
- Output: Implemented code + verification reports per story

Quality Gates:
- Pre-Implementation: quality-checklist.md validation (Article V)
- Per-Story: /verify --story P# automatic validation (Article VII)
- Test-First: Tests written before implementation (Article III)
- 100% AC Coverage: Every AC must have passing test

Progressive Delivery Pattern (Article VII):

P1 implemented → /verify --story P1 → PASS → Ship MVP or Continue
P2 implemented → /verify --story P2 → PASS → Ship Enhancement or Continue
P3 implemented → /verify --story P3 → PASS → Ship Complete Feature

Each story is independently shippable, enabling faster value delivery.

Success Metrics

Verification Quality:
- 100% AC coverage required
- All ACs must pass
- No task complete without verification

Implementation Quality:
- Tests written first
- Minimal implementation (YAGNI)
- Lint and build pass

When to Use This Skill

Use implement-and-verify when:
- User has a plan ready to execute
- User wants to implement tasks with TDD
- User needs AC verification
- User says "implement the plan"

Don't use when:
- No plan exists yet (use create-plan skill)
- User just wants to analyze code (use analyze-code skill)
- User wants to debug (use debugging skill)

Version

Version: 1.2.0
Last Updated: 2025-10-23
Owner: Claude Code Intelligence Toolkit

Change Log:
- v1.2.0 (2025-10-23): Refactored to progressive disclosure pattern (<500 lines)
- v1.1.0 (2025-10-23): Added Phase 0 Step 0.3 - Mandatory audit validation enforcement
- v1.0.0 (2025-10-22): Initial version with cross-skill references

常见问题

5 问
答案由本站依据条目字段整理
implement-and-verify怎么安装?

没有现成安装命令:按安装说明或仓库 README,把 SKILL.md 放进客户端的 skills 目录(一般一个技能一个文件夹)。

implement-and-verify支持哪些客户端?

资料没有标注宿主客户端,但只要客户端支持 Skills(Claude、Codex、Cursor 等),一般都能加载。

implement-and-verify权限高吗,安全吗?

权限级别为未标注权限。安装前先看它会读取或写入哪些内容。

implement-and-verify收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于技能本身和所用的模型或客户端,正式使用前按作者说明确认。

implement-and-verify用什么许可证?

许可证标注为 未说明(许可证不明确)。商用或二次分发前请到仓库确认条款原文。

热门专题

按场景挑技能
全部专题 →

技能内容以作者仓库为准;分类、权限级别与许可证状态的中文说明为中文整理,最近核验 未标注。