Agent skill

Onboard

by kv0906 in kv0906/pm-kit

Interactive onboarding — sets up your first project, learns who you are, generates core/identity.md profile, creates your first daily note, then loads vault context.

MITAuto-check passedKnowledge Management

Install Onboard

skills CLI
$ npx skills add kv0906/pm-kit --skill onboard -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install kv0906/pm-kit onboard --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/kv0906/pm-kit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/onboard .claude/skills/onboard && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
onboard
GitHub stars
138
Token cost
~3.3k tokens
SKILL.md length
1,138 words
Files
1
Skills in repo
26
Repo updated
First seen
Licence
MIT

At a glance

Interactive onboarding — sets up your first project, learns who you are, generates core/identity.md profile, creates your first daily note, then loads vault context.

  • Works in 7 steps: Detect & Welcome → Project Setup → Interview (3 Rounds) → …
  • Tasks that involve Note-taking
  • SKILL.md covers Usage, Flow, Phase 1: Detect & Welcome and Phase 2: Project Setup, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Onboard is an agent skill from kv0906/pm-kit. Interactive onboarding — sets up your first project, learns who you are, generates core/identity.md profile, creates your first daily note, then loads vault context. For returning users, skips setup and loads context directly.

Its SKILL.md is about 3.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Knowledge Management, covering Note-taking. The repository describes itself as: AI-augmented PM workspace for Coding Agents — daily standups, decisions, blockers, docs, and sprint reviews as markdown skills. The licence is MIT.

When your agent uses it

  • Tasks that involve Note-taking

Example prompts

  • “/onboard”

Requirements

  • Pre-approved tools (allowed-tools): Read, Write, Edit, Glob, Grep, TaskCreate, TaskUpdate, TaskList, TaskGet, AskUserQuestion

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Detect & Welcome
  2. Project Setup
  3. Interview (3 Rounds)
  4. Generate Profile
  5. First Daily Note
  6. Load Context
  7. Handoff

What it can do on your machine

Read from SKILL.md and the folder at commit 2cb5d9f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Edit
    • Glob
    • Grep
    • TaskCreate
    • TaskUpdate
    • TaskList
    • TaskGet
    • AskUserQuestion

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Onboard loads about 3.3k tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 1,138 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~59
When it runs · the whole SKILL.md, loaded when a task matches
~3.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from kv0906/pm-kit at commit 2cb5d9f, republished under its MIT licence (© kv0906). 1,138 words, ~3,277 tokens.

Download SKILL.mdSave it as .claude/skills/onboard/SKILL.md (or your agent's skills folder).
name
onboard
description
Interactive onboarding — sets up your first project, learns who you are, generates _core/identity.md profile, creates your first daily note, then loads vault context. For returning users, skips setup and loads context directly.
allowed-tools
Read, Write, Edit, Glob, Grep, TaskCreate, TaskUpdate, TaskList, TaskGet, AskUserQuestion
user-invocable
true

/onboard — Interactive Onboarding & Context Loading

Set up your first project, run an interactive interview, generate a personalized _core/identity.md, create your first daily note, then load vault context. Returning users skip straight to context loading.

Usage

/onboard          # First time: project setup → interview → profile → daily → context. Returning: context only.
/onboard --reset  # Re-run interview even if profile exists (skips project setup if already configured)

Flow

/onboard
  ├── _core/identity.md populated + config has real projects + no --reset?
  │   → Returning user → Load context → "Welcome back"
  │
  └── First time (no profile OR default projects OR --reset)?
       │
       ├── Phase 1: Welcome message
       ├── Phase 2: Project Setup (if config still has default project-a)
       │   ├── Read config.yaml
       │   ├── Detect default project-a/project-b
       │   ├── AskUserQuestion: project name
       │   ├── Edit config.yaml (replace project-a, remove project-b)
       │   ├── Create dirs: docs/{id}/, decisions/{id}/, blockers/{id}/
       │   └── Create 01-index/{id}.md from template
       │
       ├── Phase 3: Personal Interview (3 rounds, 7 questions)
       │   └── Generate _core/identity.md
       │
       ├── Phase 4: First Daily Note
       │   └── Create daily/{today}.md with welcome content
       │
       ├── Phase 5: Load Context
       │
       └── Phase 6: Handoff with "what to do next"

Phase 1: Detect & Welcome

Check if _core/identity.md has been populated (not just the default template):

Read: _core/identity.md

Also read _core/config.yaml to check if projects are still defaults:

Read: _core/config.yaml

Detection logic:

  • Returning user: _core/identity.md is populated (has a real role, not placeholder brackets) AND config does NOT contain id: project-a AND no --reset flag → Skip to Phase 5 (Load Context). Greet with:

    Welcome back! Loading your vault context...

