
getting-started
Use at the start of any session or when a task has no clear skill assignment—routes the request to the correct skill family and establishes workflow chain context.
- Installs
- 41
- 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 getting-started- 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 getting-started 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 bootstraps the session, identifying the user's domain, routing to the correct skill family, and establishing the workflow context. It prevents "unstructured thinking" by ensuring every task is approached with the appropriate skill framework.
Iron Law
NO RESPONSE TO A TASK WITHOUT CHECKING FOR APPLICABLE SKILLS FIRST
Jumping directly into a task without identifying the relevant skill framework results in generic, unverified, and low-value output.
State Machine
digraph getting_started_flow {
"Start" [shape=doublecircle];
"Step 1: Identify Domain" [shape=box];
"Step 2: Check Skill Taxonomy" [shape=box];
"Step 3: Establish Workflow Chain" [shape=box];
"Gate: Skill Applicable?" [shape=diamond];
"Step 4: Invoke Skill(s)" [shape=box];
"Ready" [shape=doublecircle];
"Start" -> "Step 1: Identify Domain";
"Step 1: Identify Domain" -> "Step 2: Check Skill Taxonomy";
"Step 2: Check Skill Taxonomy" -> "Gate: Skill Applicable?";
"Gate: Skill Applicable?" -> "Step 3: Establish Workflow Chain" [label="yes"];
"Gate: Skill Applicable?" -> "Ready" [label="no"];
"Step 3: Establish Workflow Chain" -> "Step 4: Invoke Skill(s)";
"Step 4: Invoke Skill(s)" -> "Ready";
}
When to Use This Skill
- Start of a new chat session.
- When the user introduces a new project or topic.
- When you are unsure how to approach a request.
When NOT to Use This Skill
- During an ongoing task that already has a skill invoked.
- Simple, one-off clarifications.
Core Process
Step 1: Identify Domain
Ask yourself: Is this request strategic, analytical, narrative, rhetorical, or interpersonal? (Source: system design)
Step 2: Check Skill Taxonomy
Consult the 6 families and 41 skills below. Use the 1% rule: if there is even a 1% chance a skill applies, you MUST mention it.
The 6 Skill Families
meta (6 skills) — Foundation & process enforcement
getting-started— Session bootstrap & routing (you are here)using-skills— Skill invocation discipline & 1% rule enforcementwriting-skills— TDD for documentation & skill authoringprompt-optimizer— Structured prompt refinement methodologymental-model-library— Cross-domain reasoning referencelearning-accelerator— Meta-learning & knowledge synthesis
workflow (12 skills) — Strategic & analytical workflows
problem-framing— Discovery gate & problem definitionstakeholder-discovery— Audience & stakeholder mappingmarket-context— Competitive landscape contextcompetitive-analysis— Structured competitor teardownbuyer-persona— JTBD-driven persona builderbusiness-case— ROI & investment thesisprd-writing— Product requirements (PR/FAQ method)pitch-deck— Investor & internal pitchone-pager— Executive summary documentexecutive-briefing— Board-level communicationassumption-audit— Evidence validation gatestakeholder-review— Structured feedback collection
executive (9 skills) — Leadership & decision-making
strategy-clarity— Strategic positioning & competitive advantagedevils-advocate— Adversarial stress testingoperational-excellence— Execution systems & OKRsplatform-strategist— Platform vs aggregator analysisownership-coach— Leadership accountabilityfirst-90-days— New role transition playbookhiring-talent— Talent assessment & recruitmentteam-builder— Culture & psychological safetydecision-frameworks— Structured decision methodology
narrative (4 skills) — Storytelling & creative writing
fiction-architect— Plot structure & causalitycharacter-vulnerability— Character depth testingworld-building-logic— Internal consistency enginedialogue-craft— Voice & subtext
rhetorician (5 skills) — Communication & persuasion
non-fiction-precision— Structural claritycopy-editor— Line-level prose qualityresonance-engine— Emotional & persuasive impactmemo-stress-tester— Business writing stress testscientific-advertising— Evidence-based persuasion
dealmaker (5 skills) — Negotiation & influence
negotiation-tactician— Deal & contract negotiationinfluence-architect— Persuasion & power dynamicsrapport-builder— Relationship & trust buildingfeedback-coach— Giving & receiving feedbackdifficult-conversations— High-stakes dialogue
Step 3: Establish Workflow Chain
If the task is strategic or analytical, determine which phase of the workflow chain (Discovery, Analysis, Deliverable, Review) applies. (Source: system design)
Step 4: Invoke Skill(s)
Confirm the relevant skills with the user and request permission to proceed using those frameworks. (Source: system design)
Cross-Skill Invocations
REQUIRED SUB-SKILL: using-skills — to enforce invocation discipline. RECOMMENDED SUB-SKILL: problem-framing — to begin the Discovery phase.
Rationalization Table
| Thought | Reality |
|---|---|
| "The user just asked a simple question, I don't need to check skills." | Simple questions are often the tip of a complex strategic iceberg. |
| "Checking skills will slow down the conversation." | Spending 10 seconds to find the right skill saves 10 minutes of rework. |
| "I already know how to handle this without a skill." | You are falling into confirmation bias; the skills are there to catch what you missed. |
| "None of the skills seem to perfectly match." | Use the closest skill or combine multiple skills rather than using none. |
Red Flags
These thoughts mean STOP — you are about to shortcut:
- "I'll just answer this first and then see about skills later" → This violates the Iron Law.
- "I'm sure no skill applies here" → You probably haven't looked at the taxonomy lately.
- "This task is too urgent for bootstrapping" → Urgency increases the risk of error, making bootstrapping more important.
Diagnostic Checklist
- Have I identified the user's primary domain?
- Have I checked all 6 families for applicable skills?
- Have I informed the user which skills I am invoking?
- Does the proposed plan follow the workflow chain (if applicable)?
- Have I confirmed there are no hidden prerequisites (e.g., stakeholder mapping before PRD)?
Sources
- System design — Skill Family Directory.
- System design — Workflow Chain Architecture.
- System design — Iron Laws.
FAQ
What does the getting-started skill do?
Use at the start of any session or when a task has no clear skill assignment—routes the request to the correct skill family and establishes workflow chain context.
How do I install getting-started?
Run npx skills add https://github.com/joellewis/skill-library --skill getting-started 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/getting-started/ (personal) or .claude/skills/getting-started/ (project).
Which AI agents can use getting-started?
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 getting-started 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 getting-started?
It is published by joellewis in joellewis/skill-library. It has 41 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.
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。