quality-gates
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseQuality Gates
质量门禁
This skill teaches agents how to assess task complexity, enforce quality gates, and prevent wasted work on incomplete or poorly-defined tasks.
Key Principle: Stop and clarify before proceeding with incomplete information. Better to ask questions than to waste cycles on the wrong solution.
该技能教导Agent如何评估任务复杂度、执行质量门禁检查，以及避免在不完整或定义模糊的任务上浪费工作精力。
核心原则： 在信息不完整时，先暂停并澄清需求。提出问题远比在错误的解决方案上浪费时间更有价值。
Overview
概述
Auto-Activate Triggers
自动触发条件
- Receiving a new task assignment
- Starting a complex feature implementation
- Before allocating work in Squad mode
- When requirements seem unclear or incomplete
- After 3 failed attempts at the same task
- When blocked by dependencies
- 收到新的任务分配
- 启动复杂功能的开发
- 在Squad模式下分配工作前
- 需求看起来不明确或不完整时
- 同一任务尝试3次失败后
- 被依赖项阻塞时
Manual Activation
手动触发方式
- User asks for complexity assessment
- Planning a multi-step project
- Before committing to a timeline
- 用户要求进行复杂度评估
- 规划多步骤项目时
- 承诺交付时间前
Core Concepts
核心概念
Complexity Scoring (1-5 Scale)
复杂度评分（1-5级）
| Level | Files | Lines | Time | Characteristics |
|---|---|---|---|---|
| 1 - Trivial | 1 | < 50 | < 30 min | No deps, no unknowns |
| 2 - Simple | 1-3 | 50-200 | 30 min - 2 hr | 0-1 deps, minimal unknowns |
| 3 - Moderate | 3-10 | 200-500 | 2-8 hr | 2-3 deps, some unknowns |
| 4 - Complex | 10-25 | 500-1500 | 8-24 hr | 4-6 deps, significant unknowns |
| 5 - Very Complex | 25+ | 1500+ | 24+ hr | 7+ deps, many unknowns |
Load: for detailed examples and assessment formulas.
Read("${CLAUDE_SKILL_DIR}/references/complexity-scoring.md")| 等级 | 文件数 | 代码行数 | 耗时 | 特征 |
|---|---|---|---|---|
| 1 - 极简易 | 1 | < 50 | < 30分钟 | 无依赖项，无未知因素 |
| 2 - 简单 | 1-3 | 50-200 | 30分钟 - 2小时 | 0-1个依赖项，极少未知因素 |
| 3 - 中等 | 3-10 | 200-500 | 2-8小时 | 2-3个依赖项，存在部分未知因素 |
| 4 - 复杂 | 10-25 | 500-1500 | 8-24小时 | 4-6个依赖项，存在大量未知因素 |
| 5 - 极复杂 | 25+ | 1500+ | 24+小时 | 7+个依赖项，存在诸多未知因素 |
如需详细示例和评估公式，请加载：
Read("${CLAUDE_SKILL_DIR}/references/complexity-scoring.md")Blocking Thresholds
阻塞阈值
| Condition | Threshold | Action |
|---|---|---|
| YAGNI Gate | Justified ratio > 2.0 | BLOCK with simpler alternatives |
| YAGNI Warning | Justified ratio 1.5-2.0 | WARN with simpler alternatives |
| Critical Questions | > 3 unanswered | BLOCK |
| Missing Dependencies | Any blocking | BLOCK |
| Failed Attempts | >= 3 | BLOCK & ESCALATE |
| Evidence Failure | 2 fix attempts | BLOCK |
| Complexity Overflow | Level 4-5 no plan | BLOCK |
WARNING Conditions (proceed with caution):
- Level 3 complexity
- 1-2 unanswered questions
- 1-2 failed attempts
Load: for escalation protocols and decision logic.