  • First time or --reset: Continue to Phase 2.

Display welcome message (for new users):

Welcome to PM-Kit!

I'm your AI-augmented knowledge partner for technical PM and engineering work. Let me get you set up — this takes about 3 minutes.

We'll do three things:

  1. Set up your first project
  2. Learn how you work (7 quick questions)
  3. Load your vault context

Let's get started.

Create session tasks for progress tracking:

Task 1: "Set up first project" (activeForm: "Setting up first project...")
Task 2: "Complete onboarding interview" (activeForm: "Running onboarding interview...", blockedBy: Task 1)
Task 3: "Generate personal profile" (activeForm: "Generating personal profile...", blockedBy: Task 2)
Task 4: "Create first daily note" (activeForm: "Creating first daily note...", blockedBy: Task 3)
Task 5: "Load vault context" (activeForm: "Loading vault context...", blockedBy: Task 4)

Phase 2: Project Setup

Mark Task 1 as in_progress.

Skip condition: If config.yaml does NOT contain id: project-a, projects are already configured. Mark Task 1 as completed and skip to Phase 3.

If config still has the default project-a, ask the user to name their project:

AskUserQuestion
#HeaderQuestionOptionsmultiSelect
1Project"What's your main project called? (This becomes your folder name — lowercase, hyphens ok)""my-product": "A product you're building" / "my-team": "Team-level tracking" / "my-company": "Company-wide knowledge"false

The user can pick a preset or type a custom name via "Other".

After receiving the answer
  1. Derive project ID: Use the answer directly as the ID (already lowercase with hyphens). If the user typed a display name with spaces/caps, slugify it (lowercase, replace spaces with hyphens, remove special characters).

  2. Derive display name: Capitalize the ID (e.g., my-product → My Product, acme-app → Acme App).

  3. Edit config.yaml: Use the Edit tool to:

    • Replace id: project-a with id: {project-id}
    • Replace name: Project A with name: {Display Name}
    • Replace description: Your first project with description: {Display Name} workspace
    • Remove the entire project-b block (the 4 lines: - id: project-b, name: Project B, description: Your second project, active: true)
  4. Create project directories:

    Write empty .gitkeep files to:
    - docs/{project-id}/.gitkeep
    - decisions/{project-id}/.gitkeep
    - blockers/{project-id}/.gitkeep
  5. Create project index: Write 01-index/{project-id}.md:

    markdown
    ---
    type: index
    project: {project-id}
    status: active
    ---
    
    # {Display Name}
    
    > {Display Name} workspace
    
    ---
    
    ## Open Blockers
    
    *No open blockers*
    
    ---
    
    ## Active Docs
    
    *No active docs*
    
    ---
    
    ## Recent Dailies (7 days)
    
    *No dailies yet*
    
    ---
    
    ## Recent Decisions (30 days)
    
    *No decisions yet*
    
    ---
    
    ## Manual Notes
    
    %% Add your own notes below — this section is preserved during updates %%

Mark Task 1 as completed.

Phase 3: Interview (3 Rounds)

Mark Task 2 as in_progress.

Skip condition for --reset: If --reset flag is set but projects are already configured (no project-a in config), skip Phase 2 but still run the interview.

Use AskUserQuestion for each round. All 3 rounds use a single AskUserQuestion call each (multiple questions per call).

