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 eval-design-consistency-checkgit 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/eval-design-consistency-check)<a href="https://agentmods.dev/skills/zte-aicloud/co-omnispec/eval-design-consistency-check"><img src="https://agentmods.dev/badge/skills/zte-aicloud/co-omnispec/eval-design-consistency-check/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/eval-design-consistency-check"><img src="https://agentmods.dev/badge/skills/zte-aicloud/co-omnispec/eval-design-consistency-check.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 | $0.00078 | $0.01852 |
| Opus 5.5 | $0.00031 | $0.00741 |
| Sonnet 5.5 | $0.00016 | $0.00370 |
| Haiku 4.5 | $0.00008 | $0.00185 |
Grade A, and why
eval-design-consistency-check 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 1mo 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
需求边界一致性检查
概览(职责与输入输出)
职责
本技能提供需求边界一致性检查的知识定义和执行策略,帮助审核人员:
- 检测 Scope Creep(变更超出需求范围)
- 检查需求覆盖完整性
- 验证语义一致性
输入前提
- 需要对比的两份文档(目标文档和参照文档)
- 可选:代码文件路径(用于判断业务场景归属)
输出产物
- 一致性检查结论(blocking/warning/info)
- 具体的问题描述和定位
行为准则(会话全程有效,不因对话长度放松)
- ❗ 每个发现必须引用来源(文件路径 + 行号)— 每次输出前自检
- ❗ 评分基于检查清单客观打分(按清单定义的 0/1/2 或 Pass/Partial/Fail)— 每次输出前自检
- ❗ 禁止单边修复 — 改文档必须同步改实现,改实现必须同步改文档 — 每次修改前自检
执行流程
Step 1: Scope Creep 检测
- 提取目标文档中每个变更点
- 在参照文档中查找对应业务需求依据(Grep FR-xxx / 功能点编号)
- 标记无需求依据的变更(blocking)
- 完成性要求: 已检查变更数 == 提取的变更总数
- 失败降级: 参照文档不可读 → 标注 "UNABLE TO ASSESS: 参照文档不可用"
- ✅ Checkpoint: "Step 1 完成: 检查 X 个变更点,Y 个无需求依据"
Step 2: 语义一致性检测
- 对比目标与参照文档的业务场景描述
- 识别语义不一致的描述(warning)
- 区分事实性差异和表述差异
- 完成性要求: 已对比场景数 == 两文档场景总数
- 失败降级: 语义无法判断 → 标注 "UNABLE TO ASSESS: [原因]" + 禁止推测
- ✅ Checkpoint: "Step 2 完成: 对比 X 个场景,Y 个语义不一致"
Step 3(仅 spec_review 模式): 需求覆盖检测
- 逐条检查参照文档的每个 FR-xxx
- 确认每个 FR 有对应设计条目
- 记录覆盖不完整的需求(warning)
- 完成性要求: 已检查 FR 数 == 参照文档 FR 总数
- 失败降级: 目标文档格式无法解析 → 标注 "UNABLE TO ASSESS: [原因]"
- ✅ Checkpoint: "Step 3 完成: 检查 X 个 FR,Y 个覆盖不完整"
代码读取策略
目的:仅凭文档描述无法判断一个类属于哪个业务路径。例如 LiteSummaryFileService 的文档描述是"按 FTP 汇总成功推送的网元",与 spec.md 的"FTP 推送"场景语义上看起来匹配,无法发现越界。必须读取代码才能判断业务场景归属。
与 design-reviewer 的区分:
| Agent | 读代码的目的 | 读什么 |
|---|---|---|
| design-reviewer | 验证技术实现是否准确(调用链、方法签名) | 详细实现代码 |
| requirement-consistency-reviewer | 理解变更文件的业务场景归属 | 包路径、类注释、类级 JavaDoc,不读方法体 |
执行规则:
- 从目标文档中提取所有涉及的变更文件列表
- 先尝试从文档上下文(包路径、类名、变更说明)推断业务场景归属
- 当文档上下文不足以确认时,读取对应代码文件的类级信息(包声明、类注释、类签名),不读方法体
- 判断目标:"这个类服务于哪个业务路径/应用模块",而非"这个方法的实现是否正确"
代码读取示例命令:
# 读取文件开头30行获取包路径和类注释
head -n 30 /path/to/FileName.java
# 搜索类定义行
Grep "^public class|^class" /path/to/*.java
# 按包路径筛选文件
Glob "app/application/lite/**/*.java"
示例:读 LiteSummaryFileService 时,包路径 app.application.lite.service 和类注释揭示它服务于 Lite APP 定时备份,而非 USC 主流程的周期备份推送 → 判定 Scope Creep,blocking。
问题严重度分级
| 级别 | 示例 |
|---|---|
| blocking | 变更文件/类无 spec 中的需求依据、Scope Creep、关键诉求遗漏 |
| warning | 语义描述模糊、覆盖不完整 |
| info | 文字润色建议 |
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.
- 1mo ago First seen · 142 lines · 0 tokens per session scan A aeea0793cc14
eval-design-consistency-check is a skill published in the GitHub repository ZTE-AICloud/Co-OmniSpec (57 stars, last pushed 3mo ago), licensed MIT. It adds 78 tokens to every session and 1,852 once invoked, about $0.0003 per session on Opus 5.5. 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…