Knowledge base
Skill yigityildiz0/universal-ai-skill-library/skills/common/knowledge-base
531 searchable AI Agent Skills for Claude Code, OpenAI Codex, and OpenCode — EN/TR catalog, platform and risk notes, direct ZIPs, and curated bundles.
npx -y skills add yigityildiz0/universal-ai-skill-library --skill knowledge-baseAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
3 things to look at
- 18 days oldThe repository was created 18 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Create, organize, audit, or maintain a durable Markdown knowledge base with an index, atomic notes, stable identifiers, links, tags, and maintenance checks. Use for a personal or team knowledge base, research vault, documentation library, MOC, note organization, broken links, or knowledge-base cleanup; do not confuse it with short-term agent memory.
SKILL.md
1.8 KB, 292 tokens by cl100k_base, as published. Nobody here has run it
Knowledge Base
Build a user-owned, navigable knowledge system. k-mem handles recurring working context; this skill handles durable documents and notes the user can inspect and own.
Start safely
Ask for the intended root folder and allowed sources. Do not scan the whole disk, unrelated projects, mail, or cloud services. Preserve existing structure unless a migration is explicitly requested.
Structure
- Create or repair a concise
INDEX.mdwith entry points, scope, and maintenance date. - Keep notes atomic: one durable concept, decision, procedure, or source synthesis per note.
- Use stable, human-readable IDs or slugs. Avoid timestamp-only names when notes will be referenced later.
- Record source/provenance, confidence, and update date for claims that can become stale.
- Link notes with a brief relationship reason; use a controlled tag vocabulary rather than uncontrolled tag sprawl.
- Use topic maps/MOCs only where navigation improves retrieval.
Maintenance pass
Check for broken links, duplicate notes, orphan notes, stale indexes, empty tags, and claims that need source review. Propose changes before mass moves, renames, or deletions.
Guardrails
- Do not persist hidden user profiles or personal data without clear consent.
- Never claim that note links prove truth; preserve uncertainty and source context.
- Keep imports reversible and provide a migration map for any structural change.