Round 1 — Who Are You

Ask these 2 questions in a single AskUserQuestion call:

#HeaderQuestionOptionsmultiSelect
1Role"What's your primary role?"Product Manager: "Roadmaps, specs, stakeholder alignment" / Engineering Lead: "Architecture, team velocity, technical decisions" / Founder-Operator: "Wearing all hats — product, eng, strategy" / Researcher: "Deep exploration, synthesis, knowledge work"false
2AI Experience"What's your experience with AI-assisted workflows?"New to this: "First time using AI for structured work" / Getting started: "Tried a few tools, learning the ropes" / Experienced: "Regular AI user, ready for advanced workflows"false
Round 2 — How You Work

Ask these 3 questions in a single AskUserQuestion call:

#HeaderQuestionOptionsmultiSelect
3Communication"How do you prefer feedback and communication?"Direct: "Cut to the chase, no fluff" / Collaborative: "Think together, build on ideas" / Detailed: "Thorough explanations, show your work"false
4Planning"How do you prefer to plan?"Detailed plans: "Upfront structure, clear milestones" / Flexible: "Rough direction, adapt as we go" / Minimal: "Just start building, plan emerges"false
5Energy"When do you do your best focused work?"Morning: "Peak focus before noon" / Afternoon: "Hit my stride after lunch" / Evening: "Night owl, late-day clarity" / Flexible: "Varies day to day"false
Show full SKILL.md (509 more words)Show less
Round 3 — What Drives You

Ask these 2 questions in a single AskUserQuestion call:

#HeaderQuestionOptionsmultiSelect
6Focus"What matters most in your work right now?"Shipping fast: "Velocity and momentum above all" / Quality depth: "Doing fewer things really well" / Clarity: "Understanding before building" / Alignment: "Getting everyone on the same page"true
7Coaching"How should I challenge you?"Gentle nudges: "Light reminders, supportive tone" / Moderate push: "Flag issues directly, suggest alternatives" / Intense coach: "Call out everything, hold me accountable"false

After all 3 rounds complete, mark Task 2 as completed.

Phase 4: Generate Profile

Mark Task 3 as in_progress.

Map answers to _core/identity.md. Write to the bootloader directory.

Answer Mapping

Work Hours (derived from Energy answer):

  • Morning → "7am - 3pm"
  • Afternoon → "10am - 6pm"
  • Evening → "1pm - 9pm"
  • Flexible → "Flexible"

Scope Creep Alerts (derived from Coaching answer):

  • Gentle nudges → "Gentle reminders"
  • Moderate push → "Flag when noticed"
  • Intense coach → "Call out aggressively"

Working Philosophy (generate a 1-2 sentence statement based on role + focus areas): Combine the role and selected focus areas into a concise personal statement. Examples:

  • PM + Shipping fast + Clarity → "Ship with intention — move fast but make sure every feature tells a clear story."
  • Engineering Lead + Quality depth → "Build it right the first time — depth over breadth, craft over speed."
  • Founder-Operator + Shipping fast + Alignment → "Move fast together — velocity means nothing if the team isn't aligned."
  • Researcher + Clarity + Quality depth → "Understand deeply, document clearly — knowledge compounds when it's well-structured."

Write the file using Write tool to _core/identity.md:

markdown
# Personal Profile

> Generated by `/onboard` on {today's date}. Edit anytime — tracked in your vault.

## Identity

- **Role**: {answer 1}
- **AI Experience**: {answer 2}
- **Onboarded**: {today's date YYYY-MM-DD}

## Working Style

- **Communication**: {answer 3}
- **Planning**: {answer 4}

## Energy & Schedule

- **Best Focus Time**: {answer 5}
- **Timezone**: America/New_York
- **Work Hours**: {derived from answer 5}

## Current Priorities

What matters most right now:
{for each selected focus area from answer 6, write as bullet with description}

## Coaching Settings

- **Challenge Level**: {answer 7}
- **Scope Creep Alerts**: {derived from answer 7}

## Working Philosophy

> {generated statement}

## Notes for Claude

[Add custom instructions here — this section is yours to edit freely]

---

*Regenerate with `/onboard --reset`*

Mark Task 3 as completed.

Phase 5: First Daily Note

Mark Task 4 as in_progress.

Create today's daily note at daily/{YYYY-MM-DD}.md with a welcome entry under the user's project:

markdown
---
type: daily
status: active
date: {YYYY-MM-DD}
tags: []
---

# {YYYY-MM-DD}

## {Project Display Name}

### Shipped
- Set up PM-Kit vault

### In Progress
*None*

### Blocked
*None*

### Notes

Welcome to PM-Kit! Your vault is ready. Try `/daily {project-id}: shipped X, wip Y` tomorrow.

