Turn scattered information into a maintained knowledge asset with clear scope, sources, ownership, discoverability, and freshness rules.
Scanned 9/11/2026
Install to Claude Code
npx -y skills add Dadmin88/hermes-profile-packs --skill knowledge-curation --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Knowledge Curation?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/dadmin88-knowledge-curation)More formats (shields.io, HTML) on the badges page.
---
name: knowledge-curation
description: Turn scattered information into a maintained knowledge asset with clear scope, sources, ownership, discoverability, and freshness rules.
---
# Knowledge Curation
Use when recurring questions, decisions, procedures, or reference material are fragmented or hard to trust.
## Procedure
1. Define the audience and recurring questions the knowledge asset should answer.
2. Gather authoritative sources and resolve contradictions where possible.
3. Distill durable knowledge from transient chat, status, or implementation noise.
4. Organize information around user tasks and concepts rather than source order.
5. Preserve provenance, dates, versions, and uncertainty where freshness matters.
6. Remove duplicates and identify a canonical location for each topic.
7. Assign ownership and a trigger for review or expiration.
## Quality gate
The result should be easier to find and trust than the source material. Do not create another duplicate knowledge silo.Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.