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/Leodorareluctant259/superpowers-zhnpx agentmods add skills/leodorareluctant259/superpowers-zh/writing-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/leodorareluctant259/superpowers-zh/writing-skills)<a href="https://agentmods.dev/skills/leodorareluctant259/superpowers-zh/writing-skills"><img src="https://agentmods.dev/badge/skills/leodorareluctant259/superpowers-zh/writing-skills/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/leodorareluctant259/superpowers-zh/writing-skills"><img src="https://agentmods.dev/badge/skills/leodorareluctant259/superpowers-zh/writing-skills.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 | $0.00023 | $0.06085 |
| Opus 5 | $0.00012 | $0.03043 |
| Sonnet 5 | $0.00005 | $0.01217 |
| Haiku 4.5 | $0.00002 | $0.00609 |
Grade A, and why
writing-skills 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 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.
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 writing-skills — 0 lines 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 — 655 lines — stays where its author put it; the contents beside it link to each section on GitHub.
编写技能
概述
编写技能就是将测试驱动开发应用于流程文档。
个人技能存放在智能体特定的目录中（Claude Code 用 ~/.claude/skills，Codex 用 ~/.agents/skills/）
你编写测试用例（带子智能体的压力场景），观察它们失败（基线行为），编写技能（文档），观察测试通过（智能体遵守规则），然后重构（堵住漏洞）。
核心原则： 如果你没有观察到智能体在没有该技能时失败，你就不知道这个技能是否教了正确的东西。
必需背景： 在使用此技能前，你必须理解 superpowers:test-driven-development。该技能定义了基本的红-绿-重构循环。本技能将 TDD 适配到文档编写中。
官方指南： Anthropic 官方的技能编写最佳实践请参见 anthropic-best-practices.md。该文档提供了补充本技能 TDD 导向方法的额外模式和指南。
什么是技能？
技能是经过验证的技术、模式或工具的参考指南。技能帮助未来的 Claude 实例找到并应用有效的方法。
技能是： 可复用的技术、模式、工具、参考指南
技能不是： 关于你某次如何解决问题的叙事
TDD 映射到技能
| TDD 概念 | 技能创建 |
|---|---|
| 测试用例 | 带子智能体的压力场景 |
| 生产代码 | 技能文档（SKILL.md） |
| 测试失败（红） | 智能体在没有技能时违反规则（基线） |
| 测试通过（绿） | 智能体在有技能时遵守规则 |
| 重构 | 在保持合规的同时堵住漏洞 |
| 先写测试 | 在编写技能之前先运行基线场景 |
| 观察失败 | 记录智能体使用的确切合理化借口 |
| 最小代码 | 编写针对那些具体违规行为的技能 |
| 观察通过 | 验证智能体现在遵守规则 |
| 重构循环 | 发现新的合理化借口 → 堵住 → 重新验证 |
整个技能创建过程遵循红-绿-重构。
何时创建技能
创建条件：
- 技术对你来说不是直觉上显而易见的
- 你会在不同项目中反复引用
- 模式具有广泛适用性（非项目特定）
- 其他人也会受益
不要创建：
- 一次性解决方案
- 其他地方有充分文档的标准实践
- 项目特定的约定（放在 CLAUDE.md 中）
- 机械性约束（如果可以用正则/验证强制执行，就自动化——文档留给需要判断的场景）
技能类型
技术类
有具体步骤的方法（condition-based-waiting、root-cause-tracing）
模式类
思考问题的方式（flatten-with-flags、test-invariants）
参考类
API 文档、语法指南、工具文档（office docs）
目录结构
skills/
skill-name/
SKILL.md # 主参考文档（必需）
supporting-file.* # 仅在需要时
扁平命名空间 - 所有技能在一个可搜索的命名空间中
分离文件的情况：
- 大量参考内容（100+ 行）- API 文档、全面的语法说明
- 可复用工具 - 脚本、实用程序、模板
保持内联：
- 原则和概念
- 代码模式（< 50 行）
- 其他所有内容
SKILL.md 结构
Frontmatter（YAML）：
- 两个必需字段：
name和description（完整支持字段参见 agentskills.io/specification） - 总计最多 1024 字符
name：只使用字母、数字和连字符（不要用括号、特殊字符）description：第三人称，仅描述何时使用（不是做什么）- 以"Use when..."开头，聚焦于触发条件
- 包含具体的症状、场景和上下文
- 绝不总结技能的流程或工作流（参见 CSO 章节了解原因）
- 尽量控制在 500 字符以内
---
name: Skill-Name-With-Hyphens
description: Use when [具体的触发条件和症状]
---
# 技能名称
## 概述
这是什么？用 1-2 句话说明核心原则。
## 何时使用
[如果决策不明显，使用小型内联流程图]
症状和用例的要点列表
不适用的场景
## 核心模式（技术/模式类）
前后代码对比
## 快速参考
用于快速浏览常见操作的表格或要点
## 实现
简单模式内联代码
大量参考或可复用工具链接到文件
## 常见错误
常见问题 + 修复方法
## 实际效果（可选）
具体结果
What ships with it
6 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.
- 12d ago First seen · 655 lines · 23 tokens per session scan A 0d1d2f84c062
writing-skills is a skill published in the GitHub repository Leodorareluctant259/superpowers-zh (5 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 6,085 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to writing-skills, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
ainb-fleet:daemons
Runtime-health view of the four fleet daemons — phone bridge, notifyd, ATC, and the fleet auto-continue daemon — in one table. Each row reports state (running / stopped / unknown), pid, uptime, last activity, error count, and a HEALTH reason that distinguishes a clean stop from a crash (stale heartbeat) or a…
ainb-fleet:bridge
Native phone bridge — relay messages two-way between a chat channel (Telegram, Slack, and/or Discord) and your ainb sessions. Inbound chat messages route to a target session (by name: prefix, else a conductor- first default) and are delivered via tmux send-keys; the session's reply is captured from its JSONL…
ainb-fleet
Fleet orchestration overview — the ainb fleet ... Rust subcommand namespace for driving every claude session on the host. Routes to the sub-skills (ainb-spawn / standup / broadcast / sequence / needs / daemon / atc). Invoke this for an at-a-glance map of what fleet can do; reach for the specific sub-skill for the verb…
ainb-fleet:daemon
Long-running watcher that scans every claude session every 5s and auto-sends continue to any session whose recent tmux pane buffer matches a known API-error regex (ratelimited, overloadederror, internalservererror, requesttimeout, sockethangup, fetchfailed, ECONNRESET). Use this when you want unattended recovery from…
ainb-fleet:standup
Show fleet status — every claude session running on the host, merged across ainb + claude-peers broker + background jobs. Use when you need to enumerate sessions before composing an action, check the summary of each session, or pipe the list into jq for filtering. (Writes go via tmux by default; a peerid is just an…
ainb-fleet:cost
Show fleet spend — per-session, per-model, per-day, and per-group USD cost rollups for every claude/codex session, sourced live from ainb's burndown analytics (which already prices every provider call). Use when you need spend visibility across a multi-session fleet, want to find the most expensive session/model, or…