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 ZTE-AICloud/Co-OmniSpec --skill checklistgit clone --depth 1 https://github.com/ZTE-AICloud/Co-OmniSpecWrote 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/zte-aicloud/co-omnispec/checklist)<a href="https://agentmods.dev/skills/zte-aicloud/co-omnispec/checklist"><img src="https://agentmods.dev/badge/skills/zte-aicloud/co-omnispec/checklist/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/zte-aicloud/co-omnispec/checklist"><img src="https://agentmods.dev/badge/skills/zte-aicloud/co-omnispec/checklist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00072 | $0.02033 |
| Opus 5 | $0.00036 | $0.01017 |
| Sonnet 5 | $0.00014 | $0.00407 |
| Haiku 4.5 | $0.00007 | $0.00203 |
Grade A, and why
checklist 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
检查清单生成技能
清单核心概念
清单是需求编写的单元测试 — 验证特定领域中需求的质量、清晰度和完整性.
不用于验证/测试:
- 不是"验证按钮点击正确"
- 不是"测试错误处理有效"
- 不是检查代码/实现是否符合规范
用于需求质量验证:
- "是否为所有卡片类型定义了视觉层次需求？"(完整性)
- "'突出显示'是否通过具体尺寸/位置进行了量化？"(清晰度)
- "所有交互元素的悬停状态需求是否一致？"(一致性)
用户输入
在继续之前, 你必须考虑用户的消息内容(如果不为空).
执行步骤
0. skill执行开始时间打点记录
开始执行步骤之前，需要进行一些打点记录工作，记录本skill的执行时间到 start_time字段：
- 判断当前操作系统，windows还是linux系统;
- 针对不同操作系统运行脚本获取配置
windows:
Get-Date -Format "yyyy-MM-dd HH:mm:ss"linux:date +"%Y-%m-%d %H:%M:%S" - 将获取的时间记录到
start_time
1. 设置
- 判断当前操作系统, windows 还是 linux 系统;
- 针对不同操作系统从仓库根目录运行脚本
windows:
scripts/powershell/check-prerequisites.ps1 --jsonlinux:scripts/bash/check-prerequisites.sh --json - 解析 JSON 以获取 FEATURE_DIR 和 AVAILABLE_DOCS 列表
- 所有文件路径必须是绝对路径
- 对于参数中的单引号如 "I'm Groot", 使用转义语法: 例如 'I'''m Groot'(或优先使用双引号)
2. 澄清意图(动态)
推导最多三个初始上下文澄清问题(无预编目录). 它们必须:
- 从用户的表述 + 从规范/计划/任务中提取的信号生成
- 只询问实质上改变清单内容的信息
- 如果在用户输入中已经明确, 则跳过
- 优先考虑精确性而非广度
生成算法:
- 提取信号: 功能领域关键词、风险指标、利益相关者提示、显式交付物
- 将信号聚类为候选焦点区域(最多 4 个), 按相关性排序
- 识别可能的受众和时间(作者、审查者、QA、发布)
- 检测缺失维度: 范围广度、深度/严格性、风险重点、排除边界、可测量验收标准
- 从以下原型中选择问题:
- 范围细化、风险优先级、深度校准、受众框架、边界排除、场景类别缺口
问题格式规则:
- 如果提供选项, 生成紧凑表格(Option | Candidate | Why It Matters)
- 最多 A-E 选项; 自由形式更清晰时省略表格
- 不要让用户重述已说内容
交互不可能时的默认值:
- 深度: Standard
- 受众: Reviewer(PR, 代码相关); Author(其他)
- 焦点: 前 2 个相关性聚类
输出问题(标记 Q1/Q2/Q3). 回答后若 >=2 个场景类别仍不清楚, 可追问最多 2 个(Q4/Q5), 总计不超过 5 个问题.
3. 理解用户请求
结合用户输入 + 澄清答案:
- 推导清单主题(例如: security, review, deploy, ux)
- 整合用户明确提到的必需项目
- 将焦点选择映射到类别框架
- 从规范/计划/任务中推断缺失上下文(不要虚构)
4. 加载功能上下文
从 FEATURE_DIR 读取:
- spec.md: 功能需求和范围
- design.md(如果存在): 技术细节、依赖关系
- tasks.md(如果存在): 实施任务
上下文加载策略:
- 仅加载与活动焦点区域相关的必要部分
- 优先将长部分总结为简洁的场景/需求要点
- 使用渐进式披露: 仅在检测到差距时添加后续检索
5. 生成清单
创建 FEATURE_DIR/checklists/ 目录(如果不存在). 生成唯一清单文件名:
- 使用短描述性名称(例如
ux.md,api.md,security.md) - 如果文件已存在, 追加到现有文件
- 每次运行创建新文件(不覆盖现有清单)
- 项目从 CHK001 开始顺序编号
核心原则 — 测试需求, 而非实现:
每个清单项目必须评估需求本身, 检查:
- 完整性: 所有必要的需求是否存在？
- 清晰度: 需求是否明确无歧义且具体？
- 一致性: 需求之间是否相互一致？
- 可测量性: 需求是否可以客观验证？
- 覆盖度: 是否涵盖了所有场景/边缘情况？
What ships with it
1 file 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.
- 10d ago First seen · 190 lines · 72 tokens per session scan A 382aa68a364e
checklist is a skill published in the GitHub repository ZTE-AICloud/Co-OmniSpec (54 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 2,033 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…