agentleFS
NoaiRoxNoaiRox/specialist-agent/skills/onboard/SKILL.md

onboard

Skill2 starsChanged 9 months agoMITView on GitHub

Use when joining an unfamiliar codebase, starting on a new team, or needing to understand a project's architecture, conventions, and key modules quickly.

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

6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 153 edited versions we read keep these.

  • 5

    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. Distinctive:

    Before contributing to an unfamiliar repo

    line 20
  2. Distinctive:

    When documentation is missing or outdated

    line 21
  3. Very specific:

    NOT for: projects you already know well (use @scout for quick checks instead)

    line 22
  4. Distinctive:

    If tests exist, the test command was identified

    line 115
  5. Distinctive:

    Read actual code: - Never rely solely on README or documentation

    line 129
  6. Distinctive:

    Actionable output: - Every section should help the developer start working

    line 134

“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 - Codebase Onboarding

Understand any codebase in minutes. Generates a developer guide with architecture, conventions, key modules, and getting-started instructions.

Target: $ARGUMENTS

When to Use

  • First day on a new project or team
  • Picking up an open-source project for the first time
  • Reviewing a project before a technical interview
  • Before contributing to an unfamiliar repo
  • When documentation is missing or outdated
  • NOT for: projects you already know well (use @scout for quick checks instead)

Workflow

Step 1: Project Discovery

Scan the project root:

Read: package.json / pyproject.toml / go.mod / Cargo.toml
Read: README.md (if exists)
Read: ARCHITECTURE.md / CLAUDE.md / CONTRIBUTING.md (if exist)
Scan: Top-level directory structure

Extract:

  • Project name and description
  • Language and framework
  • Package manager and scripts
  • Entry points

Step 2: Architecture Mapping

Map the project structure:

Identify:
  - Source root (src/, app/, lib/)
  - Module/feature boundaries
  - Shared utilities
  - Configuration files
  - Test structure
  - CI/CD setup

Generate architecture diagram:

src/
├── modules/          → Feature modules (users, orders, products)
│   └── [module]/
│       ├── types/    → TypeScript interfaces
│       ├── services/ → Business logic
│       ├── hooks/    → State management
│       └── components/ → UI components
├── shared/           → Shared utilities
├── config/           → App configuration
└── app/              → App entry and routing

Step 3: Convention Detection

Detect coding conventions by reading actual files:

ConventionHow to Detect
NamingRead 3-5 files, check function/variable naming
File structureMap actual directory patterns
State managementFind store/state imports (Redux, Zustand, Pinia, etc.)
API layerFind HTTP client usage (axios, fetch, etc.)
TestingFind test files, check framework (Jest, Vitest, etc.)
StylingFind CSS/styled imports (Tailwind, CSS Modules, etc.)
Error handlingFind try/catch patterns, error boundaries
ImportsCheck for path aliases, barrel exports

Step 4: Key Module Analysis

For each major module/feature:

Module: [name]
├── Purpose: [what it does]
├── Files: [count]
├── Dependencies: [what it imports from]
├── Dependents: [what imports from it]
├── Entry point: [main file]
└── Tests: [yes/no, coverage estimate]

Focus on the 3-5 most important modules.

Step 5: Developer Guide Generation

Compile everything into an actionable guide.

Verification Protocol

Before claiming onboarding is complete:

  1. Architecture diagram was generated from actual file structure (not assumed)
  2. Conventions were detected from reading real code (not README claims)
  3. At least 3 key modules were analyzed
  4. Setup instructions were verified by checking scripts in package.json
  5. If tests exist, the test command was identified

Anti-Rationalization

ExcuseReality
"README explains everything"READMEs are often outdated. Verify against actual code.
"Architecture is obvious"Obvious to maintainers, not newcomers. Map it explicitly.
"Too many files to analyze"Focus on top 3-5 modules. Don't skip the mapping step.
"No tests to analyze"That IS the finding. Report it in the guide.
"Conventions aren't consistent"Document the inconsistencies. It's useful for the developer.

Rules

  1. Read actual code - Never rely solely on README or documentation
  2. Map before explaining - Architecture diagram first, then details
  3. Focus on key modules - 3-5 most important, not all of them
  4. Detect, don't assume - Conventions come from reading files, not guessing
  5. Be honest about gaps - Missing tests, docs, or conventions are findings too
  6. Actionable output - Every section should help the developer start working

Output

──── /onboard ────
Project: [name]
Stack: [language + framework + key libraries]

Architecture:
[directory tree diagram]

Conventions:
  Naming: [camelCase / snake_case / PascalCase]
  State: [Redux / Zustand / Pinia / Context]
  API: [axios / fetch / tRPC]
  Testing: [Jest / Vitest / Playwright]
  Styling: [Tailwind / CSS Modules / styled-components]

Key Modules:
  1. [module] - [purpose] ([X files])
  2. [module] - [purpose] ([X files])
  3. [module] - [purpose] ([X files])

Getting Started:
  Install: [command]
  Dev: [command]
  Test: [command]
  Build: [command]

Notes:
  - [important observations]
  - [potential gotchas]
  - [missing documentation areas]

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.