Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/AndrewNgGirl/SkillLensnpx agentmods add skills/andrewnggirl/skilllens/skill-scorerWrote 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/andrewnggirl/skilllens/skill-scorer)<a href="https://agentmods.dev/skills/andrewnggirl/skilllens/skill-scorer"><img src="https://agentmods.dev/badge/skills/andrewnggirl/skilllens/skill-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/andrewnggirl/skilllens/skill-scorer"><img src="https://agentmods.dev/badge/skills/andrewnggirl/skilllens/skill-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 | $0.00095 | $0.02521 |
| Opus 5 | $0.00048 | $0.01260 |
| Sonnet 5 | $0.00019 | $0.00504 |
| Haiku 4.5 | $0.00010 | $0.00252 |
Grade A, and why
skill-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 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
skill-scorer
一个"评测 Skill 的 Skill"。接收任意 Agent Skill 的源文件,必须依据本仓库的官方评分入口和 rubric/rubric.yaml
给出 5 大支柱的 100 分制评分、等级、证据引用与改进建议。Rubric 内置三类型差异化(atomic / pipeline / composite),子维度数随 skill 结构自动启用,由 applies_to 字段控制。同时兼容 Cursor / Claude / OpenClaw 三套规范。
When to use
- 用户提供
SKILL.md/ skill 文件夹 /.zip/ GitHub URL,并请求评分、审计或改进建议。 - 用户询问"我这个 skill 写得怎么样"、"怎么提升我的 skill 质量"、"帮我对齐官方最佳实践"。
- 不适用于:评价非 Skill 类文档(普通 README / 博客 / prompt 模板)。
Code Agent Quick Start
如果你是 Cursor、WorkBuddy、Hermes、小龙虾或类似 code agent,先读 USAGE.md。
推荐先运行 CLI 向导,让用户选择通用评测或金融专家版;如果选择金融专家版,向导会继续确认金融子场景,并输出后续官方命令:
python3 skills/skill-scorer/scripts/score.py --agent-wizard <path-to-skill-zip-dir-or-SKILL.md>
规则分预览:
python3 skills/skill-scorer/scripts/score.py <path-to-skill-zip-dir-or-SKILL.md>
完整 agent-side Deep Review(使用 code agent 自己的模型套餐,不消耗 SkillLens 服务端 key):
python3 skills/skill-scorer/scripts/score.py --agent-prompt <path-to-skill-zip-dir-or-SKILL.md> > agent-deep-review-prompt.md
# 将 agent-deep-review-prompt.md 完整交给当前 code agent 的模型,保存严格 JSON 为 agent-llm-results.json
python3 skills/skill-scorer/scripts/score.py --llm-results agent-llm-results.json <path-to-skill-zip-dir-or-SKILL.md>
不得临时生成自定义评分脚本替代官方 CLI;最终分数必须来自最后一步官方 CLI 输出。
金融专家版(可选)应优先通过 --agent-wizard 选择;手动执行时,必须在 --agent-prompt 和 --llm-results 两步都加入相同的 --domain finance --scenario <scenario-id>。支持的场景详见 USAGE.md。
Inputs
- 一个
SKILL.md文本,或 - 一个 skill 目录(含
scripts/references/assets/等),或 - 一个
.zip打包的 skill,或 - 一个指向 skill 仓库/子目录的 GitHub URL(Web 工具侧支持)。
Outputs
{
"spec": "claude | openclaw",
"language": "zh | en",
"score": 0-100,
"grade": "S | A | B | C | D",
"pillars": [
{
"id": "business_value",
"score": 0-25,
"dimensions": [
{
"id": "...",
"checks": [
{
"id": "...",
"status": "pass|partial|fail|n_a",
"evidence": "<primary-language alias>",
"evidence_zh": "中文现状",
"evidence_en": "English diagnosis",
"fix": "<primary-language alias>",
"fix_zh": "中文改法",
"fix_en": "English fix"
}
]
}
]
}
],
"bonus": 0-5,
"suggestions": [
{
"title": "Top 改进项",
"title_zh": "中文 Top 改进项",
"title_en": "English Top Improvement",
"why": "现状",
"why_zh": "中文现状",
"why_en": "English why",
"how": "改法",
"how_zh": "中文改法",
"how_en": "English how"
}
],
"deepReviewCertificate": {
"status": "verified"
}
}
What ships with it
60 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.