Read("${CLAUDE_SKILL_DIR}/references/blocking-thresholds.md")| 条件 | 阈值 | 操作 |
|---|---|---|
| YAGNI门禁 | 合理复杂度比值 > 2.0 | 阻塞并提供更简单的替代方案 |
| YAGNI警告 | 合理复杂度比值 1.5-2.0 | 警告并提供更简单的替代方案 |
| 关键未解决问题 | > 3个 | 阻塞 |
| 缺失依赖项 | 任何阻塞性依赖 | 阻塞 |
| 失败尝试次数 | >= 3 | 阻塞并升级 |
| 验证失败 | 2次修复尝试失败 | 阻塞 |
| 复杂度溢出 | 4-5级任务无规划 | 阻塞 |
警告条件（需谨慎执行）：
- 3级复杂度
- 1-2个未解决问题
- 1-2次失败尝试
如需升级流程和决策逻辑，请加载：
Read("${CLAUDE_SKILL_DIR}/references/blocking-thresholds.md")References
参考资源
Load on demand with :
Read("${CLAUDE_SKILL_DIR}/references/<file>")| File | Content |
|---|---|
| Detailed Level 1-5 characteristics, quick assessment formula, checklist |
| BLOCKING vs WARNING conditions, escalation protocol, gate decision logic, attempt tracking |
| Pre-task gate validation, stuck detection, complexity breakdown (Level 4-5), requirements completeness |
| Gate validation process templates, context system integration, common pitfalls |
| LLM-as-judge patterns, quality aspects, fail-open/closed strategies, graceful degradation, triple-consumer artifacts |
可通过按需加载：
Read("${CLAUDE_SKILL_DIR}/references/<file>")| 文件 | 内容 |
|---|---|
| 1-5级复杂度的详细特征、快速评估公式、检查清单 |
| 阻塞与警告条件、升级流程、门禁决策逻辑、尝试次数跟踪 |
| 任务前门禁验证、困境检测、4-5级复杂度分解、需求完整性检查 |
| 门禁验证流程模板、上下文系统集成、常见陷阱 |
| LLM-as-judge模式、质量评估维度、开/关失败策略、优雅降级、三方消费者工件 |
Quick Reference
快速参考
Gate Decision Flow
门禁决策流程
0. YAGNI check (runs FIRST — before any implementation planning)
→ Read project tier from scope-appropriate-architecture
→ Calculate justified_complexity = planned_LOC / tier_appropriate_LOC
→ If ratio > 2.0: BLOCK (must simplify)
→ If ratio 1.5-2.0: WARN (present simpler alternative)
→ Security patterns exempt from YAGNI gate
1. Assess complexity (1-5)
2. Count critical questions unanswered
3. Check dependencies blocked
4. Check attempt count
if (yagni_ratio > 2.0) -> BLOCK with simpler alternatives
else if (questions > 3 || deps blocked || attempts >= 3) -> BLOCK
else if (complexity >= 4 && no plan) -> BLOCK
else if (yagni_ratio > 1.5 || complexity == 3 || questions 1-2) -> WARNING
else -> PASS0. YAGNI检查（优先执行 — 在任何开发规划前）
→ 从scope-appropriate-architecture读取项目层级
→ 计算合理复杂度 = 计划代码行数 / 层级适配代码行数
→ 若比值 > 2.0：阻塞（必须简化）
→ 若比值 1.5-2.0：警告（提供更简单的替代方案）
→ 安全模式不受YAGNI门禁限制
1. 评估复杂度（1-5级）
2. 统计未解决的关键问题数量
3. 检查依赖项是否阻塞
4. 检查尝试次数
if (yagni_ratio > 2.0) -> 阻塞并提供更简单替代方案
else if (questions > 3 || deps blocked || attempts >= 3) -> 阻塞
else if (complexity >= 4 && no plan) -> 阻塞
else if (yagni_ratio > 1.5 || complexity == 3 || questions 1-2) -> 警告
else -> 通过Gate Check Template
门禁检查模板
markdown
undefinedmarkdown
undefinedQuality Gate: [Task Name]
质量门禁：[任务名称]
Complexity: Level [1-5]
Unanswered Critical Questions: [Count]
Blocked Dependencies: [List or None]
Failed Attempts: [Count]
Status: PASS / WARNING / BLOCKED
Can Proceed: Yes / No
undefined复杂度： [1-5]级
未解决关键问题： [数量]
阻塞依赖项： [列表或无]
失败尝试次数： [数量]
状态： 通过 / 警告 / 阻塞
是否可执行： 是 / 否
undefinedEscalation Template
升级模板
markdown
undefinedmarkdown
undefinedEscalation: Task Blocked
升级：任务阻塞
Task: [Description]
Block Type: [Critical Questions / Dependencies / Stuck / Evidence]
Attempts: [Count]
任务： [描述]
阻塞类型： [关键问题 / 依赖项 / 困境 / 验证失败]
尝试次数： [数量]
What Was Tried
已尝试方案
- [Approach 1] - Failed: [Reason]
- [Approach 2] - Failed: [Reason]
- [方案1] - 失败原因：[说明]
- [方案2] - 失败原因：[说明]
Need Guidance On
需要指导的内容
- [Specific question]
Recommendation: [Suggested action]
---- [具体问题]
建议： [建议操作]
---Integration with Context System
与上下文系统集成
javascript
// Add gate check to context
context.quality_gates = context.quality_gates || [];
context.quality_gates.push({
