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/redfox-data/redfox-community-dsh/optimize-skill-mdnpx skills add redfox-data/redfox-community-dsh --skill optimize-skill-mdgit clone --depth 1 https://github.com/redfox-data/redfox-community-dshWrote 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/redfox-data/redfox-community-dsh/optimize-skill-md)<a href="https://agentmods.dev/skills/redfox-data/redfox-community-dsh/optimize-skill-md"><img src="https://agentmods.dev/badge/skills/redfox-data/redfox-community-dsh/optimize-skill-md.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 | $0.00085 | $0.02258 |
| Opus 5 | $0.00043 | $0.01129 |
| Sonnet 5 | $0.00017 | $0.00452 |
| Haiku 4.5 | $0.00009 | $0.00226 |
Grade A, and why
optimize-skill-md 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 6d 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skillmd Optimize
📝 简介
对照 标准书写格式 对目标 SKILL.md 进行全面优化：修复 YAML 描述、重组章节结构、精简冗余内容、统一术语格式。
✨ 功能特性
| 功能模块 | 能力描述 | 核心价值 |
|---|---|---|
| YAML 修复 | 第三人称 + WHAT + WHEN + 触发词 | 提升 Agent 匹出准确率 |
| 章节重组 | 合并/拆分/删除空壳章节 | 结构清晰易读 |
| 冗余精简 | 删除科普/重复/修饰词 | 降低 token 开销 |
| 格式统一 | 术语/代码块/路径规范 | 全文一致性 |
| 渐进重构 | 超 500 行外移至 references/ |
主体精简可控 |
| 开头规范 | 强制简介 + 功能特性表格 | 一眼定位能力边界 |
硬约束
- 仅改 SKILL.md：不修改
README.md、scripts/、references/等其他文件 - 保留原有逻辑：不改变 Skill 的功能行为，仅优化表达
- 保持引用路径：不改动文件间的引用关系
- 强制开头章节：每个 SKILL.md 必须以「📝 简介」和「✨ 功能特性」章节开头
优化流程
Step 1: 读取并分析
- 读取目标
SKILL.md - 读取 standard-format.md
- 按以下维度逐项评估，标记问题点：
| 维度 | 检查要点 |
|---|---|
| YAML 描述 | 是否第三人称？包含 WHAT + WHEN？有触发词？≤ 1024 字符？ |
| 章节结构 | 一级标题是否清晰？章节划分合理？有冗余/缺失章节？有空壳章节？开头是否有简介和功能特性？ |
| 内容简洁度 | 存在冗余解释？基础知识科普？重复说明？过长示例（3+）？ |
| 格式规范 | 术语统一？表格标准？代码块标注语言？路径正斜杠？ |
| 渐进披露 | 主体 ≤ 500 行？详细信息在外移？引用一级深度？ |
| 反模式 | Windows 路径？时间敏感信息？多个等价选项？ |
Step 2: 应用优化（按优先级）
P1: 修复 YAML 描述
# ❌ 优化前
description: 处理文件
# ✅ 优化后
description: 从 PDF 文件中提取文本和表格，支持合并和表单填写。当用户处理 PDF 文件或提及 PDF、表单、文档提取时使用。
规则：
- 第三人称描述功能
当用户...时使用句式标注触发场景- 末尾追加
触发词：xxx、xxx - 总长 ≤ 1024 字符
P2: 重组章节结构
-
强制：SKILL.md 开头必须包含
## 📝 简介（2-3 句话说明核心功能）和## ✨ 功能特性（三列表格：功能模块 | 能力描述 | 核心价值）两个章节，位于一级标题之后、其他章节之前 -
若原文
## 概述/## 产品概述存在，将其重命名为## 📝 简介，内容精简为 2-3 句话 -
若原文无功能特性章节，从 YAML description、交互流程、输出格式中提炼 4-6 条功能要点，以表格形式呈现（功能模块 | 能力描述 | 核心价值）
-
确保一级标题
# XXX精确描述核心功能 -
合并内容 < 5 行的短章节
-
拆分 > 50 行的长章节
-
删除空壳章节（有标题无实质内容）
-
删除属于 README 的用户向章节（一键安装、使用场景、项目架构、常见问答）
-
为关键章节添加 emoji 前缀（
## 📊 输出格式、## ⚠️ 注意事项）
P3: 精简冗余内容
删除以下类型内容：
- 基础知识科普（"JSON 是一种数据格式..."）
- 重复说明（同一规则在多处出现）
- 冗余修饰词（"请注意"、"需要特别说明的是"、"众所周知"）
- 第 3 个及以上的相似示例（保留 1-2 个即可）
P4: 统一格式
- 术语统一：全文选定一个术语，替换所有变体（如 "API 接口" 替换 "URL"、"端点"、"路由"）
- 代码块标注：所有代码块添加语言类型（```bash、```json、```markdown）
- 路径正斜杠：
scripts/search.py而非scripts\search.py - 表格对齐：表头与分隔符对齐
What ships with it
4 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.
- 6d ago First seen · 195 lines · 85 tokens per session scan A 4fe85c028bf6
optimize-skill-md is a skill published in the GitHub repository redfox-data/redfox-community-dsh (5 stars, last pushed 4d ago), licensed MIT. It adds 85 tokens to every session and 2,258 once invoked, about $0.0004 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
dsh-hooks-authoring
编写或调试已安装的 dsh-hooks-plugin 的 hook 脚本。配置在 /.dsh/hooks.json，事件挂 PreToolUse/PostToolUse/UserPromptSubmit/SessionStart 等；命令从 toolinput.command 读，决策只能通过 stdout JSON 表达（permissionDecision deny/ask/allow），退出码不 gate，hookEventName 必须回填，Windows 上 command 由 PowerShell 解释且可能被沙箱拦外部 exe。.
web-artifact-designer
把视觉/前端设计需求做成可直接在浏览器打开的自包含 HTML 或 SVG 设计稿——海报、信息图、落地页、数据图表、卡片、banner、UI 组件稿、单页应用原型等。When the user asks for a visual design, poster, infographic, landing page, chart, mockup, or complains that existing frontend output looks generic/ugly, use this skill to produce a polished, self-contained HTML/SVG artifact instead of a…
dsh-sdk-upgrade
Safely select and install a compatible official @deepseek-ai SDK release for dsh plugin projects (dsh-web, dsh-trading, and similar monorepos) from npm using an isolated worktree, explicit cohort review, CI-equivalent validation, and controlled rollout — including syncing the project's declared DSH host-version floor…
dsh-web-pet-developer
Create a pet for the dsh-pet plugin and integrate it into the dsh web GUI — author a v2 pet.json manifest plus an 8-column x 9-row atlas per the Codex/hatch-pet contract (live2d pets, voice packs and status decorations included), drop it into the pet-center user directory or contribute it as a built-in asset under…
company-research-method
本技能规范一次公司研究的流程与纪律，产出每个数字都能标注来源文件与行号的公司速览卡。合规底线：仅供研究，不构成投资建议；不接付费/需登录数据源（企查查、Wind 等留给用户自行导出后作为 dataFiles 传入）。.
dsh-plugin-guide
Use when developing, reviewing, packaging, debugging, or answering questions about DeepSeek Harness (DSH) plugins — the plugin-based agent harness on vendored Cordis. Applies the official plugin-development constraints (plugin contract, cordis.yml layers, services/events/effects, tool DSL, bundles/profiles) backed by…