agentleFS
Sign inStart free
0mlkrizzz655335v0mlkrizzz655335v/claude-skills-zh/skills/automation/onboard/SKILL.md

onboard

Skill2 starsChanged 5 months agoMITView on GitHub

新手引导流程。了解你的基本偏好、定第一个目标、指引下一步。"disable-model-invocation: true

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 149 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use only when the user explicitly invokes /onboard.

    line 9
  2. Distinctive:

    Do not browse accounts, install integrations, clone repositories, or change settings merely to enrich onboarding.

    line 19

“Common” is measured: kept by at least 6 in 10 of the 149 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Onboard

Use only when the user explicitly invokes /onboard. Help them choose one useful first task with a short conversation. Do not make them repeat context already provided.

Ask only the next question that affects the direction. A preferred name is optional; work context and the desired result usually matter more. Offer a few concrete options when the user is unsure, and use an available question tool only when its current mode permits it. Match the user's language.

Use the answers in this conversation. Save personal preferences only when the user directly requests persistent saving and the current environment permits it; follow the active memory or rule workflow. Never treat answering an onboarding question as permission to write a personal rule. If saving is unavailable, explain it without claiming future memory.

For a product question, use current local/runtime evidence and the installed openai-docs skill as appropriate. Do not guess settings paths, tool availability, or integrations.

Once a concrete task is clear, give a compact next step. If the user asks to perform it, end the onboarding interview and continue the authorized work using the relevant workflow; do not require them to repeat the task in a new message. If they only wanted suggestions, provide a usable prompt or plan and stop. A Plan-mode switch requires a supported tool and user intent; never claim a mode changed without a successful tool result.

Do not browse accounts, install integrations, clone repositories, or change settings merely to enrich onboarding. Do such actions only when needed for the specific task the user has chosen and authorized.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free