Keyboard shortcuts

Press or to navigate between chapters

Press S or / to search in the book

Press ? to show this help

Press Esc to hide this help

Trust System

LibSkills uses a multi-axis trust system to help AI agents decide how much to trust a skill.

Axes

Tier (Quality)

TierWhoReviewTrust Range
Tier 1LibSkills maintainersFull accuracy audit90–100
Tier 2CommunityFormat + safety check50–89

Upgrading: Tier 2 → Tier 1 requires 2 maintainer approvals and a full accuracy review.

Group (Popularity)

GroupCriteria
Main10,000+ GitHub stars OR ecosystem standard OR dependency of 5+ main-group libraries
ContribAll other libraries

Trust Score (0–100)

Calculated from 5 components:

ComponentMaxSource
Official Review40Tier 1 maintainer review
Stars20GitHub stars tier (10K+ = 20, 5K+ = 15, 1K+ = 10, <1K = 5)
Community Votes20User ratings and usage signals
Update Freshness15Skill updated within 60 days of library release
Issue Health5Low open issue count relative to stars

Interpretation:

ScoreMeaning
95–100Gold standard — fully verified, actively maintained
80–94High quality — reviewed but minor gaps possible
60–79Community — useful but not fully audited
0–59Draft — minimal validation

Risk Level

LevelMeaningAI Priority
highMisuse causes crashes, data corruption, or security issuesAI MUST read P0 files
mediumMisuse causes bugs or unexpected behaviorAI SHOULD read P0 files
lowMisuse causes suboptimal but correct behaviorAI MAY read P0 files

repo_skill — Self-Hosted Trust

When repo_skill: true, the skill lives in the library’s own repository (.libskills/). This carries inherent trust:

  • The library maintainers endorse the skill
  • Updates track library releases naturally
  • Content is versioned alongside the code

Registry-only skills (repo_skill: false) start at a lower trust baseline.

For AI Agents

When consuming a skill, AI agents should:

  1. Prefer Tier 1 over Tier 2 — higher review confidence
  2. Respect risk_level — high-risk libraries require mandatory P0 reading
  3. Check trust_score — scores < 50 suggest the skill needs verification before relying on it
  4. Prefer repo_skill=true — maintained alongside the library
  5. Check updated_at — stale skills may describe outdated APIs