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 xiqin/loom --skill loom-writing-skillsgit clone --depth 1 https://github.com/xiqin/loomWrote 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/xiqin/loom/loom-writing-skills)<a href="https://agentmods.dev/skills/xiqin/loom/loom-writing-skills"><img src="https://agentmods.dev/badge/skills/xiqin/loom/loom-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/xiqin/loom/loom-writing-skills"><img src="https://agentmods.dev/badge/skills/xiqin/loom/loom-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 | $0.00046 | $0.00829 |
| Opus 5 | $0.00023 | $0.00415 |
| Sonnet 5 | $0.00009 | $0.00166 |
| Haiku 4.5 | $0.00005 | $0.00083 |
Grade A, and why
loom-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 11d 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.
What it actually says
编写新 Skill
Skill 文件结构
skills/
<skill-name>/
SKILL.md # 必需：skill 主文件
references/ # 可选：参考文件
*.md
scripts/ # 可选：可执行检查、生成器、转换器
assets/ # 可选：模板、prompt 片段、示例输入输出
evals/ # 可选：触发边界样例
SKILL.md 格式
---
name: loom-<skill-name>
description: >
简短描述。说明何时使用此 skill。
Use when: <触发条件描述>.
Trigger keywords: <关键词列表>.
---
# <Skill 标题>
## 触发条件
- 用户说 xxx 时触发
- 在 xxx 流程中自动触发
## 执行流程
### Step 1: ...
### Step 2: ...
## 约束
- 规则 1
- 规则 2
## 完成条件与下一步
完成后继续。
Frontmatter 字段
| 字段 | 必需 | 说明 |
|---|---|---|
| name | 是 | skill 名称，必须与目录名一致 |
| description | 是 | 简短描述，用于 Skill 工具选择 |
编写原则
| 正确做法 | 反模式 |
|---|---|
| 单一职责 | 一个 skill 做多件事 |
| 清晰触发条件 | 触发太宽或太窄 |
| 完整执行流程 | 步骤描述模糊 |
| 可中断、可链式 | 缺少完成条件或不串联 |
| 有必要的自检清单 | 输出质量不可验证 |
职责分层
- Router skill：只做入口分流、解释推荐路径和上下文策略；不得写流水线状态。
- Pipeline skill：选择、推进或调整流水线；只有这类 skill 可以持久化
dynamic_steps或推进pipeline.state.json。 - Execution skill：执行已确认阶段；不得自行扩大流程范围或跳过 gate。
- Review skill：findings 优先，先列问题和证据，再给摘要。
触发与上下文负载
description必须说明Use when:，并保持短而精确。- 写清楚触发条件和非触发条件，避免 model 在相邻场景误触发。
- 主
SKILL.md只放必须执行的步骤；长解释、示例、模板放references/或assets/。 - 每个步骤必须有可检查的完成标准，避免 agent 提前宣布完成。
去沉积检查
修改 skill 时逐段做 no-op test：如果删除某句话不会改变 agent 行为，就删除或移入 reference。
常见沉积信号：
- 同一规则在多个文件重复但措辞不同。
- skill 同时承担 router、pipeline、execution、review 多层职责。
- 长篇背景说明没有对应检查动作。
- 没有说明失败时该停下、降级还是请求用户确认。
参考与测试
详细的 references 结构、scripts/evals 写法、测试方法和常见反模式见 references/detailed-guide.md。
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.
- 11d ago First seen · 104 lines · 46 tokens per session scan A 96cb7b87c96d
loom-writing-skills is a skill published in the GitHub repository xiqin/loom (5 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 829 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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…