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-specifygit 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-specify)<a href="https://agentmods.dev/skills/zte-aicloud/co-omnispec/eval-specify"><img src="https://agentmods.dev/badge/skills/zte-aicloud/co-omnispec/eval-specify.svg" alt="Measured on agentmods" 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 | $0.00073 | $0.01587 |
| Opus 5 | $0.00036 | $0.00794 |
| Sonnet 5 | $0.00015 | $0.00317 |
| Haiku 4.5 | $0.00007 | $0.00159 |
Grade A, and why
eval-specify 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 8d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec 内容质量评测
适用范围
当前仅定义 spec_eval 模式的量规。design_eval、detail_eval 的量规待后续扩展。
四维评分（每维 25 分，满分 100）
维度 1：Business Value（业务价值）- 25 分
评估内容：
- 需求是否真正解决业务痛点（不是伪需求）
- 用户故事是否合理、可验证
- 优先级划分是否合理（P1/P2 的依据充分）
- 业务背景描述是否清晰
检查项：
- 业务背景/痛点描述是否具体、可理解
- 用户故事是否基于真实业务场景，非虚构
- P1/P2 优先级是否有明确依据（如：核心路径 vs 增强功能）
- 业务价值阐述是否避免空泛表述（如"提升用户体验"无具体说明）
典型扣分项：
- 用户故事脱离实际业务场景
- 优先级划分缺乏依据
- 业务价值阐述空泛
打分参考：
- 25 分：全部满足，无扣分项
- 20-24 分：1 处 minor 问题
- 15-19 分：2 处问题或 1 处明显问题
- 10-14 分：多处问题
- 0-9 分：严重缺失
维度 2：Technical Completeness（技术完整性）- 25 分
评估内容：
- 功能需求覆盖是否全面（关键场景无遗漏）
- 边界条件、异常情况是否考虑
- 非功能性需求（性能、安全、兼容性）是否提及
- GWT 场景是否具体、可测试
检查项：
- 主流程、异常流程、边界场景是否都有覆盖
- 是否考虑并发、重试、回滚、超时等常见技术场景
- 性能、安全、兼容性等 NFR 是否提及（若适用）
- GWT 场景的 Given/When/Then 是否完整、具体
典型扣分项：
- 遗漏关键边界场景（如并发、重试、回滚）
- 性能要求缺失或过于模糊
- 验收场景不完整
打分参考：同维度 1
维度 3：Clarity & Testability（清晰度与可测性）- 25 分
评估内容：
- FR 描述是否无歧义、可量化
- 验收标准是否明确（避免"及时"、"合理"等模糊词）
- 术语使用是否一致
- 是否避免过于抽象的描述
检查项：
- FR 描述是否可被不同读者一致理解
- 验收条件是否可量化（时间、次数、阈值等）
- 是否避免模糊词汇（"尽快"、"合理"、"较快"、"及时"）
- 术语（如：网元、推送、校验码）前后是否一致
典型扣分项：
- 使用模糊词汇（"尽快"、"合理"、"较快"）
- 验收条件无法量化
- 术语前后不一致
打分参考：同维度 1
维度 4：Traceability（可追溯性）- 25 分
评估内容：
- 每条 FR 是否能追溯到 feature_description
- 用户故事与 FR 的对应关系是否清晰
- 验收场景与 FR 的覆盖关系
检查项：
- 每条 FR 是否能在 feature_description 中找到对应诉求
- 是否引入了原始需求之外的功能（scope creep）
- 用户故事与 FR 的映射关系是否清晰
- 验收场景是否覆盖了对应的 FR
典型扣分项：
- FR 无法追溯到原始需求
- 引入了原始需求之外的功能（scope creep）
- 用户故事与 FR 对应关系混乱
打分参考：同维度 1
Finding 结构
每个 finding 必须包含以下字段：
| 字段 | 类型 | 说明 |
|---|---|---|
| severity | string | info | warning | error |
| location | string | 问题位置（章节名、FR 编号、用户故事编号等） |
| message | string | 问题描述 |
| recommendation | string | 改进建议 |
| line | number | null | 行号（可选，无法定位时为 null） |
| gene_related | string | null | 若问题位置与 Genome Usage Metadata 中某基因的 locations 匹配，填写该 gene_id；否则为 null |
| gene_contribution | string | null | 当 gene_related 非空时必填：positive（基因预填充有助于质量）、negative（基因预填充导致或加剧问题）、neutral（与基因无关或无法判断） |
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.
- 8d ago First seen · 161 lines · 73 tokens per session scan A 37b90ba17869
eval-specify is a skill published in the GitHub repository ZTE-AICloud/Co-OmniSpec (54 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 1,587 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.