---

## Tomorrow

- Start using `/daily` for standups

Skip condition: If daily/{today}.md already exists, do not overwrite it.

Mark Task 4 as completed.

Phase 6: Load Context

Mark Task 5 as in_progress (or create it if this is a returning user without tasks).

Load vault context in this order:

1. Core Config (Always First)
_core/config.yaml      → Projects, paths, note types, keywords
_core/PROCESSING.md    → I-P-O flows for all skills
_core/MANIFESTO.md     → Philosophy and principles
2. Vault Context
CLAUDE.md              → Vault overview, skills, agents, conventions
_core/identity.md      → Personal profile (just generated or existing)
3. Project Indexes
01-index/{project}.md  → MOC for each active project
4. Current State
daily/{today}.md       → Today's standup (if exists)
daily/{yesterday}.md   → Yesterday's context
5. Active Blockers
blockers/**/status: open  → All open blockers across projects

Smart loading rules:

  • Only load indexes for projects marked active: true in config.yaml
  • Read today's and yesterday's dailies for current context
  • Scan open blockers to understand current obstacles

Mark Task 5 as completed.

Phase 7: Handoff

New Users

Personalize the ready message based on their profile:

You're all set, {role}!

Your profile is saved to _core/identity.md. Here's what I set up:

  • Project: {project display name} ({project-id}/)
  • Config: {n} active projects
  • Index: 01-index/{project-id}.md
  • Today: daily/{today}.md (your first entry)

Based on your preferences, I'll keep communication {communication style} and challenge you at {coaching level} intensity.

A few commands to try:

  • /daily {project-id}: shipped X, wip Y — Write your standup
  • /ask — Quick vault lookup
  • /progress {project-id} — Project status
  • /push — Save changes to git

What would you like to work on?

Returning Users

Welcome back!

Context loaded:

  • Config: {n} active projects
  • Indexes: {n} project MOCs
  • Today: {summary or "No standup yet"}
  • Blockers: {n} open across projects
  • Updates: {version status from API check, non-fatal — e.g. "Up to date (v2026.02.14)" or "Update available: vX → vY"}

What would you like to work on?

© kv0906, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/onboard of kv0906/pm-kit.

Open the folder on GitHubat commit 2cb5d9f

Compare with similar skills

Onboard next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Onboard compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Onboard this skillkv0906/pm-kit138—~3.3kAutomated safety check: PassMIT
Qmdalsk1992/CloddsBot2.9k3 repos~1.2kAutomated safety check: PassMIT
Obsidian Canvas BoardsAgriciDaniel/claude-obsidian15k—~1.4kAutomated safety check: PassMIT
LLM Wikilewislulu/llm-wiki-skill655—~3.7kAutomated safety check: PassNone
Para Memory Filespaperclipai/paperclip99k1 repos~909Automated safety check: PassMIT
Add Frontmatterheyitsnoah/claudesidian2.6k—~951Automated safety check: PassMIT

Similar skills

  • Qmd

    alsk1992/CloddsBot

    Local hybrid search for markdown notes and docs. An agent skill from alsk1992/CloddsBot.

    2.9k GitHub starsUsed in 3 repos~1.2k tokens
    Knowledge ManagementAuto-check passed
  • Obsidian Canvas Boards

    AgriciDaniel/claude-obsidian

    Creates, inspects and updates Obsidian JSON Canvas boards in a vault, with text, file, link, group and edge nodes, using safe recoverable edits.

    15k GitHub stars~1.4k tokensUpdated 29 days ago
    Knowledge ManagementAuto-check passed
  • LLM Wiki

    lewislulu/llm-wiki-skill

    Build and maintain a Karpathy-style LLM knowledge base — a self-compiling Obsidian markdown wiki where an Agent ingests raw sources, compiles cross-linked concept/entity/summary pages, answers…

    655 GitHub stars~3.7k tokensUpdated 5 mo ago
    Knowledge ManagementAuto-check passed
  • Para Memory Files

    paperclipai/paperclip

    Use a file-based PARA memory system to store, retrieve, and organize durable knowledge across sessions.

