skill-smith

A skill for creating and improving instructions that teach an AI agent how to handle a specialized type of work.

In plain words
What is it for?
Use it to create a new agent skill, improve an existing SKILL.md file, design its workflow, or decide how supporting references and resources should be arranged.
Why use it?
It provides a structured way to gather examples, define rules, and organize a skill so its results are more consistent.

Skill for Claude CodeCodexCursor

Install

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.

agentmods
npx agentmods add skills/programmeranthony/expert-coding-harness/skill-smith
Any agent
npx skills add ProgrammerAnthony/Expert-Coding-Harness --skill skill-smith
Clone the repo
git clone --depth 1 https://github.com/ProgrammerAnthony/Expert-Coding-Harness

Made for: Claude Code, Codex, Cursor.

Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,775 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00085 $0.01775
Opus 5 $0.00043 $0.00888
Sonnet 5 $0.00017 $0.00355
Haiku 4.5 $0.00009 $0.00178

Measured 2d ago against content hash 0363930b9d97, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-smith 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 2d 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.

.cursor/skills/skill-smith/SKILL.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

技能铸造师

铁律:每一行内容都要对得起 token 消耗。不写 Claude 已经知道的东西,只写它不知道的领域知识、流程规范和决策框架。

什么是技能

技能是给 AI Agent 的"专项培训手册"——把它从通用助手变成领域专家。好的技能应该:

  • 提供 Claude 不具备的领域知识或流程约束
  • 让输出更一致、更可预测
  • 减少用户每次都要重复解释的上下文

工作流

Step 1:理解需求(必须完成,不可跳过)

至少收集 3 个具体的使用示例:

询问用户:
"请给我 3 个你会如何使用这个技能的具体例子,
包括你会说什么,以及你期望得到什么输出。"

没有 3 个具体例子,不进入下一步。

同时了解:

  • "现在没有这个技能时,你是怎么做的?"(理解 Gap)
  • "这个技能最重要的限制/铁律是什么?"
  • "输出格式有特殊要求吗?"

Step 2:架构规划

加载 references/architecture-guide.md,回答以下问题:

  1. 主文件 SKILL.md

    • 核心工作流是什么?(步骤清单)
    • 有哪些铁律(必须遵守的规则)?
    • 需要哪些用户确认门控?
  2. 参考文档 references/

    • 哪些内容是重型参考资料(检查清单、模板、规范)?
    • 按需加载哪些文档(在工作流的哪个步骤加载)?
    • 每个 reference 文件聚焦一个主题
  3. 资源文件 assets/(可选):

    • 用于输出但不用于推理的文件(图片、固定模板)

架构决策原则

  • SKILL.md 控制在 500 行以内
  • 超出 500 行的内容移到 references/
  • 每个 reference 文件聚焦单一主题

Step 3:编写 SKILL.md

3.1 Frontmatter(决定触发时机)

加载 references/description-guide.md

---
name: skill-name
description: "核心描述。触发词:[关键词 1]、[关键词 2]、[关键词 3]..."
---

描述要求

  • 前 50 字说明解决什么问题
  • 列出 10-20 个触发关键词(中英文都要包含)
  • 包含触发场景的动词(创建、分析、优化、生成...)
3.2 铁律(Iron Law)

在标题下方立即写出最重要的约束:

# 技能名称

铁律:[最重要的行为约束,用户最需要知道的一条规则]
3.3 工作流(核心内容)

加载 references/workflow-patterns.md

使用勾选清单格式,让 AI 可以追踪进度:

## 工作流

- [ ] 第一步:[描述](标注是否必须)
  - [子步骤 1]
  - [子步骤 2]
- [ ] 第二步:[描述]
  - 用户确认门控:[在继续前必须获得用户批准]

确认门控示例

**将以上内容展示给用户确认,批准后才继续。**
3.4 参考资源

文件末尾列出所有 references 及加载时机:

## 参考资源

- `references/checklist.md` — 在第 3 步加载,用于[目的]
- `references/template.md` — 在输出阶段加载,用于[目的]

Step 4:编写 References

每个 reference 文件:

  • 聚焦单一主题(不要"大杂烩")
  • 以表格、清单、代码示例为主(减少叙述性文字)
  • 文件名描述内容(security-checklist.md 而非 ref1.md

Step 5:质量检查

发布前检查清单

  • SKILL.md 是否 < 500 行?
  • 每段内容是否都对得起 token(删掉 Claude 已经知道的废话)?
  • description 是否包含了足够的触发关键词?
  • 铁律是否明确(最重要的约束)?
  • 工作流中是否有合适的用户确认门控?
  • 是否在第一步就要求了 3 个具体例子?
  • references 是否按需加载而非一次性全加载?
  • 是否有反模式清单(告诉 AI 不该做什么)?

Step 6:README.md

Read the full file on GitHub · 193 lines

Files

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.

Changes

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.

  1. 2d ago First seen · 193 lines · 85 tokens per session scan A 0363930b9d97

Subscribe to this mod's changes

skill-smith is a skill published in the GitHub repository ProgrammerAnthony/Expert-Coding-Harness (235 stars, last pushed 3mo ago), licensed MIT. It adds 85 tokens to every session and 1,775 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 2026-08-30.

Related

Other skills, from other repositories

article-writing

Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.

affaan-m/ECC · 57 tokens

a-evolve

Apply A-Evolve's agentic evolution methodology to improve AI agent performance across runs. Use when the user wants to diagnose agent failures, generate targeted skills from error patterns, evolve system prompts, or accumulate episodic knowledge. Works standalone or inside AutoResearchClaw pipelines. Triggers on…

aiming-lab/AutoResearchClaw · 100 tokens

hive.chart-creation-foundations

Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…

aden-hive/hive · 133 tokens

📝 任务完成后归档

重要提醒: 每次完成复杂调试或开发任务后,主动执行此流程! 将学到的经验归档为 skill,供以后参考。不要等用户提醒。.

Project-N-E-K-O/N.E.K.O · 49 tokens

deck-course-module

暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.

nexu-io/html-anything · 25 tokens

code-documenter

Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides.

zebbern/claude-code-guide · 39 tokens