Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add skillmds/skillmd/plugin install create-agent-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/skillmds/skillmd/skill-publisher)<a href="https://agentmods.dev/skills/skillmds/skillmd/skill-publisher"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/skill-publisher/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/skillmds/skillmd/skill-publisher"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/skill-publisher.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 | $0.00103 | $0.03514 |
| Opus 5.5 | $0.00041 | $0.01406 |
| Sonnet 5 | $0.00021 | $0.00703 |
| Haiku 4.5 | $0.00010 | $0.00351 |
Grade A, and why
skill-publisher 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 4d 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.
This is a copy
100% identical to skill-publisher — 1 line differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Publisher
一键将 agent skill 发布到 GitHub，自动完成验证、README 质量检查、补全、推送和真实安装验证。
前置条件
ghCLI 已安装且已登录（gh auth status）- Skill 目录包含有效的
SKILL.md（含 YAML frontmattername+description） - 优先使用
/Users/joe/.agents/skills/<name>作为正式源目录；.codex/.claude可作为兼容入口。
发布流程
当用户要求发布 skill 时，运行发布脚本：
python3 ~/.agents/skills/qiaomu-skill-publisher/scripts/publish_skill.py <skill_dir>
确定 skill 目录
- 如果用户说"发布这个 skill"且当前在某个 skill 目录 → 用当前目录
- 如果用户指定了 skill 名称 → 优先在
~/.agents/skills/下查找 - 如果不确定 → 问用户要发布哪个 skill
脚本自动完成的步骤
- 验证 SKILL.md 的 YAML frontmatter（name + description）
- 检查 gh CLI 就绪状态
- 创建 LICENSE（MIT，如果缺少）
- 生成或检查 README.md：生成时不再写 TODO 模板；已存在时拦截明显占位符
- 识别仓库名：优先使用当前
origin仓库名，避免把skill-publisher误发到错误 repo - 初始化 git（如果需要）
- 创建或更新 GitHub 公开仓库并推送
- 验证
npx skills add --list可发现，并在临时目录真实安装
参数选项
| 参数 | 说明 |
|---|---|
--private |
创建私有仓库（默认公开） |
--dry-run |
仅检查，不实际发布 |
--skip-verify |
跳过 npx skills 验证 |
--github-user USER |
指定 GitHub 用户名（默认自动获取） |
--repo-name NAME |
指定 GitHub 仓库名；默认优先使用当前 origin 仓库名，否则使用 skill name |
--no-symlink |
跳过同步 ~/.agents/skills/ 实体目录 |
自动同步 ~/.agents/skills/ 实体目录
发布成功后，脚本可自动把 skill 同步到 ~/.agents/skills/<name> 作为实体目录。
这个目录是通用 Agent Skills 标准目录，以下工具会自动读取： OpenCode、Codex CLI、Cursor、Gemini CLI、GitHub Copilot、Amp、Cline、Warp 等。
一次发布，多工具共享，无需重复配置。
如果当前发布源已经是 ~/.agents/skills/<name>，脚本会跳过同步，避免误删自己的源目录。若 skill name 与 repo name 不一致，或者你不想产生本地副本，发布时加 --no-symlink。
⚠️ SKILL.md YAML 安全规则（发布前必查）
npx skills 使用严格 YAML 解析器，以下写法会导致安装失败（报 "No valid skills found"）：
| ❌ 错误写法 | ✅ 正确写法 |
|---|---|
description: 含有 "引号" 的文字 |
改用 | 块标量（见下方） |
description: 含单引号'的文字 |
改用 | 块标量 |
description: 含冒号: 的文字 |
改用 | 块标量 |
最安全的 description 写法：
description: |
描述放这里，可以随意包含 "双引号"、'单引号'、冒号: 等特殊字符
触发词: 用户说...时触发
脚本已内置 YAML 严格校验（pyyaml），会在发布前捕获这类错误并给出修复提示。
更新已发布的 skill
对已有 GitHub 仓库的 skill 再次运行同一命令，脚本会检测到仓库已存在，自动 commit + push 更新。
What ships with it
2 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.
- 4d ago First seen · 277 lines · 103 tokens per session scan A a82afcb04dc7
skill-publisher is a skill published in the GitHub repository skillmds/skillmd (1 stars, last pushed yesterday), licensed MIT. It adds 103 tokens to every session and 3,514 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to skill-publisher, differing in 1 line, and is treated as a copy.
Other skills, from other repositories
repo-hygiene
Use when the scheduled repo-hygiene workflow runs from GitHub Actions (or an operator dry-run) to scan the repository for small, certain docs/test/code hygiene issues and fix them as one batched branch.
gh-skill
Manage agent skills with gh skill. Use this skill to discover, preview, install, update, and publish Agent Skills so an agent can self-manage the skills available in its environment.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
atmos-hooks
Atmos hooks: lifecycle events, hook kinds, command/store/git/security hooks, step/steps hooks, when: conditions, scoping and overrides, toolchain integration, --skip-hooks, and Atmos Pro/local output.
conventional-commit
Conventional Commit - Generate Conventional Commits 1.0.0 compliant messages. MANDATORY for all git commits. Invoke when user says 'commit', 'commit this', or asks to commit code.
merge
Resolve an in-progress merge or rebase by the intent of both sides, re-run the full gate on the merged tree, and finish the operation.