    99k GitHub starsUsed in 1 repo~909 tokens
    Knowledge ManagementAuto-check passed
  • Add Frontmatter

    heyitsnoah/claudesidian

    Add or update YAML frontmatter properties to enhance Obsidian note organization.

    2.6k GitHub stars~951 tokensUpdated 6 mo ago
    Knowledge ManagementAuto-check passed
  • Obsidian Bases Editor

    AgriciDaniel/claude-obsidian

    Explains, drafts and validates Obsidian Bases .base files, building filters, formulas and table, card or list views, and applying edits only through one inspected transaction.

    15k GitHub stars~1.2k tokensUpdated 29 days ago
    Knowledge ManagementAuto-check passed

More from kv0906/pm-kit

All 26 skills in this repo
  • Mermaid Visualizer

    kv0906/pm-kit

    Transform text content into professional Mermaid diagrams for presentations and documentation.

    138 GitHub starsUsed in 2 repos~2.2k tokens
    Auto-check passed
  • Gws

    kv0906/pm-kit

    This skill should be used when the user asks to "set up gws", "install Google Workspace CLI", "connect Gmail to Claude", "manage Google Drive from terminal", "send email from CLI", "check my…

    138 GitHub stars~1.6k tokensUpdated 3 mo ago
    Auto-check passed
  • Jira

    kv0906/pm-kit

    Jira integration via acli CLI. An agent skill from kv0906/pm-kit.

    138 GitHub stars~4.2k tokensUpdated 3 mo ago
    Auto-check: notes
  • Professional Excalidraw diagram generation expert that creates complete, valid .excalidraw.json files based on user descriptions.

    138 GitHub stars~3k tokensUpdated 3 mo ago
    Auto-check passed
  • Ask

    kv0906/pm-kit

    Fast vault Q&A — quick lookups, decision history, blocker status, doc search.

    138 GitHub stars~781 tokensUpdated 3 mo ago
    Auto-check passed
  • Block

    kv0906/pm-kit

    Flag a blocker with severity, owner, and due date. An agent skill from kv0906/pm-kit.

    138 GitHub stars~466 tokensUpdated 3 mo ago
    Auto-check: notes

Questions about Onboard

What does Onboard do?

Interactive onboarding — sets up your first project, learns who you are, generates core/identity.md profile, creates your first daily note, then loads vault context. Onboard is an agent skill from kv0906/pm-kit.md profile, creates your first daily note, then loads vault context.

When should I use Onboard?

Onboard fits situations like: tasks that involve Note-taking.

How do I install Onboard in Claude Code?

Run `npx skills add kv0906/pm-kit --skill onboard -a claude-code`. Or copy the skill folder (.claude/skills/onboard in kv0906/pm-kit) into .claude/skills/onboard in your project. Claude Code loads it when a task matches its description.

How do I install Onboard in Codex?

Run `npx skills add kv0906/pm-kit --skill onboard -a codex`. Or copy the skill folder (.claude/skills/onboard in kv0906/pm-kit) into .agents/skills/onboard in your project. Codex loads it when a task matches its description.

Can I use Onboard in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add kv0906/pm-kit --skill onboard -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/onboard, .gemini/skills/onboard, .github/skills/onboard and .opencode/skills/onboard in your project.

What does Onboard need to run?

SKILL.md names no scripts, command-line tools or credentials: Onboard is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Write, Edit, Glob, Grep, TaskCreate, TaskUpdate, TaskList, TaskGet, AskUserQuestion.

Does Onboard access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Onboard safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Onboard use?

Onboard is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Onboard use?

About 3.3k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Onboard?

Skills that share tags, products or a category with Onboard: Qmd (alsk1992/CloddsBot, 2.9k stars), Obsidian Canvas Boards (AgriciDaniel/claude-obsidian, 15k stars), LLM Wiki (lewislulu/llm-wiki-skill, 655 stars) and Para Memory Files (paperclipai/paperclip, 99k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Onboard?

kv0906 (a GitHub user) maintains it in kv0906/pm-kit, which has 138 GitHub stars. The repository holds 26 skills in this directory. The repository was last updated on June 29, 2026.

Source: kv0906/pm-kit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.