Skip to content

ferdinandobons/knowledge-transfer / plugins/knowledge-transfer/skills/knowledge-transfer

knowledge-transfer

Verified

Use when a colleague is leaving a project and must hand over knowledge, or when someone new joins a project and receives handover.zip or a handover/ folder. Two phases: export (analyze project + agent project memories from Claude, Codex, or another assistant, then produce a transferable handover.zip archive containing a non-technical onboarding doc + filtered portable memories + a privacy-safe omissions manifest) and import (extract/read the handover package, dry-run the candidate memories, verify every claim against current code, then install accepted memories through the current agent's memory mechanism with per-memory receipts). Trigger on /knowledge-transfer, /knowledge-transfer:knowledge-transfer, $knowledge-transfer, 'handover', 'knowledge transfer', 'passaggio di consegne', 'onboard a new colleague', or when the user mentions taking over / leaving a project.

FileKindSize
SKILL.mdskill md11.9 KB
agents/openai.yamlconfig280 B
references/agent-memory.mdmarkdown2.5 KB
references/onboarding-template.mdmarkdown2.0 KB
references/package-format.mdmarkdown7.5 KB
references/privacy-filter.mdmarkdown3.0 KB

references/onboarding-template.md

View on GitHub
# ONBOARDING.md template

Audience: someone joining the project who has never seen it. They may not be deeply
technical — a product manager should follow every section. The goal is that after
reading they know what the main pieces are and how work flows, BEFORE they ask the
AI anything technical.

**Length: 600–1000 words. Hard cap: 2 pages.** Cutting is part of the job: pick what
matters, drop the rest.

**Language:** the project's dominant language. Detect it from README, docs, and
recent commit messages. If mixed or unclear, use English.

## Required structure

```markdown
# <Project name>

> One sentence: the project explained to a colleague over coffee.

## What it's for

The problem it solves and for whom. 2–4 sentences. No architecture here.

## The main pieces

The 3–7 components that matter. For each: its everyday name, what it does in plain
words (2–3 sentences), and where it lives (folder/file in backticks — name it, don't
explain the code). Skip utilities and glue.

## How the work flows

2–3 end-to-end flows narrated in plain language: "When a user does X, the <piece>
does Y, then hands off to <piece> which does Z." Pick the flows someone will
actually trace in their first week. No code, no sequence diagrams.

## Where to start

The 2–4 files to read first and why. How to run the project (the actual commands,
this is the one place commands are allowed).

## Things to know

Gotchas, conventions, and historical decisions that cannot be deduced from the code
— sourced from the exported memories and CLAUDE.md. Each item: one or two sentences,
plain language. If a gotcha has a memory in the package, this is a summary, not a
duplicate.
```

## Tone rules

- No unexplained jargon. If a term is unavoidable, gloss it in parentheses.
- No exhaustive inventories — this is a map, not a census.
- Plain verbs over nominalizations ("the store saves recipes" not "persistence is
  handled by the storage layer").
- Never paste code. Name files; explain behavior in words.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall