← All skill packs

Research & Analysis Workflows

Skill pack
3 skills0 selected
fantasymaxSkills in this pack

Use when the user wants to build a personalized AI configuration through structured self-interview rather than copying templates. Two outputs: (A) Principles document — CLAUDE.md / AGENTS.md / CODEX.md / .cursorrules / system-prompt for Claude Code, Cursor, Codex, OpenCode, Trae, Qoder etc. (B) Custom skill package — extracts one of the user's recurring tasks into a reusable SKILL.md with examples and references. Trigger especially when users say things like build my own CLAUDE.md / write AGENTS.md / make a custom skill / AI that understands me / 我的 principles / 自己的 skill / 个性化 AI / 把我会的事教给 AI. Do NOT use for customer research about other users, product discovery interviews, market research, or generic help-me-write-a-system-prompt requests.

English

Use when {B1 一句话定义关键动词}. This includes: {B7 2 子场景列举,3–5 个,逗号隔开}. Trigger especially when the user mentions {B7 1 触发原话片段,至少 3 句,原话保留} or files matching {B7 2 文件名/关键词}. Do NOT use for {B7 3 反例 + 通用兜底"general writing requests where the user doesn't want X-specific style"}.

Chinese

{B1 一句话定义动词} {B1 对象}, with deterministic enforcement on {B13 触发事件,如 git push / file save / session start}. Use when {B7 1 触发原话;如自然语言也支持触发}. The hook ensures {B13 + B5 转化的硬拦截规则}, even if Claude Code's model-side reasoning forgets. Do NOT use for: {B7 3 反例}.

Chinese

Includes User Research for AI Config and other workflows.

Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI

Supported by the Atlas install prompt. Skill-specific requirements vary.

Pack stats

Skills3CategorygeneralStars0

What’s included

User Research for AI Config

Use when the user wants to build a personalized AI configuration through structured self-interview rather than copying templates. Two outputs: (A) Principles document — CLAUDE.md / AGENTS.md / CODEX.md / .cursorrules / system-prompt for Claude Code, Cursor, Codex, OpenCode, Trae, Qoder etc. (B) Custom skill package — extracts one of the user's recurring tasks into a reusable SKILL.md with examples and references. Trigger especially when users say things like build my own CLAUDE.md / write AGENTS.md / make a custom skill / AI that understands me / 我的 principles / 自己的 skill / 个性化 AI / 把我会的事教给 AI. Do NOT use for customer research about other users, product discovery interviews, market research, or generic help-me-write-a-system-prompt requests.

{kebab Case Skill Name}

Use when {B1 一句话定义关键动词}. This includes: {B7 2 子场景列举,3–5 个,逗号隔开}. Trigger especially when the user mentions {B7 1 触发原话片段,至少 3 句,原话保留} or files matching {B7 2 文件名/关键词}. Do NOT use for {B7 3 反例 + 通用兜底"general writing requests where the user doesn't want X-specific style"}.

{kebab Hook Skill Name}

{B1 一句话定义动词} {B1 对象}, with deterministic enforcement on {B13 触发事件,如 git push / file save / session start}. Use when {B7 1 触发原话;如自然语言也支持触发}. The hook ensures {B13 + B5 转化的硬拦截规则}, even if Claude Code's model-side reasoning forgets. Do NOT use for: {B7 3 反例}.

Quick start

  1. Choose your skills. Select individual skills above, or choose the entire pack.
  2. Copy the install prompt. Use Copy install prompt above the list.
  3. Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.

Try it with your agent

After installation, start with a request like:

Example request
Use the User Research for AI Config skill to help with my task.
Ask me for the context you need before getting started.

Requirements & license

  • A coding agent that can access your project files and install skills.
  • Your agent checks each skill’s instructions, dependencies, and permissions during setup.
  • License details are not provided in these listings. Check the author’s terms before using the skills.
Research & Analysis Workflows | Agent Skills Atlas