using-skills
Invoke before responding to any non-trivial task—enforces the 1% rule that if any skill has even a 1% chance of improving output, it must be invoked first.
- Installs
- 40
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/joellewis/skill-library --skill using-skills- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads using-skills automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Overview
This skill enforces the discipline of skill invocation, preventing the agent from shortcutting workflows or rationalizing its way out of using available frameworks. It is the core defensive mechanism against AI overconfidence and drift.
Iron Law
IF THERE IS EVEN A 1% CHANCE A SKILL APPLIES, INVOKE IT
AI models are biased toward immediate generation over reference-checking. This rule forces a "pause and check" behavior that prevents low-quality, ungrounded output.
State Machine
digraph using_skills_flow {
"Task Received" [shape=doublecircle];
"Step 1: Check Skill Database" [shape=box];
"Decision: Is it ≥ 1%?" [shape=diamond];
"Step 2: Propose Skill to User" [shape=box];
"Step 3: Apply Skill Logic" [shape=box];
"Done" [shape=doublecircle];
"Task Received" -> "Step 1: Check Skill Database";
"Step 1: Check Skill Database" -> "Decision: Is it ≥ 1%?";
"Decision: Is it ≥ 1%?" -> "Step 2: Propose Skill to User" [label="yes"];
"Decision: Is it ≥ 1%?" -> "Done" [label="no"];
"Step 2: Propose Skill to User" -> "Step 3: Apply Skill Logic";
"Step 3: Apply Skill Logic" -> "Done";
}
When to Use This Skill
- Whenever a new request is received.
- When an ongoing project shifts into a new phase (e.g., from Analysis to Deliverable).
- When you find yourself "guessing" the right approach.
When NOT to Use This Skill
- Simple, factual lookups with no strategic or creative component.
- Basic conversational chitchat.
Core Process
Step 1: Scan for Applicable Skills
Check the taxonomy of 41 skills across 6 families. Do not rely on memory; use the taxonomy to identify potential matches. (Source: system design)
Step 2: Apply the 1% Rule
Ask: "Is there even a 1% chance that [skill-name] would improve the outcome of this task?" If yes, it is mandatory to mention it. (Source: system design)
Step 3: Present Options to User
State clearly which skills apply and what value they add. Do not make the decision for the user; present it as a professional recommendation. (Source: system design)
Step 4: Execute with Full Rigor
Once a skill is selected, you MUST follow its state machine and iron laws without exception. (Source: system design)
Cross-Skill Invocations
REQUIRED SUB-SKILL: getting-started — for initial session context. RECOMMENDED SUB-SKILL: prompt-optimizer — to refine the invocation of other skills.
Rationalization Table
| Thought | Reality |
|---|---|
| "The user didn't ask for a skill, so I won't use one." | The user may not know which skills are available. It is your job to recommend them. |
| "This task is slightly different from the skill description." | Use the 1% rule; even a partial match provides better structure than no structure. |
| "I've already used three skills, adding another will be too complex." | Complexity is often exactly what a complex problem needs. |
| "I can just apply the principles of the skill without formally invoking it." | Formal invocation is the only way to ensure the state machine and iron laws are followed. |
Red Flags
These thoughts mean STOP — you are about to shortcut:
- "I'll just handle this one manually" → You are avoiding the 1% rule.
- "This skill is overkill for this small request" → Small requests are where frameworks catch the most hidden errors.
- "I don't have the sources for that skill handy" → You should use the extraction methodology to find them.
Diagnostic Checklist
- Have I checked the full list of 41 skills for this task?
- Did I apply the 1% rule correctly?
- Have I explained the "why" behind the recommended skill(s)?
- Am I following the state machine of the invoked skill?
- Did I resist the urge to "wing it"?
Sources
- System design — The 1% Rule.
- System design — Rationalization Defense.
- System design — Iron Law Registry.
FAQ
What does the using-skills skill do?
Invoke before responding to any non-trivial task—enforces the 1% rule that if any skill has even a 1% chance of improving output, it must be invoked first.
How do I install using-skills?
Run npx skills add https://github.com/joellewis/skill-library --skill using-skills in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/using-skills/ (personal) or .claude/skills/using-skills/ (project).
Which AI agents can use using-skills?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is using-skills safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains using-skills?
It is published by joellewis in joellewis/skill-library. It has 40 recorded installs.
More from joellewis/skill-library
fiction-architect
joellewis/skill-library
Open the skill to read its SKILL.md instructions.
world-building-logic
joellewis/skill-library
Open the skill to read its SKILL.md instructions.
character-vulnerability
joellewis/skill-library
Open the skill to read its SKILL.md instructions.
problem-framing
joellewis/skill-library
Use when beginning analytical or strategic tasks, facing undefined problems, or facing analysis paralysis—requires explicit problem definition before proceeding.
Popular productivity & automation skills
agent-browser
vercel-labs/agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
lark-doc
open.feishu.cn
飞书云文档（Docx / Wiki）内容操作：读取、创建、编辑文档，插入或下载图片附件，以及操作思维笔记。用户提供文档 URL/token（包括 doubao.com 的 /docx/、/wiki/）时使用；按 URL 路径/token 而非域名路由；/page/ 是妙搭应用，非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive；随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。
lark-base
open.feishu.cn
飞书多维表格（Base）操作：建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式（BaseApp/AppMode 页面与组件）、Workspace 目录、workflow、角色权限、模板中心（多维表格模板分类/列表/搜索）；遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps；文件导入/导出转 lark-drive，认证/授权转 lark-shared。
lark-drive
open.feishu.cn
飞书云空间（云盘/云存储）：管理 Drive 文件和文件夹，包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签（secure labels）和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题，或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用；doubao.com 云空间 URL/token 也按资源路径和 token 路由，不回退 WebFetch。不负责：文档内容编辑（走 lark-doc）、表格/Base 表内数据操作（走 lark-sheets/lark-base）、知识空间节点/成员管理（走 lark-wiki）、原生 Markdown 文件读写/patch/diff（走 lark-markdown）。
lark-shared
open.feishu.cn
Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.
lark-im
open.feishu.cn
飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片（Interactive Card）、监听卡片按钮回调（card.action.trigger）。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶（添加/移除/查询置顶会话）、管理标签数据、处理卡片回调时使用。