task_id: taskId,
timestamp: new Date().toISOString(),
complexity_score: 3,
gate_status: 'pass', // pass, warning, blocked
critical_questions_count: 1,
unanswered_questions: 1,
dependencies_blocked: 0,
attempt_count: 0,
can_proceed: true
});javascript
// 将门禁检查结果添加到上下文
context.quality_gates = context.quality_gates || [];
context.quality_gates.push({
task_id: taskId,
timestamp: new Date().toISOString(),
complexity_score: 3,
gate_status: 'pass', // pass, warning, blocked
critical_questions_count: 1,
unanswered_questions: 1,
dependencies_blocked: 0,
attempt_count: 0,
can_proceed: true
});Integration with Evidence System
与验证系统集成
javascript
// Before marking task complete
const evidence = context.quality_evidence;
const hasPassingEvidence = (
evidence?.tests?.exit_code === 0 ||
evidence?.build?.exit_code === 0
);
if (!hasPassingEvidence) {
return { gate_status: 'blocked', reason: 'no_passing_evidence' };
}javascript
// 标记任务完成前
const evidence = context.quality_evidence;
const hasPassingEvidence = (
evidence?.tests?.exit_code === 0 ||
evidence?.build?.exit_code === 0
);
if (!hasPassingEvidence) {
return { gate_status: 'blocked', reason: 'no_passing_evidence' };
}Best Practices Pattern Library
最佳实践模式库
Track success/failure patterns across projects to prevent repeating mistakes and proactively warn during code reviews.
| Rule | File | Key Pattern |
|---|---|---|
| YAGNI Gate | | Pre-implementation scope check, justified complexity ratio, simpler alternatives |
| Pattern Library | | Success/failure tracking, confidence scoring, memory integration |
| Review Checklist | | Category-based review, proactive anti-pattern detection |
跟踪跨项目的成功/失败模式，避免重复犯错，并在代码评审时主动发出警告。
| 规则 | 文件 | 核心模式 |
|---|---|---|
| YAGNI门禁 | | 开发前范围检查、合理复杂度比值、更简单替代方案 |
| 模式库 | | 成功/失败跟踪、置信度评分、记忆集成 |
| 评审检查清单 | | 基于类别的评审、主动反模式检测 |
Pattern Confidence Levels
模式置信度等级
| Level | Meaning | Action |
|---|---|---|
| Strong success | 3+ projects, 100% success | Always recommend |
| Mixed results | Both successes and failures | Context-dependent |
| Strong anti-pattern | 3+ projects, all failed | Block with explanation |
| 等级 | 含义 | 操作 |
|---|---|---|
| 高成功率 | 3+个项目，100%成功 | 始终推荐 |
| 结果混合 | 既有成功也有失败 | 视上下文而定 |
| 高反模式 | 3+个项目，全部失败 | 阻塞并说明原因 |
Common Pitfalls
常见陷阱
| Pitfall | Problem | Solution |
|---|---|---|
| Skip gates for "simple" tasks | Get stuck later | Always run gate check |
| Ignore WARNING status | Undocumented assumptions cause issues | Document every assumption |
| Not tracking attempts | Waste cycles on same approach | Track every attempt, escalate at 3 |
| Proceed when BLOCKED | Build wrong solution | NEVER bypass BLOCKED gates |
| 陷阱 | 问题 | 解决方案 |
|---|---|---|
| 为“简单”任务跳过门禁 | 后续陷入困境 | 始终执行门禁检查 |
| 忽略警告状态 | 未记录的假设导致问题 | 记录所有假设 |
| 未跟踪尝试次数 | 在同一方案上浪费时间 | 跟踪所有尝试，3次后升级 |
| 被阻塞时仍继续执行 | 开发错误的解决方案 | 绝不绕过阻塞的门禁 |
Related Skills
相关技能
- - Project tier detection that feeds YAGNI gate
ork:scope-appropriate-architecture - - Enforce testing standards as part of quality gates
ork:architecture-patterns - - LLM-as-judge patterns for quality validation
llm-evaluation - - Validate datasets meet quality thresholds
ork:golden-dataset
- - 项目层级检测，为YAGNI门禁提供数据
ork:scope-appropriate-architecture - - 作为质量门禁的一部分，执行测试标准
ork:architecture-patterns - - 用于质量验证的LLM-as-judge模式
llm-evaluation - - 验证数据集是否符合质量阈值
ork:golden-dataset
Key Decisions
关键决策
| Decision | Choice | Rationale |
|---|---|---|
| Complexity Scale | 1-5 levels | Granular enough for estimation, simple enough for quick assessment |
