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 hanzhcn/laohan-skills --skill laohan-skillcreatorgit clone --depth 1 https://github.com/hanzhcn/laohan-skillsWrote 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/hanzhcn/laohan-skills/laohan-skillcreator)<a href="https://agentmods.dev/skills/hanzhcn/laohan-skills/laohan-skillcreator"><img src="https://agentmods.dev/badge/skills/hanzhcn/laohan-skills/laohan-skillcreator/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/hanzhcn/laohan-skills/laohan-skillcreator"><img src="https://agentmods.dev/badge/skills/hanzhcn/laohan-skills/laohan-skillcreator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 310 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00087 | $0.05915 |
| Opus 5 | $0.00044 | $0.02958 |
| Sonnet 5 | $0.00017 | $0.01183 |
| Haiku 4.5 | $0.00009 | $0.00592 |
Grade A, and why
laohan-skillcreator 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 — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.
laohan Skill 创建·审计·修复·优化器
创建是生产能力，审计是只读诊断，修复是小范围纠错，优化才是实验性演进。先判断模式，再使用与风险相称的验证；不得把一次明确的小修复升级成完整优化项目。
参考来源
当前借鉴 6 组上游来源。具体文件与最近核验 commit 记录在 references/upstream-sources.json。修改本 Skill 自身或用户要求更新方法时，先运行 scripts/check-upstreams.sh；发现上游变化后阅读相关 diff，只吸收能改善本地真实行为的变化，不自动覆盖本地方法。
-
anthropics/skills · skill-creator（https://github.com/anthropics/skills）
- 借鉴：渐进式披露（metadata→body→bundled 三层）、同条件 baseline 对比、盲比较、description 优化器、从 transcript 找重复工作、更新保持原名
- 核心理念：好的 skill 分三层渐进披露，不是一坨
-
Agent Skills specification / best practices（https://github.com/agentskills/agentskills）
- 借鉴：frontmatter 公共规范、渐进式披露、真实经验优先、控制强度与任务脆弱性匹配、从执行轨迹删除无效步骤
- 核心理念：Skill 应补充 agent 缺少的领域经验，不重复常识；过度全面同样会降低效果
-
mattpocock/skills · writing-great-skills（https://github.com/mattpocock/skills）
- 借鉴：触发分支、信息层级、完成条件、单一真源、去除 duplication/sediment/no-op
- 核心理念：Skill 追求过程可预测，不追求所有输出相同；不同分支只加载各自需要的信息
-
thananon/9arm-skills · debug-mantra/post-mortem/scrutinize（https://github.com/thananon/9arm-skills）
- 借鉴：verbatim recitation（首次一次+逐字+silent apply）、硬门控措辞、refuse to draft、跨 skill offer 非自动、先质疑意图、cite or it didn't happen
- 核心理念：不确定就停下来，每个 claim 要有引用
-
alchaincyf/darwin-skill + SkillLens / SkillOpt（https://github.com/alchaincyf/darwin-skill）
- 借鉴：9 维评分体系、反例黑名单 8 条、棘轮机制（git ratchet）、独立子 agent 复评、人在回路 5 阶段
- 核心理念：SkillLens 显示无 rubric 的 LLM 成对判断只有 46.4% 准确率，验证过的 meta-skill rubric 提升到 73.8%，仍不足以代替真实任务验证
-
obra/superpowers · writing-skills（https://github.com/obra/superpowers）
- 借鉴：只有深度创建/优化才做无 Skill baseline 与压力场景；可机械执行的约束优先交给脚本或 verifier
- 核心理念：测试应证明 Skill 改变了实际行为，但不能把 TDD 仪式强加给明确的小修复
核心理念
四原则：
- 路由决定成本 — name + description 负责让 agent 找到 Skill，正文第一步负责选择正确分支；触发准确不等于每次都走重流程
- 结构引导行为 — 好骨架比好指令有效
- 精简优于完整 — 每个章节都要证明存在的价值
- 效果先于格式分 — 静态 rubric 用于发现问题；触发、执行、held-out 样本与用户验收决定是否保留改动
先选模式
每次只选一个主模式：
| 模式 | 何时用 | 默认验证强度 |
|---|---|---|
CREATE |
新建一个可复用 Skill | 真实样本、触发/反触发、执行测试；复杂或高影响 Skill 再加 held-out |
AUDIT |
体检、评分、检查合理性 | 只读，引用具体行和行为证据；不修改文件 |
SURGICAL_FIX |
恢复原版、修正明确错误、更新固定合同或路径 | 比对真源、最小修改、直接覆盖该错误的针对性回归；不做静态评分、blind judge 或无关 held-out |
OPTIMIZE |
用户明确要求提升效果、比较新旧方案或全面演进 | 冻结 baseline/指标，运行 held-out；主观结果才用 blind judge |
UPSTREAM_REFRESH |
更新本 Skill 借鉴的方法或核验引用是否变化 | 运行上游检查，阅读变化，只合并相关增益并更新记录 commit |
What ships with it
7 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.
- 8d ago First seen · 377 lines · 87 tokens per session scan A 9a9c1876c938
laohan-skillcreator is a skill published in the GitHub repository hanzhcn/laohan-skills (11 stars, last pushed 13d ago), licensed MIT. It adds 87 tokens to every session and 5,915 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
videonote
A skill for turning video links or local videos from supported platforms into AI-generated Markdown notes. It can inspect videos, use available subtitles or transcription, and return notes with key points and chapters.
officecli-data-dashboard
Use this skill to build a multi-element Excel dashboard — Dashboard sheet on open, multiple formula-driven KPI cards, multiple charts, sparklines, and conditional formatting — from CSV or tabular input. Trigger on: 'dashboard', 'KPI dashboard', 'analytics dashboard', 'executive dashboard', 'metrics dashboard', 'CSV to…
douyin-upload
A workflow for using the sau command-line tool to log in to Douyin, the Chinese short-video platform, check account cookies, and publish videos or image-and-text posts.
kuaishou-upload
A workflow for using the sau command-line tool to log in to Kuaishou, a Chinese social media platform, check account cookies, and publish videos or image-and-text posts.
xiaohongshu-upload
A workflow for using the sau command-line tool to log in to Xiaohongshu, a Chinese social media platform, check account cookies, and publish videos or image-and-text posts.
skill-authoring
Author SKILL.md skills: frontmatter, validator limits, structure.