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/PANGKAIFENG/ai-product-manager-skillsnpx agentmods add skills/pangkaifeng/ai-product-manager-skills/team-skill-creatorWrote 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/pangkaifeng/ai-product-manager-skills/team-skill-creator)<a href="https://agentmods.dev/skills/pangkaifeng/ai-product-manager-skills/team-skill-creator"><img src="https://agentmods.dev/badge/skills/pangkaifeng/ai-product-manager-skills/team-skill-creator/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/pangkaifeng/ai-product-manager-skills/team-skill-creator"><img src="https://agentmods.dev/badge/skills/pangkaifeng/ai-product-manager-skills/team-skill-creator.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 | $0.00124 | $0.03770 |
| Opus 5 | $0.00062 | $0.01885 |
| Sonnet 5 | $0.00025 | $0.00754 |
| Haiku 4.5 | $0.00012 | $0.00377 |
Grade C, and why
team-skill-creator scanned grade C with 1 finding 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 12d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
删除时先 dry-run/影响检查，再使用 Skillshare 的 uninstall/disable/trash 能力并同步；不要直接 `rm -rf` runtime symlink。 How it starts
The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill 生命周期治理（team-skill-creator）
中文速查
- 中文名：Skill 生命周期治理 / 能力沉淀判断
- 英文稳定名：
team-skill-creator - 适合：新建、导入、合并、发布、更新、弃用、退役、删除 Skill，并治理来源与分发目标
- 不适合：只评审已有 Skill，改用
skill-reviewer；一次性任务不要强行沉淀为 Skill
核心原则
这个 Skill 是治理编排层，不是新的复制工具。先确定能力是否值得沉淀，再确定唯一权威来源、生命周期和目标，最后调用已有工具完成发布与分发。
| 层级 | 唯一职责 | 不负责 |
|---|---|---|
team-skill-creator |
能力判断、查重、仓库选择、生命周期、验证和发布计划 | 自己实现所有 Agent 的复制协议 |
| GitHub 仓库 | 版本事实源、评审、回滚和公开披露边界 | 直接让每个 Agent 立即可用 |
| Skillshare | 从聚合目录同步到 Codex、Claude、OpenCode、Qoder、WorkBuddy 等本地目标 | 选择权威仓库或发布 Multica |
| Multica publisher | 通过白名单和稳定 ID 发布 Multica Skill 内容 | 管理本地 Agent，或自动决定项目/Agent/小队绑定 |
禁止对 $SKILLSHARE_SKILLS_ROOT 聚合目录运行 skillshare push。 该目录可能汇集多个来源，不能被当作单一 GitHub 仓库整体发布。GitHub 发布必须在选定的权威 checkout 中精确暂存目标 Skill。
不要替换系统 .system/skill-creator；把它作为结构和脚手架基线。
权威来源决策
先选来源，再写文件：
| 来源 | 适用条件 | 标准仓库 |
|---|---|---|
| 统一公开仓 | 通用、可复用、来源和许可证允许公开，且通过披露检查 | PANGKAIFENG/ai-product-manager-skills |
| 项目级 | 只服务单个仓库，依赖其架构、命令或领域约束 | 项目仓库内 .skillshare/skills 或约定目录 |
| 本地受限 | 包含客户数据、内部 URL、凭据、个人绝对路径或不可公开来源 | 受控本地目录；先去敏或拆分，不进入公开 catalog |
| 本地草稿 | 尚未通过验证或用户明确要求不发布 | 独立草稿目录，不进入正式分发 |
通用能力默认以统一公开仓为候选权威源，但公开性不确定时必须停在项目级或本地受限状态。公开发布前检查 secrets、内部 URL、客户数据、许可证和 provenance。不要从 Skillshare 聚合目录反推权威仓库；以 catalog、Git remote 和 Skill provenance 为准。
生命周期
| 动作 | 处理方式 |
|---|---|
| 新增 | 查重后选择来源，创建、验证、评审、合并，再分发 |
| 导入 | 记录来源和许可证，决定 new / merge / replace / reject |
| 更新 | 在权威仓库分支修改；skill-creator 负责行为优化，skill-reviewer 负责发布门禁 |
| 弃用 | 标记替代项和迁移说明，停止新绑定，保留旧引用 |
| 退役 | 停止维护和自动发布，保留墓碑记录与稳定 ID |
| 删除 | 先查引用和影响面，经明确批准后依次处理仓库、catalog、Skillshare 目标和 Multica 映射；必须有回滚方案 |
默认先弃用或退役，不直接删除。重命名按“新增稳定名称 + 弃用旧名称”处理，避免破坏引用。
Workflow
- 用一句话复述要沉淀的能力，并识别本次动作：新增、导入、合并、更新、弃用、退役或删除。
- 检查统一公开仓、用户指定项目和本地候选来源的 remote、默认分支、ahead/behind 和 dirty 状态。存在用户改动时使用独立 worktree，不清理或覆盖。
- 扫描相似 Skill。至少包含统一公开仓、Skillshare 聚合源、系统 Skills、当前项目和导入来源：
python3 <this-skill>/scripts/inspect_existing_skills.py \
--name "<candidate-name>" \
--description "<request summary>" \
--catalog-root /path/to/ai-product-manager-skills \
--root /path/to/current-project \
--import-root /path/to/imported/skills \
--fetch-catalog --json
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.
- agents/openai.yaml 258 B
- evals/evals.json 3.1 KB
- references/assetization-gate.md 2.9 KB
- references/creation-rubric.md 7.7 KB
- references/skill-template-standards.md 5.8 KB
- scripts/create_team_skill.py 7.5 KB runs code
- scripts/inspect_existing_skills.py 23 KB runs code
- tests/test_governance_contract.py 8.5 KB runs code
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.
- 12d ago First seen · 222 lines · 124 tokens per session scan C 945d76f496b4
team-skill-creator is a skill published in the GitHub repository PANGKAIFENG/ai-product-manager-skills (11 stars, last pushed 13d ago), licensed MIT. It adds 124 tokens to every session and 3,770 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
baoyu-comic
A tool for creating original educational comics that explain knowledge or ideas through multiple illustrated panels. It supports different art styles and tones and can create several comics in one batch.
baoyu-diagram
Create professional, dark-themed SVG diagrams of any type — architecture diagrams, flowcharts, sequence diagrams, structural diagrams, mind maps, timelines, illustrative/conceptual diagrams, and more. Use this skill whenever the user asks for any kind of technical or conceptual diagram, visualization of a system…
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…
agent-wiki
Incremental LLM-friendly wiki generator for Obsidian note vaults. Use when: (1) Building wiki from notes, (2) Ingesting notes to wiki, (3) Obsidian LLM wiki, (4) Incremental knowledge base management. Triggers: 'build wiki from notes', 'ingest notes to wiki', 'Obsidian LLM wiki', 'incremental knowledge base'.
sequential-think
Multi-step reasoning engine for complex analysis and systematic problem solving. Use when: (1) Complex debugging scenarios with multiple layers, (2) Architectural analysis and system design, (3) Problems requiring hypothesis testing and validation, (4) Multi-component failure investigation, (5) Performance bottleneck…