Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Kokxi/qa-test-skills --skill qa-requirement-reviewgit clone --depth 1 https://github.com/Kokxi/qa-test-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kokxi/qa-test-skills/qa-requirement-review)<a href="https://agentmods.dev/skills/kokxi/qa-test-skills/qa-requirement-review"><img src="https://agentmods.dev/badge/skills/kokxi/qa-test-skills/qa-requirement-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kokxi/qa-test-skills/qa-requirement-review"><img src="https://agentmods.dev/badge/skills/kokxi/qa-test-skills/qa-requirement-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00135 | $0.01923 |
| Opus 5 | $0.00068 | $0.00962 |
| Sonnet 5 | $0.00027 | $0.00385 |
| Haiku 4.5 | $0.00014 | $0.00192 |
Grade A, and why
qa-requirement-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
需求评审专项
核心原则
需求评审不是挑刺，而是确保需求可理解、可测试、可实现。
五维评审速查
各维度的详细检查清单、评审问题速查和严重度矩阵参见
references/review-standards.md。
评分规则：每个维度10分，总分≥40分为"有条件通过"，≥45分为"通过"。
| 维度 | 评分核心 | 典型问题 |
|---|---|---|
| 完整性 | 功能/非功能/约束/验收是否完整 | 主流程缺失、异常未定义、验收标准缺失 |
| 清晰性 | 术语/描述/示例是否清晰无歧义 | 术语歧义、描述模糊、缺少示例 |
| 一致性 | 内部/外部/版本是否一致 | 前后矛盾、与现有系统冲突 |
| 可测试性 | 验证/度量/自动化是否可行 | "体验好"不可验证、性能未量化 |
| 可实现性 | 技术/资源/业务是否可行 | 架构不支持、时间不合理 |
每维度的完整检查清单和评分标准详见
references/review-standards.md。
评审报告模板
完整模板（含五维评分表格、P0-P2问题清单）参见
references/report-template.md。
简要结构：
# 需求评审报告
## 评审结论：[通过/有条件通过/不通过]
## 五维评分：完整性X/10 清晰性X/10 一致性X/10 可测试性X/10 可实现性X/10
## 问题清单
### P0（必须修改）
### P1（建议修改）
### P2（可选修改）
## 改进建议
输出示例
评审一个PRD：用户登录功能需求 → 完整性检查：功能描述完整✅，但缺少非功能需求❌ → 清晰性检查："登录超时"未定义具体时间❌ → 一致性检查：前后描述一致✅ → 可测试性检查："响应要快"不可量化❌，应改为"登录响应<2秒" → 可实现性检查：技术方案可行✅ → 评审报告：P0问题（缺少非功能需求）+ P1问题（模糊表述）
五维评审判定示范（pass/fail 对照）：
| 维度 | PASS 示例 | FAIL 示例 | 判定要点 |
|---|---|---|---|
| 完整性 | "支持用户名+密码登录、验证码、密码找回，含异常场景" | "用户能登录系统"（无边界/异常/非功能） | 主流程+分支+异常+非功能是否齐 |
| 清晰性 | "密码错误3次锁定15分钟" | "密码错误多次后锁定"（多次=？锁定多久=？） | 数量/时间/条件是否有具体值 |
| 一致性 | 全文用"验证码"表述，前后一致 | 前文"短信验证码"后文"图形验证码" | 术语/规则/数据定义前后是否矛盾 |
| 可测试性 | "登录响应时间<2秒（P95）" | "响应要快" | 指标是否可量化、可观测 |
| 可实现性 | "基于现有统一认证服务实现" | "接入自研AI人脸识别（当前无此能力）" | 技术方案在当前栈是否可行 |
检查清单
需求评审完成后检查：
- 评审维度是否覆盖？
- 检查清单是否执行？
- 问题是否识别？
- 问题是否分类？
- 建议是否可行？
- 报告是否规范？
常见评审陷阱
- 只挑刺不建树：发现100个问题但没给1个改进建议 → 每个P0/P1问题必须附带建议
- 凭感觉不打分：说"这块不够好"但不指哪个维度 → 评审结论必须基于五维评分
- 过度纠错细节：纠结错别字忽略结构性缺失 → 区分"格式问题"和"内容问题"，优先评审内容
- 遗漏非功能：只看功能完整不看性能/安全 → 五维评审缺一不可
- 评审完不追踪：报告给了就完了 → 必须标注每条问题的处理状态（已修/待修/已确认）
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago Changed ed52218f4870
- 12d ago First seen · 130 lines · 135 tokens per session scan A 729a04a96790
qa-requirement-review is a skill published in the GitHub repository Kokxi/qa-test-skills (27 stars, last pushed 9d ago), licensed MIT. It adds 135 tokens to every session and 1,923 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
tdd-cycle
Red-Green-Refactor test-driven development cycle.
TDD 开发纪律助手
A development skill based on TDD, or test-driven development: write or update a test first, make it pass with the smallest code change, then improve the code and check for regressions.
red-green-tdd
Red/green test discipline for implementation work. Use once a doublecheck spec is on record and implementation is about to start — write a test that fails for the missing behavior, run it to see it fail (red), make the change, run again to see it pass (green).
test-driven-development
TDD: enforce RED-GREEN-REFACTOR, tests before code.
mk:development
Use when implementing features or writing code. TDD enforcement is opt-in via --tdd / MEOWKITTDD=1. Provides code patterns, skill loading, and coding standards.
sparc-methodology
SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration.