GitHub Repos intermediate 3 min read Jun 6, 2026
Public Preview Sign in free for the full digest →

Archive Colleague Knowledge as AI Skills

“A colleague's years of institutional knowledge walks out the door in 2 weeks — colleague-skill archives it as a callable AI persona in 30 minutes.”

Archive Colleague Knowledge as AI Skills
Source · github.com

“"when a colleague leaves, their knowledge walks out the door. Can we keep it?" — Tianyi Zhou, ROADMAP.md”

You know that feeling when your most knowledgeable teammate gives their two weeks' notice and you realize you have no idea how they made half the decisions they did? Their tribal knowledge — why they built the auth system that way, their preferred code review tone, their read on which stakeholders to escalate to — never made it into any doc. colleague-skill addresses this gap: it ingests their existing chat logs, emails, and documents before they leave, and distills them into an AI persona that knows their decision patterns and work style. The alternative is either a rushed knowledge-transfer session that captures maybe 20% of what they knew, or months of re-learning what they already figured out.

claude-codeai-skillsknowledge-preservationpythonopen-sourcepersona-distillationdevtools

You run /create-colleague inside Claude Code and answer three questions: the person's alias, their role summary, and a personality snapshot. Then you choose a data source — Feishu auto-collect pulls messages and docs directly, Slack uses the API, WeChat imports from a SQLite export, or you paste text directly. The tool splits everything into two separate files: work.md covering technical systems, workflows, and output format preferences, and persona.md covering a five-layer personality model governing communication style, decision approach, and MBTI-influenced posture. Both merge into SKILL.md, a single file Claude Code loads as a first-class skill you call with /{slug}. If the distillation gets something wrong — type 'He wouldn't say that' — it writes the fix to the exact layer it belongs in without touching the other.

01
Dual-layer output (Work Skill + Persona as separate files) — you update the technical knowledge base independently from the personality model, so adding new documents does not overwrite corrections you already made to communication style
02
Eight data source connectors (Feishu, DingTalk, Slack, WeChat SQLite, email .eml/.mbox, PDF, images, direct text) — you are not blocked if the person only used one platform
03
Dialogue correction without re-ingestion — type 'He wouldn't do that' and the fix writes to the targeted layer only; no re-running the full pipeline
04
Incremental evolution — append new files after initial creation and they auto-merge into the existing skill; version history archives every update with rollback support
05
Four-host compatibility (Claude Code, OpenClaw, Hermes Agent, Codex) — the SKILL.md output is plain Markdown; switching agent host does not require rebuilding the skill
06
Community gallery with 215 contributed skills from 165 contributors — browse and install existing skills to understand the format before building your own
07
/list-colleagues, /colleague-rollback, /delete-colleague management commands — you manage the full skill lifecycle inside Claude Code without touching the file system manually
Who it’s for

If you are an engineering lead or IC at a Chinese tech company using Feishu or DingTalk, with a team member about to leave and access to their chat history, this tool is directly usable today. Also relevant if you are exploring the Claude Code skills ecosystem and want a concrete multi-source data ingestion example to study. Not recommended for regulated industries (no consent mechanism built in), English-first orgs relying on Slack free tier (90-day history cap per INSTALL.md), or anyone who needs production-grade stability — no tagged releases exist and only 3 contributors are active.

Worth exploring

Worth a test run today if you are in a Feishu-heavy org and have a leaving colleague willing to consent — setup is a single git clone and the skill runs entirely inside Claude Code. Treat it as experimental: no releases and 3 contributors means the API surface will change without warning. The privacy architecture — operator's OAuth for P2P chats, no subject consent mechanism — is a structural limitation that makes enterprise rollout legally complicated in most Western jurisdictions until the project addresses it at the design level.

Developer playbook
Tech stack, code snippet, sentiment, alternatives.
PM playbook
Adoption angles, user fit, positioning.
CEO playbook
Traction signals, ROI, build vs buy.
Deep-dive insight
Full long-form analysis, no fluff.
Easy mode
Core idea, fast — when you need the gist.
Pro mode
Technical nuance, edge cases, tradeoffs.
Read the full digest
Go beyond the preview

Deep-dive insight, Easy and Pro modes, plus action playbooks — the full breakdown is one tap away.

Underrated tools. Unfiltered takes.

Read the full digest in the Snaplyze app for deep-dive insight, Easy and Pro modes, and the playbooks you can actually use.

Install Snaplyze →