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 WhispeRre/pangu --skill pangu-skillgit clone --depth 1 https://github.com/WhispeRre/panguWrote 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/whisperre/pangu/pangu-skill)<a href="https://agentmods.dev/skills/whisperre/pangu/pangu-skill"><img src="https://agentmods.dev/badge/skills/whisperre/pangu/pangu-skill/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/whisperre/pangu/pangu-skill"><img src="https://agentmods.dev/badge/skills/whisperre/pangu/pangu-skill.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 | $0.00141 | $0.07464 |
| Opus 5 | $0.00071 | $0.03732 |
| Sonnet 5 | $0.00028 | $0.01493 |
| Haiku 4.5 | $0.00014 | $0.00746 |
Grade A, and why
pangu-skill 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 11d 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 — 494 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pangu Skill 1.0
v1.0 · 2026-07-06 — An Agent Skill quality evaluator and validation optimizer built around a 9-dimension rubric, test-prompt validation, git ratchet decisions, and human-in-the-loop checkpoints.
Core idea: evaluate → improve → validate → human confirm → keep or revert → generate result cards. Project identity:
pangu-skill.
设计哲学
autoresearch 的精髓：
- 单一可编辑资产 — 每次只改一个 SKILL.md
- 双重评估 — 结构评分（静态分析）+ 效果验证（跑测试看输出）
- 棘轮机制 — 只保留改进，自动回滚退步
- 独立评分 — 评分用子agent，避免「自己改自己评」的偏差
- 人在回路 — 每个skill优化完后暂停，用户确认再继续
与纯结构审查的区别：不只看 SKILL.md 写得规不规范，更看改完后实际跑出来的效果是否更好。
评估 Rubric（9维度，总分100）
设计依据：基于 SkillLens 论文（arXiv 2605.23899）实证发现——LLM-as-judge 评估 skill 质量准确率仅 46.4%（接近随机），加入 meta-skill 三维度后提升到 73.8%。本 rubric 强化 dim3 / dim5 评分标准，新增 dim9「反例与黑名单」，权重平衡到 100。目的：让评分对真实质量更敏感，减少 LLM judge 的乐观偏差。
结构维度（59分）— 静态分析
| # | 维度 | 权重 | 评分标准 |
|---|---|---|---|
| 1 | Frontmatter质量 | 7 | name规范、description包含做什么+何时用+触发词、≤1024字符、禁结尾加"灵活应用/根据情况判断"等空话尾巴 |
| 2 | 工作流清晰度 | 12 | 步骤明确可执行、有序号、每步有明确输入/输出 |
| 3 | 失败模式编码 | 12 | 必须显式编码失败模式（写出"如果 X 失败 → Y"的明确分支）；有fallback路径、错误恢复；只写正向流程而不写失败分支扣 ≥3 分（SkillLens meta-skill 维度） |
| 4 | 检查点设计 | 6 | 关键决策前有用户确认、防止自主失控；检查点必须显性标记（🔴/STOP/CHECKPOINT），仅靠"如果...建议..."措辞不算 |
| 5 | 可执行具体性 | 17 | 不模糊、有具体参数/格式/示例、可直接执行；禁止"建议/可以考虑/根据情况/灵活把握/视情况而定"等软化措辞——出现 ≥3 处扣 ≥3 分（SkillLens actionable specificity 维度） |
| 6 | 资源整合度 | 4 | references/scripts/templates引用正确、路径可达 |
效果维度（35分）— 需要实测
| # | 维度 | 权重 | 评分标准 |
|---|---|---|---|
| 7 | 整体架构 | 12 | 结构层次清晰、不冗余不遗漏、与Agent Skill 生态一致；冗余/AI腔废话段落（说白了/换句话说/首先其次综上等AI 套话禁用词）出现一处扣 1 分 |
| 8 | 实测表现 | 23 | 用测试prompt跑一遍，输出质量是否符合skill宣称的能力 |
Meta-skill 维度（6分）— 反例与黑名单
| # | 维度 | 权重 | 评分标准 |
|---|---|---|---|
| 9 | 反例与黑名单 | 6 | skill 必须有"不要做什么"的反例清单；只写"应该做 X"没有"不要做 Y"扣 ≥3 分；红灯/危险动作/反模式应单独章节列出（SkillLens risk-action blacklist 维度） |
评分规则
- 维度1-7、9：每个维度打 1-10 分，乘以权重得到该维度得分
- 维度8（实测表现）：跑2-3个测试prompt，按输出质量打1-10分
- 总分 = Σ(维度分 × 权重) / 10，满分100
- 改进后总分必须 严格高于 改进前才保留
What ships with it
8 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.
- 11d ago First seen · 494 lines · 141 tokens per session scan A 78896cfcfd3e
pangu-skill is a skill published in the GitHub repository WhispeRre/pangu (22 stars, last pushed 2mo ago), licensed MIT. It adds 141 tokens to every session and 7,464 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
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…