| Block Threshold | 3 critical questions | Prevents proceeding with too many unknowns |
| Escalation Trigger | 3 failed attempts | Balances persistence with avoiding wasted cycles |
| Level 4-5 Requirement | Plan required | Complex tasks need upfront decomposition |
| 决策 | 选择 | 理由 |
|---|---|---|
| 复杂度等级 | 1-5级 | 足够精细用于估算，同时简单到可快速评估 |
| 阻塞阈值 | 3个关键问题 | 避免在未知因素过多时继续执行 |
| 升级触发条件 | 3次失败尝试 | 在坚持和避免浪费时间之间取得平衡 |
| 4-5级任务要求 | 必须有规划 | 复杂任务需要预先分解 |
Capability Details
能力细节
complexity-scoring
complexity-scoring
Keywords: complexity, score, difficulty, estimate, sizing, 1-5 scale
Solves: How complex is this task? Score task complexity on 1-5 scale, assess implementation difficulty
关键词： complexity, score, difficulty, estimate, sizing, 1-5 scale
解决问题： 任务复杂度如何？在1-5级范围内为任务复杂度评分，评估开发难度
blocking-thresholds
blocking-thresholds
Keywords: blocking, threshold, gate, stop, escalate, cannot proceed
Solves: When should I block progress? >3 critical questions = BLOCK, Missing dependencies = BLOCK
关键词： blocking, threshold, gate, stop, escalate, cannot proceed
解决问题： 何时应阻塞进度？>3个关键问题=阻塞，缺失依赖项=阻塞
critical-questions
critical-questions
Keywords: critical questions, unanswered, unknowns, clarify
Solves: What are critical questions? Count unanswered, block if >3
关键词： critical questions, unanswered, unknowns, clarify
解决问题： 什么是关键问题？统计未解决数量，超过3个则阻塞
stuck-detection
stuck-detection
Keywords: stuck, failed attempts, retry, 3 attempts, escalate
Solves: How do I detect when stuck? After 3 failed attempts, escalate
关键词： stuck, failed attempts, retry, 3 attempts, escalate
解决问题： 如何检测陷入困境？3次失败尝试后升级
gate-validation
gate-validation
Keywords: validate, gate check, pass, fail, gate status
Solves: How do I validate quality gates? Run pre-task gate validation
关键词： validate, gate check, pass, fail, gate status
解决问题： 如何验证质量门禁？执行任务前门禁验证
pre-task-gate-check
pre-task-gate-check
Keywords: pre-task, before starting, can proceed
Solves: How do I check gates before starting? Assess complexity, identify blockers
关键词： pre-task, before starting, can proceed
解决问题： 启动前如何检查门禁？评估复杂度，识别阻塞因素
complexity-breakdown
complexity-breakdown
Keywords: breakdown, decompose, subtasks, split task
Solves: How do I break down complex tasks? Split Level 4-5 into Level 1-3 subtasks
关键词： breakdown, decompose, subtasks, split task
解决问题： 如何分解复杂任务？将4-5级任务拆分为1-3级子任务
requirements-completeness
requirements-completeness
Keywords: requirements, incomplete, acceptance criteria
Solves: Are requirements complete enough? Check functional/technical requirements
关键词： requirements, incomplete, acceptance criteria
解决问题： 需求是否足够完整？检查功能/技术需求
escalation-protocol
escalation-protocol
Keywords: escalate, ask user, need help, human guidance
Solves: When and how to escalate? Escalate after 3 failed attempts
关键词： escalate, ask user, need help, human guidance
解决问题： 何时及如何升级？3次失败尝试后升级
llm-as-judge
llm-as-judge
Keywords: llm as judge, g-eval, aspect scoring, quality validation
Solves: How do I use LLM-as-judge? Evaluate relevance, depth, coherence with thresholds
关键词： llm as judge, g-eval, aspect scoring, quality validation
解决问题： 如何使用LLM-as-judge？对照阈值评估相关性、深度、连贯性
yagni-gate
yagni-gate
Keywords: yagni, over-engineering, justified complexity, scope check, too complex, simplify
Solves: Is this complexity justified? Calculate justified_complexity ratio against project tier, BLOCK if > 2.0, surface simpler alternatives
关键词： yagni, over-engineering, justified complexity, scope check, too complex, simplify
解决问题： 复杂度是否合理？对照项目层级计算合理复杂度比值，>2.0则阻塞，提供更简单替代方案