Onboard

SkillDocs & knowledge

Use when taking over an existing codebase that has no living document. Produces a factual record of what already exists.

Use Onboard in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add Onboard and connect your AI. About a minute.

Claude ChatGPT Ahel Desktop

Also: Claude Code · Cursor · Codex

Then ask your AI: use the Onboard skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Account requirements not reviewed. Check the skill instructions before use; Ahel provides instructions and does not run this skill.

No other account needed.

Add Ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

OnboardStart free

What this skill tells your AI

The instructions your AI receives, as published by hashgraph-online/awesome-codex-plugins in plugins/ouonet/praxis/skills/onboard/SKILL.md and read by Ahel’s review.

Goal: read the codebase, produce living documentation. No code changes. No plans. No gap analysis.

living documentation

README.md : project overview, what it is, who it's for, how to use it.
docs/tech-spec.md : main technical specification (core backbone, ≤300 lines).
docs/specs/*.md : modular subsystem details split out when bulky (>15 lines). Referenced by path.

Technical specification is declarations only: current ground truth facts (atemporal, no narrative, no history, no plans).

Steps

Explore entry points, public interfaces, key dependencies, test patterns, file structure. Read, don't guess.
Ask the user about anything ambiguous — never invent architecture.
Write docs/tech-spec.md using the canonical format (field meanings: archive skill, "tech-spec format"):

purpose / user / use-case / architecture / stack / entry /
contract / flow / invariant / constraint / convention

Omit milestone — onboard makes no plans.
Details >15 lines (schemas, algorithms, protocol states) go to docs/specs/<topic>.md.
Keep declarations atomic (≤25 words/sentence) with structured lists/tables; no text walls.

Confirm with user.

docs/tech-spec.md must contain: stack + at least one contract + at least one convention (covering quality baseline — lint/format/typecheck tools, error-handling, security — read from code; see ../references/quality.md) before done.

Don't

Invent facts not found in code or README.
Add gap analysis, temporal/historical narratives, plans, or code changes.
Paste large code blocks or schemas — reference by path or modularize into docs/specs/.

After

docs/tech-spec.md on disk → user continues with normal design → plan → tdd.

Signals

GitHub stars: 1k
Forks: 316
Last commit: Oct 2026
Hacker News mentions: 20

Advanced

Item type: skill
Key: onboard-hashgraph-online
Source: github.com/hashgraph-online/awesome-codex-plugins

github.com/hashgraph-online/awesome-codex-plugins