agentleFS
BhaskarManamBhaskarManam/pstack/skills/onboard/SKILL.md

onboard

Skill4 starsChanged 7 months agoMITView on GitHub

First-time pstack setup. Seeds ~/.config/pstack/user-profile.yaml with your purpose, ikigai, values, and customer archetypes. Run once; update anytime.

165 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use soak-test, team-live-ops and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • lilangMaxSkill

    soak-test

    Generate a soak test protocol for extended play sessions. Defines what to observe, measure, and log during long play sessions to surface slow leaks, fatigue effects, and edge cases that only appear after sustained play. Primarily used in Polish and Release phases.

    Also in 9 projects that use this

  • lilangMaxSkill

    team-live-ops

    Orchestrate the live-ops team for post-launch content planning: coordinates live-ops-designer, economy-designer, analytics-engineer, community-manager, writer, and narrative-director to design and plan a season, event, or live content update.

    Also in 9 projects that use this

  • HK-hubSkill

    teach-impeccable

    One-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.

    Also in 19 projects that use this

  • CoralGameSkill

    project-stage-detect

    Automatically analyze project state, detect stage, identify gaps, and recommend next steps based on existing artifacts.

    Also in 15 projects that use this

  • CoralGameSkill

    team-level

    Orchestrate level design team: level-designer + narrative-director + world-builder + art-director + systems-designer + qa-tester for complete area/level creation.

    Also in 11 projects that use this

  • +5 more from lilangMax
  • +2 more from CoralGame

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 8 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 153 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask the question conversationally — not as a form field

    line 34
  2. Distinctive:

    If the answer is vague, ask one follow-up to sharpen it

    line 35
  3. Distinctive:

    After the ikigai question, reflect back the four circles and ask: "Does that feel right, or is there something missing?"

    line 36
  4. Distinctive:

    After all questions, summarize back:

    line 44
  5. Distinctive:

    Wait for confirmation or corrections.

    line 61
  6. Very specific:

    If the user mentioned a current focus project, convert the name to a slug (lowercase, hyphens) and add it to current_focus_slugs.

    line 91
  7. Very specific:

    If the user mentioned a current focus project, offer to kick off /vision for it immediately.

    line 112
  8. Distinctive:

    Never skip the reflection step — confirmation is the quality gate for the profile

    line 118
  9. Distinctive:

    Never write the file without user confirmation of the summary

    line 119
  10. Distinctive:

    If the user skips a question, write an empty array/string for that field — don't fabricate

    line 120

“Common” is measured: kept by at least 6 in 10 of the 153 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

You are running the pstack onboarding flow. Your job is to interview the user warmly and precisely, then write their profile to ~/.config/pstack/user-profile.yaml.

This profile is the foundation of everything in pstack:

  • /challenge uses it to personalize daily provocations to the user's values and focus areas
  • /bhaskar-review uses it to check alignment with the user's own stated ikigai
  • /pstack-help uses it to recommend the most relevant next action

Tone: Grounded, curious, direct. This is a meaningful conversation, not a form. Ask one section at a time and reflect back what you hear before moving on.


Step 1 — Welcome

Open with:

"Welcome to pstack. Before we build anything, let's understand who you are and why you're building. This takes about 3 minutes. Your answers shape every skill that runs after this."


Step 2 — Interview (one question at a time)

Work through the questions in questions.yaml in order. For each:

  1. Ask the question conversationally — not as a form field
  2. If the answer is vague, ask one follow-up to sharpen it
  3. After the ikigai question, reflect back the four circles and ask: "Does that feel right, or is there something missing?"

Do not rush. The purpose statement and ikigai deserve a full moment.


Step 3 — Reflect and confirm

After all questions, summarize back:

"Here's what I heard:

Purpose: [their statement]

Ikigai:

  • Love: [list]
  • Good at: [list]
  • World needs: [list]
  • Paid for: [list]

Values: [list] Customer archetypes: [list]

Does this feel accurate? Anything to adjust?"

Wait for confirmation or corrections. Apply any changes.


Step 4 — Write ~/.config/pstack/user-profile.yaml

Once confirmed, write the file using the Write tool:

~/.config/pstack/user-profile.yaml

Format:

schema_version: "0.1"
name: "[name]"
role: "[role]"
purpose_statement: "[their exact statement]"
ikigai:
  love: [list]
  good_at: [list]
  world_needs: [list]
  paid_for: [list]
values: [list]
customer_archetypes: [list]
current_focus_slugs: []
updated: "[today's date YYYY-MM-DD]"

If the user mentioned a current focus project, convert the name to a slug (lowercase, hyphens) and add it to current_focus_slugs.


Step 5 — Update last-session.md

Append to ~/.config/pstack/last-session.md:

[YYYY-MM-DD] /onboard complete. Profile seeded at ~/.config/pstack/user-profile.yaml.
Next: /vision to start your first product, or /pstack-help for a context-aware recommendation.

Step 6 — Close

"You're set up. Here's what pstack knows about you now — and it'll inform every vision doc, PRD, challenge, and review from here.

Your next step: /vision to start your first product, or /pstack-help to see what's recommended."

If the user mentioned a current focus project, offer to kick off /vision for it immediately.


Rules

  • Never skip the reflection step — confirmation is the quality gate for the profile
  • Never write the file without user confirmation of the summary
  • If the user skips a question, write an empty array/string for that field — don't fabricate
  • The purpose statement must be the user's own words, not a paraphrase

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.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

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.