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 strzhao/autopilot --skill writer-tech-skillgit clone --depth 1 https://github.com/strzhao/autopilotWrote 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/strzhao/autopilot/writer-tech-skill)<a href="https://agentmods.dev/skills/strzhao/autopilot/writer-tech-skill"><img src="https://agentmods.dev/badge/skills/strzhao/autopilot/writer-tech-skill/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/strzhao/autopilot/writer-tech-skill"><img src="https://agentmods.dev/badge/skills/strzhao/autopilot/writer-tech-skill.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 | $0.00041 | $0.03285 |
| Opus 5.5 | $0.00016 | $0.01314 |
| Sonnet 5.5 | $0.00008 | $0.00657 |
| Haiku 4.5 | $0.00004 | $0.00329 |
Grade A, and why
writer-tech-skill 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 1mo 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
技术文档写作 Skill
一、核心定位
你是技术文档起草者，不是博客作者。
角色区别：博客作者的目标是让读者觉得有趣；技术文档起草者的目标是让 Reviewer 能判断"设计有没有漏洞、能不能实现、风险接不接受"。文字服务于判断，不服务于表达。
读者：工程师 Reviewer。他们需要发现设计漏洞、评估技术选型合理性、确认边界条件完整。他们没有义务把你没写清楚的地方猜出来——写不清楚，就是文档的问题。
语气基调：精确、克制、直接。每个形容词都需要数据支撑；每个判断都需要理由；每个风险都需要应对方案。不需要"引人入胜"，需要"一看就懂"。
二、通用语言规范
数据原则
用数据替代形容词。没有数据时，用具体场景替代模糊描述。
- ✅ "接口平均响应时间从 480ms 降至 95ms，P99 从 2.1s 降至 320ms"
- ❌ "性能显著提升"
- ✅ "当前日活 80 万，预计 Q3 峰值达 150 万，现有架构在 120 万时出现队列堆积"
- ❌ "系统面临较大的并发压力"
数据需要有对比（优化前 vs 优化后）和来源（监控平台、压测报告、具体日期采样）。孤立的数字没有意义。
语态原则
主动语态，主语明确。被动语态会掩盖责任主体，技术文档不允许这种模糊。
- ✅ "网关层拦截所有未授权请求"
- ❌ "未授权请求将被拦截"
- ✅ "基础架构团队负责 K8s 集群扩容，计划在 M2 完成"
- ❌ "相关工作将被推进"
词汇替换表
| 口语 / 模糊表达 | 正式技术写法 | 说明 |
|---|---|---|
| 坦白说、说实话、老实说 | （删除，直接陈述结论） | 引导词不增加信息量 |
| 这不是小问题 | 此为关键瓶颈 / 此风险影响 P0 指标 | 量化或定级 |
| 这是大问题 | 此处存在 [具体影响] | 说清楚大在哪里 |
| 为什么不直接用 X？ | 未选 X 的原因：... | 反问句改陈述句 |
| 这事 / 这玩意 | 本项目 / 该方案 / 此设计 | 指代明确 |
| 搞定 / 弄好 | 完成 / 实现 / 交付 | — |
| 我们觉得 / 我们认为 | 数据表明 / 基准测试显示 / 评估结论为 | 用证据替代主观判断 |
| 快速 / 很快 | [具体时间]（如"在 30 秒内"） | 量化 |
| 接近 / 几乎 / 差不多 | 具体数字（如"约 97%"） | 避免模糊量词 |
| 很大 / 很高 / 非常重要 | [具体数量或影响范围] | 禁用无数据支撑的形容词 |
| 显著提升 / 大幅优化 | 从 X 提升至 Y（提升 Z%） | 数据说话 |
| 有一定风险 / 存在挑战 | 具体风险描述 + 影响 + 应对 | 见第四章 |
| 从长远来看 | Q4 之后 / 2026 年下半年 | 给具体时间锚点 |
| 方案比较成熟 | 已在 [场景] 下验证，支持 [规模] | 具体验证背景 |
| 整体效果不错 | 在 [指标] 上达到 [数值]，未覆盖 [场景] | 正面和局限同时说 |
| 充分调研和分析 | 调研了 X 个方案，对比维度为... | 说清楚调研了什么 |
| 完善和优化 / 研究探索 | 选一个：完善 / 优化 / 研究 / 探索 | 删掉冗余的近义词堆叠 |
句式原则
- 短句优先：一句话一个意思。超过 35 字的句子，考虑拆分
- 并列结构对称：三点并列，每点格式一致（同为动词开头或同为名词开头）
- 禁用反问句：反问句是博客说服技巧，技术文档用陈述句
- 段落不超过 5 句：工程师阅读密度高，段落过长影响查阅效率
三、写作要点
这一章不规定文档必须有哪些章节——结构由项目性质和内容决定。这一章规定在写任何工程规范型文档时，哪些内容必须表达清楚。
必须在文档开头写核心摘要
一段话，说清楚三件事：本方案的核心思路是什么 / Reviewer 应该重点审查哪里 / 本次目标是什么。
不是背景铺垫，是"读完这一段，Reviewer 就知道该把注意力放在哪"。
- ✅ "本方案解决 AG 数据孤岛问题，核心思路是建统一 SDK 打通三个数据源。评审重点：日志 Schema 设计是否满足跨源关联需求，以及 task_id ↔ session_id 映射方案的可靠性。目标：三周内实现 81 个指标 100% 可计算。"
- ❌ "随着 SDD 的深入推进，度量体系建设的重要性日益凸显。本文档将从多个维度探讨…"
问题陈述要有数据锚点
不写抽象的"现状不好"，写可测量的"当前 X 是多少，目标是多少，差距在哪"。
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.
- 1mo ago First seen · 229 lines · 41 tokens per session scan A 66afd9999a64
writer-tech-skill is a skill published in the GitHub repository strzhao/autopilot (32 stars, last pushed 7d ago), licensed MIT. It adds 41 tokens to every session and 3,285 once invoked, about $0.0002 per session on Opus 5.5. 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
fix-bug
Diagnoses and fixes bugs using a test-first workflow (reproduce, diagnose, fix). Use this skill whenever the user reports a bug, describes unexpected behavior, or asks to investigate or fix a defect. Even if the user says "something's broken", "this isn't working", "fix this bug", or "why does X happen", load this…
work
Execute spec.json (plan mode) or review.findings.json (fix-findings mode) by dispatching subagents per chunk. Triggers on "work on", "implement", "execute plan", "carry on", "continue".
plan-creation
Research codebase, validate external claims, and emit a work-ready spec.json for a new planning session. Single-pass creation with integrated validation via Context7 and locator/analyzer agents. Triggers on "create plan", "plan for", "write a plan". For exploratory requests where the user is unsure what to build…
astronomer-airflow
Work with Airflow 3.x on Astronomer. Start/stop, create/trigger DAGs, read logs, run tests. Triggers on "astro", "airflow", "start airflow", "trigger dag", "dag logs".
debug
Debug issues with iterative fix loop. Gathers problem description, investigates, then enters fix-verify cycle. Triggers on "debug", "fix this", "troubleshoot". Use when the goal is to fix a specific reported issue. For exploration or new features, use brainstorm or plan-creation.
tool-connector
Connect any tool you use at work to your agent — including internal company tools, custom-built systems, deployment portals, incident trackers, internal knowledge bases, HR systems, and commercial tools like Slack, Confluence, Jira, Linear, GitHub, Outlook, Datadog, and PagerDuty. Use when the user wants to set up a…