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 agentmods add skills/uvwt/agentdock/skill-authoringnpx skills add uvwt/agentdock --skill skill-authoringgit clone --depth 1 https://github.com/uvwt/agentdockWhat 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 | $0.00046 | $0.03084 |
| Opus 5 | $0.00023 | $0.01542 |
| Sonnet 5 | $0.00009 | $0.00617 |
| Haiku 4.5 | $0.00005 | $0.00308 |
Grade A, and why
skill-authoring 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 2d 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 — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Authoring
用于创建或维护 AgentDock 第一方 Skill。Skill 的本体是模型可读取的说明文档；工具负责真实检查、编辑、命令执行、打包、安装和验证。
目标 Skill 应由两部分构成：
可移植核心契约
+
可选的宿主适配说明
移除 AgentDock 专属适配说明后，Skill 的业务流程、包内引用、环境变量契约和辅助脚本仍应完整可用。
何时使用
使用本 Skill 处理：
- 创建新的第一方 Skill；
- 修改、重构或升级现有 Skill；
- 调整触发描述、正文流程、引用资料或辅助脚本；
- 补充测试、示例、安全约束和可移植性检查；
- 递增版本并完成源码侧与当前激活版本验证。
不要使用本 Skill 处理第三方 Skill 的正式安全审查、真实凭据配置或已安装版本回滚。这些属于 skill-installation。
核心原则
- 先定义模型何时应该选择该 Skill，再写正文。
- Skill 只描述方法、边界和工具选择，不承担统一执行职责。
- Skill 核心契约必须与宿主无关；包内文件使用相对路径，环境由运行宿主注入。
- 简单 Skill 优先只有一份
SKILL.md；只有确有需要时才增加引用、脚本或测试。 - 修改正文、引用、脚本或行为后必须递增语义化版本。
- 同名同版本内容必须保持不可变。
- 环境值、设备状态和运行数据不得进入 Skill 包。
- 所有验证都要落到当前已安装并激活的版本，不能只看源码目录。
- 第一方 Skill 必须通过本 Skill 的
lint，不能只通过包安装校验。
完整规范见包内 references/skill-package-spec.md。
标准流程
1. 理解需求和触发条件
先明确：
- 用户真正要解决的问题；
- 模型在什么请求下应选择该 Skill；
- 哪些相邻任务不属于该 Skill；
- 需要调用哪些真实工具；
- 是否需要辅助脚本、引用资料或测试；
- 是否涉及网络、写入、删除、凭据或高风险动作。
不要用“管理某能力全生命周期”这类宽泛描述。description 必须让模型能稳定判断何时选中它。
2. 确定职责边界
正文至少说明：
- 适用场景和不适用场景；
- 读取或修改的对象；
- 默认只读行为；
- 写操作和破坏性操作的确认规则；
- 失败时需要返回的证据。
一个 Skill 应围绕一个稳定能力边界组织。需求已经跨越独立职责时，应拆成多个 Skill。
3. 创建源码目录
普通第一方和社区 Skill 默认放在独立的 agentdock-skills 仓库：
skills/<skill-name>/
只有随 AgentDock 安装包自举、与运行时版本强绑定的核心 Skill 才放在 AgentDock 主仓库：
core-skills/<skill-name>/
按需选择结构：
skills/<skill-name>/
└── SKILL.md
skills/<skill-name>/
├── SKILL.md
├── references/
├── scripts/
└── tests/
skills/<skill-name>/
├── SKILL.md
├── run.py
└── tests/
不要为了形式创建空目录，也不要把普通集成重新放回 AgentDock 主仓库。
4. 编写 Frontmatter
当前 AgentDock 正式解析：
---
name: example-skill
description: 清楚说明何时使用、解决什么问题
version: 1.0.0
---
要求：
name使用稳定、简短、全小写的连字符名称；description同时覆盖触发场景和能力边界；version使用语义化版本；- Frontmatter 后必须有非空 Markdown 正文；
- 不增加当前解析器未支持的环境变量或执行字段。
5. 编写可移植核心
目标 Skill 的正文和脚本默认只假设：
- 当前工作目录是 Skill 包根目录；
- 包内资源可通过相对路径访问；
- 环境变量来自当前进程环境；
- 运行宿主负责选择工具、切换目录和注入环境；
- 不依赖 AgentDock 的安装目录、状态目录或专属变量。
有根目录脚本时，通用执行示例应写成：
What ships with it
3 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.
- 2d ago First seen · 347 lines · 46 tokens per session scan A 153b67fcfba8
skill-authoring is a skill published in the GitHub repository uvwt/agentdock (440 stars, last pushed 2d ago), licensed Apache-2.0. It adds 46 tokens to every session and 3,084 once invoked, about $0.0002 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
discipline
Bulletproof agent operating protocol. 15 failure-prevention rules distilled from 120+ real sessions and 10 agent definitions. Covers fabrication, constraint tracking, verification, scoping, retry discipline, and communication. Load before any task to prevent the most common agent failure modes.
memory-curation
When you have read / processed a workspace asset in this session and learned something durable about it, write a memory page so future sessions benefit. Maintain the workspace wiki's hierarchical structure as it grows.
evolve-session-review
Automatically triggered by Stop hook. Reviews session for evolution learnings.
help-video-ingest
Extract help-center (ohjeet) articles from LIPAS YouTube tutorial videos using Gemini's native video understanding, consolidate them into task-sized help pages, translate to sv/en, and publish to the help CMS (which feeds the AI-assistant knowledge base). Use when turning tutorial videos or guide PDFs into ohjeet…
notion-knowledge-capture
Capture conversations and decisions into structured Notion pages; use when turning chats/notes into wiki entries, how-tos, decisions, or FAQs with proper linking.
prompt-miner
Rank past prompts by session outcome and mine the markers that produce the best sessions. Runs the deterministic mine-traces.mjs engine over Claude + Pi JSONL traces, scores each session by a friction + ground-truth outcome proxy, ranks the initiating prompts, then synthesizes falsifiable prompt markers STRATIFIED by…