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 233i/agent-skills --skill using-agent-skillsgit clone --depth 1 https://github.com/233i/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/233i/agent-skills/using-agent-skills)<a href="https://agentmods.dev/skills/233i/agent-skills/using-agent-skills"><img src="https://agentmods.dev/badge/skills/233i/agent-skills/using-agent-skills.svg" alt="Measured on agentmods" 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 | $0.00045 | $0.02117 |
| Opus 5 | $0.00023 | $0.01059 |
| Sonnet 5 | $0.00009 | $0.00423 |
| Haiku 4.5 | $0.00005 | $0.00212 |
Grade A, and why
using-agent-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 8d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
使用 Agent Skills
概览
Agent Skills 是一组按开发阶段组织的工程工作流技能集合。每个 skill 都编码了一套资深工程师会遵循的具体流程。这个元技能帮助你为当前任务找到并应用合适的 skill。
技能发现
当一个任务到来时,先判断它处于哪个开发阶段,再应用对应的 skill:
任务到来
│
├── 想法模糊 / 需要细化? ───────→ idea-refine
├── 新项目 / 新功能 / 新改动? ─→ spec-driven-development
├── 已有 spec,需要拆任务? ───→ planning-and-task-breakdown
├── 正在实现代码? ────────────→ incremental-implementation
│ ├── UI 工作? ────────────→ frontend-ui-engineering
│ ├── API 工作? ───────────→ api-and-interface-design
│ └── 需要更好的上下文? ───→ context-engineering
├── 正在写 / 跑测试? ─────────→ test-driven-development
│ └── 浏览器相关? ─────────→ browser-testing-with-devtools
├── 出故障了? ───────────────→ debugging-and-error-recovery
├── 正在做代码评审? ─────────→ code-review-and-quality
│ ├── 有安全顾虑? ─────────→ security-and-hardening
│ └── 有性能顾虑? ─────────→ performance-optimization
├── 正在提交 / 建分支? ───────→ git-workflow-and-versioning
├── CI/CD 流水线工作? ───────→ ci-cd-and-automation
├── 写文档 / ADR? ───────────→ documentation-and-adrs
└── 准备部署 / 发布? ─────────→ shipping-and-launch
核心操作行为
这些行为始终适用,跨所有 skill 生效,而且不可妥协。
1. 明确暴露假设
在实现任何稍微复杂的事情之前,先明确写出你的假设:
我当前的假设:
1. [关于需求的假设]
2. [关于架构的假设]
3. [关于范围的假设]
→ 如果不对请现在纠正,否则我会按这些继续。
不要悄悄补全有歧义的需求。最常见的失败模式,就是基于错误假设一路做下去却没人发现。越早暴露不确定性,返工成本越低。
2. 主动处理困惑
当你遇到不一致、互相冲突的需求,或说明不清晰时:
- 停下。 不要靠猜继续。
- 点名具体困惑点。
- 说明权衡,或提出澄清问题。
- 等待问题被解决后再继续。
坏例子: 默默选一个理解然后赌它是对的。
好例子: “我在 spec 里看到 X,但现有代码是 Y。请问哪个优先?”
3. 该反驳时就反驳
你不是一个只会点头的机器。当某种做法有明显问题时:
- 直接指出问题
- 解释具体代价,最好量化,例如“这会额外增加约 200ms 延迟”,而不是“这可能会更慢”
- 提出替代方案
- 如果人类在充分了解信息后仍然坚持,就接受这个决定
一味迎合是一种失败模式。面对糟糕方案说一句“当然可以!”然后照做,对谁都没有帮助。真诚的技术分歧,比虚假的赞同更有价值。
4. 强制保持简单
你天然会倾向于把事情做复杂。要主动抵抗这种冲动。
在完成任何实现前,都问自己:
- 能不能用更少的代码完成?
- 这些抽象真的值回它们的复杂度吗?
- 一个资深工程师看到后,会不会问“你为什么不直接……?”
如果你写了 1000 行,而 100 行就够,那就是失败。优先选择平实、明显的方案。聪明过头的代码很贵。
5. 严守范围边界
只改你被要求改的东西。
不要:
- 删除你看不懂的注释
- 顺手“清理”与任务无关的代码
- 借机重构相邻系统
- 未经明确批准删除“看起来没用”的代码
- 因为“感觉会有用”就擅自加功能
你的工作应该像外科手术一样精准,而不是未经请求的装修翻新。
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.
- 8d ago First seen · 173 lines · 45 tokens per session scan A c0fc3de0b003
using-agent-skills is a skill published in the GitHub repository 233i/agent-skills (6 stars, last pushed 5mo ago), licensed MIT. It adds 45 tokens to every session and 2,117 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…