- domains/finance/rubric.yaml 24 KB
- examples/banking-workflow-assistant/SKILL.md 2.5 KB
- examples/finance-scenario-advisor/SKILL.md 2.8 KB
- examples/financial-data-analysis-agent/SKILL.md 2.5 KB
- examples/financial-education-coach/SKILL.md 2.5 KB
- examples/mega-pipeline/agents/a11y/SKILL.md 275 B
- examples/mega-pipeline/agents/api/SKILL.md 269 B
- examples/mega-pipeline/agents/async/SKILL.md 281 B
- examples/mega-pipeline/agents/audit/SKILL.md 281 B
- examples/mega-pipeline/agents/authn/SKILL.md 281 B
- examples/mega-pipeline/agents/authz/SKILL.md 281 B
- examples/mega-pipeline/agents/backend/SKILL.md 293 B
- examples/mega-pipeline/agents/caching/SKILL.md 293 B
- examples/mega-pipeline/agents/circuit/SKILL.md 293 B
- examples/mega-pipeline/agents/complexity/SKILL.md 311 B
- examples/mega-pipeline/agents/compliance/SKILL.md 311 B
- examples/mega-pipeline/agents/config/SKILL.md 287 B
- examples/mega-pipeline/agents/cors/SKILL.md 275 B
- examples/mega-pipeline/agents/coverage/SKILL.md 299 B
- examples/mega-pipeline/agents/crypto/SKILL.md 287 B
- examples/mega-pipeline/agents/csrf/SKILL.md 275 B
- examples/mega-pipeline/agents/deps/SKILL.md 275 B
- examples/mega-pipeline/agents/docs/SKILL.md 275 B
- examples/mega-pipeline/agents/env/SKILL.md 269 B
- examples/mega-pipeline/agents/events/SKILL.md 287 B
- examples/mega-pipeline/agents/frontend/SKILL.md 299 B
- examples/mega-pipeline/agents/gdpr/SKILL.md 275 B
- examples/mega-pipeline/agents/headers/SKILL.md 293 B
- examples/mega-pipeline/agents/i18n/SKILL.md 275 B
- examples/mega-pipeline/agents/idor/SKILL.md 275 B
- examples/mega-pipeline/agents/imports/SKILL.md 293 B
- examples/mega-pipeline/agents/infra/SKILL.md 281 B
- examples/mega-pipeline/agents/licensing/SKILL.md 305 B
- examples/mega-pipeline/agents/logging/SKILL.md 293 B
- examples/mega-pipeline/agents/memory/SKILL.md 287 B
- examples/mega-pipeline/agents/metrics/SKILL.md 293 B
- examples/mega-pipeline/agents/migration/SKILL.md 305 B
- examples/mega-pipeline/agents/naming/SKILL.md 287 B
- examples/mega-pipeline/agents/observability/SKILL.md 329 B
- examples/mega-pipeline/agents/perf/SKILL.md 275 B
- examples/mega-pipeline/agents/privacy/SKILL.md 293 B
- examples/mega-pipeline/agents/ratelimit/SKILL.md 305 B
- examples/mega-pipeline/agents/rbac/SKILL.md 275 B
- examples/mega-pipeline/agents/retries/SKILL.md 293 B
- examples/mega-pipeline/agents/schema/SKILL.md 287 B
- examples/mega-pipeline/agents/secrets/SKILL.md 293 B
- examples/mega-pipeline/agents/security/SKILL.md 299 B
- examples/mega-pipeline/agents/serialization/SKILL.md 329 B
- examples/mega-pipeline/agents/sql/SKILL.md 269 B
- examples/mega-pipeline/agents/sqli/SKILL.md 275 B
- examples/mega-pipeline/agents/streaming/SKILL.md 305 B
- examples/mega-pipeline/agents/style/SKILL.md 281 B
- examples/mega-pipeline/agents/tests/SKILL.md 281 B
- examples/mega-pipeline/agents/threading/SKILL.md 305 B
- examples/mega-pipeline/agents/timeout/SKILL.md 293 B
- examples/mega-pipeline/agents/tracing/SKILL.md 293 B
- examples/mega-pipeline/agents/typing/SKILL.md 287 B
- examples/mega-pipeline/agents/xss/SKILL.md 269 B
- examples/mega-pipeline/SKILL.md 397 B
- examples/pr-pipeline/agents/reviewer/SKILL.md 443 B
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 · 177 lines · 95 tokens per session scan A 72564747d198
skill-scorer is a skill published in the GitHub repository AndrewNgGirl/SkillLens (75 stars, last pushed 3mo ago), licensed MIT. It adds 95 tokens to every session and 2,521 once invoked, about $0.0005 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
skill-sentinel
Auditoria e evolucao do ecossistema de skills. Qualidade de codigo, seguranca, custos, gaps, duplicacoes, dependencias e relatorios de saude.
large-workspace-handling
To partition large workspaces (100+ files) into scoped subagent tasks when context is insufficient.
skill-navigator
A skill that recommends which already-installed local agent skill matches a described task. It uses the machine's skill catalogue and does not perform the task itself.
Autoresearch
Iteratively improve a weak skill through score, tweak, and retest loops. Run against a target skill, define failure mode and rubric, execute the loop, and get a scored report with recommendations.
template-audit
Audit and quality-gate scripts for the template research framework. Covers documentation linting, filepath audits, mock-usage checking, template drift, and confidentiality / git-guard checks.
Verification Before Completion
Mandatory empirical verification suite execution before declaring task completion.