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 zhaixin244-wq/fnw --skill chip-doc-scorergit clone --depth 1 https://github.com/zhaixin244-wq/fnwWrote 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/zhaixin244-wq/fnw/chip-doc-scorer)<a href="https://agentmods.dev/skills/zhaixin244-wq/fnw/chip-doc-scorer"><img src="https://agentmods.dev/badge/skills/zhaixin244-wq/fnw/chip-doc-scorer/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/zhaixin244-wq/fnw/chip-doc-scorer"><img src="https://agentmods.dev/badge/skills/zhaixin244-wq/fnw/chip-doc-scorer.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 | $0.00152 | $0.06017 |
| Opus 5.5 | $0.00061 | $0.02407 |
| Sonnet 5.5 | $0.00030 | $0.01203 |
| Haiku 4.5 | $0.00015 | $0.00602 |
Grade A, and why
chip-doc-scorer 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 2mo 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 — 452 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chip Doc Scorer — 芯片架构文档多维度评分器
核心理念：量化评估 → 定位短板 → 生成报告 → 指导改进 → 复评验证 适用文档类型：FS 功能规格书 / UA 微架构文档 / RTL 代码 集成方法论：
doc-quality-feedback-loop.md+risk-driven-methodology.md+cross-agent-consistency.md
设计哲学
- 文档类型自适应 — 根据文档类型自动选择对应评分 Rubric
- 双重评估 — 脚本可查项（自动化）+ LLM 审查项（语义分析）
- 量化可追溯 — 每个维度有明确的评分标准和扣分依据
- 对标规范 — 评分标准对齐项目质量检查清单（QC/MC/IC）
- 结果可比较 — 支持版本间对比，量化改进效果
- 风险感知 — 高风险维度权重自动提升，评审资源分配更精准
- 闭环改进 — 评分→改进→复评，最多 3 轮迭代直到达标
评分 Rubric 总览
| 文档类型 | Rubric | 总分 | 维度数 | 对标清单 |
|---|---|---|---|---|
| FS | FS Rubric | 100 | 8+1 | quality-checklist-fs.md |
| UA | UA Rubric | 100 | 10+1 | quality-checklist-microarch.md |
| RTL | RTL Rubric | 100 | 10+1 | quality-checklist-impl.md |
"+1" 为跨文档一致性维度，仅在上下游文档存在时启用。
FS 功能规格书 Rubric（100分）
评分维度
| # | 维度 | 权重 | 评分标准 | 对标 QC |
|---|---|---|---|---|
| F1 | 需求覆盖 | 15 | RTM 覆盖率 ≥90%=满分，每降 5% 扣 2 分；REQ 编号缺失/未追溯扣分 | QC-05, QC-21 |
| F2 | 接口完整性 | 15 | §6 信号均有 §5.x.2 对应端口；无悬空信号；位宽参数化；接口时序明确 | QC-01, QC-10, QC-13, QC-20 |
| F3 | PPA 量化度 | 10 | §8 所有指标有数值或"待综合验证"标注；子模块分配合计 ≤ 顶层；有约束类型 | QC-03, QC-11, QC-14 |
| F4 | 功能描述质量 | 15 | §4 数据流表完整（输入→处理→输出）；控制流有仲裁/流控/超时描述；工作模式有状态转移图 | QC-06, QC-16 |
| F5 | 寄存器定义 | 10 | §7 地址无重叠；位域覆盖所有 bit；访问类型正确；复位值明确 | QC-02, QC-12 |
| F6 | 异常处理 | 10 | §5.x.4 + §6.4 异常表非空；每个异常有触发条件、行为、恢复方式、相关信号 | QC-06 |
| F7 | 图表规范 | 10 | D2/Wavedrom 格式正确；PNG 文件存在；图文描述一致；每张图有说明文字 | QC-09, QC-18, QC-23~27 |
| F8 | 文档规范 | 15 | 版本号/修订历史一致；约束与假设非空；缩略语完整；子模块编号连续；时钟/复位已明确 | QC-04, QC-07, QC-08, QC-15, QC-17, QC-19, QC-22 |
| F9 | 跨文档一致性 | 10 | PR→FS 需求覆盖率 ≥95%；端口定义与 PR 一致 | cross-agent-consistency |
评分规则
- 每个维度按 1-10 分打分，乘以权重系数（权重/10）得到维度得分
- 总分 = Σ(维度分 × 权重/10)，满分 100
- 扣分必须附具体理由（引用 QC 编号和文档章节）
- 风险加权：维度涉及 Critical/High 风险 REQ 时，权重 ×1.5
评分等级
| 等级 | 分数区间 | 含义 | 建议 |
|---|---|---|---|
| S | 90-100 | 优秀 | 可直接进入 UA 阶段 |
| A | 80-89 | 良好 | 小幅修改后可进入 UA |
| B | 70-79 | 合格 | 需修复明显缺陷后重新评分 |
| C | 60-69 | 不合格 | 需返回 FS 设计阶段补充 |
| D | <60 | 严重不足 | 需重新编写 FS |
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.
- 2mo ago First seen · 452 lines · 152 tokens per session scan A 5019eee3c3df
chip-doc-scorer is a skill published in the GitHub repository zhaixin244-wq/fnw (31 stars, last pushed 5mo ago), licensed MIT. It adds 152 tokens to every session and 6,017 once invoked, about $0.0006 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.
chip-doc-scorer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| chip-doc-scorerzhaixin244-wq/fnw | Skill | 31 | 5mo ago | MIT | A | 152 | Claude Code |
| orbit-notionnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 117 | Claude Code, Codex |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | yesterday | Apache-2.0 | A | 123 | Claude Code |
| apify-youtube-transcript-scrapersickn33/agentic-awesome-skills | Skill | 50k | yesterday | MIT | A | 48 | Claude Code |
| report-to-pdfasgeirtj/system_prompts_leaks | Skill | 71k | 2d ago | CC0-1.0 | A | 17 | Claude Code, Codex |
| legal-holdanthropics/claude-for-legal | Skill | 10.0k | 3d ago | Apache-2.0 | A | 68 | Claude Code |
| artifact-template-minimal-letterheadasgeirtj/system_prompts_leaks | Skill | 71k | 2d ago | CC0-1.0 | A | 54 | Claude Code, Codex |