knowledge-router

Build a lightweight routing layer across existing knowledge sources such as MEMORY.md, daily memory files, self-improving notes, skill references, and audit records. Use when you need to decide where a question should be answered from before reading too much, when you want a unified knowledge index, or when you want to detect which knowledge should be promoted into a more durable layer.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "knowledge-router" with this command: npx skills add lethehades/knowledge-router

Knowledge Router

Route queries to the right knowledge layer before doing broad reading.

Core workflow

  1. Scan known knowledge sources and classify them by role.
  2. Infer the query intent: rule, fact, method, evidence, or improvement.
  3. Recommend primary and secondary sources.
  4. Emit promotion hints when knowledge seems mature enough to move upward into a more durable layer.

Read references as needed

  • Read references/source-types.md for the knowledge source model.
  • Read references/routing-rules.md for intent-to-source routing rules.
  • Read references/promotion-rules.md for when knowledge should be promoted or extracted.
  • Read references/report-format.md for the report structure.
  • Read references/release-minimal.md before packaging or publishing so the first public surface stays minimal.

Use scripts as needed

  • Use scripts/knowledge_router.py "<query>" [--scope ...] [--output report.txt] to build a routing report.

Operating rules

  • Prefer routing over re-storing knowledge.
  • Prefer a small number of clearly justified sources over broad search noise.
  • Treat audit logs as evidence, not as the first answer source for general method questions.
  • Keep the first version focused on source typing, query intent, and recommendation quality.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Security

Flue — Desktop Software Bridge

Flue is a lightweight bridge enabling command-line control of professional desktop software by executing scripts inside the app's automation runtime and retu...

Registry SourceRecently Updated
Security

Trent OpenClaw Security Assessment

Assess your Agent deployment against security risks using Trent.

Registry SourceRecently Updated
Security

TrustBoost PII Sanitizer

Sanitizes PII from text before sending to LLMs. Use when handling user-generated text that may contain sensitive data, when privacy compliance is required (G...

Registry SourceRecently Updated
1350Profile unavailable
Security

Agent Causal

Helps decide to ship, continue, or roll back changes from A/B test and DiD data by providing statistical analysis, decisions, and audit trails.

Registry SourceRecently Updated
900Profile unavailable