SkillVaultskills Browse all 1,000+ skills

Productivity · Version 1.3.0 · Reviewed 2026-08-02

Repository Knowledge Router

Turn engineering context into a reliable artifact for path-to-knowledge mapping and context retrieval routing with evidence, explicit trade-offs, and a verification plan.

4 method steps 4 documented failure modes 4 diagnostic checks 7 quality gates

Routes changed files and engineering questions to the smallest relevant set of architecture, policy, and domain knowledge. It grounds the decision in repository paths, ownership, instruction files, architecture documents, rule metadata, and representative questions and explicitly prevents loading every knowledge file for every task, causing conflicts, context waste, and stale guidance leakage.

₹199 one-time

Get this skill archive

Install in your AI coding tool

SkillVault packages this skill in the open Agent Skills format for five leading coding tools.

What this skill helps you do

  • Path-to-knowledge mapping
  • Context retrieval routing
  • Knowledge overlap detection

How Repository Knowledge Router works

You provide

Repository access, entry points, and the target change

It inspects

Real execution path for path-to-knowledge mapping, not naming

It decides

A context retrieval routing explanation with safe change seams

You verify

Claims confirmed against code paths or a test

What it checks first

Repository Knowledge Router routes changed files and engineering questions to the smallest relevant set of architecture, policy, and domain knowledge. It grounds the decision in repository paths, ownership, instruction files, architecture documents, rule metadata, and representative questions and explicitly prevents loading every knowledge file for every task, causing conflicts, context waste, and stale guidance leakage. Use it when the work involves Path-to-knowledge mapping, Context retrieval routing, Knowledge overlap detection.

  1. The entry points and the data flow between them, which is the fastest way to build an accurate mental model.
  2. Where behavior is actually decided, rather than where it appears to be configured.
  3. Which parts change frequently, since those carry the most current knowledge and the most risk.
  4. The seams where a change can be made safely without a wide blast radius.

Failure modes it recognizes

  • A mental model built from naming conventions that no longer match behavior.
  • Hidden coupling through global state, events, or reflection that static reading misses.
  • Dead code that appears authoritative and misleads the reader.
  • Documentation that describes an intended design the code no longer implements.

Answers it will reject

  • Explaining what code does line by line rather than what it is responsible for and why.
  • Trusting comments and documentation over the executing code path.
  • Recommending a refactor before the current behavior is understood and covered by tests.

Decision rules it applies

  • Trace one real request end to end before generalizing about the architecture.
  • Verify a claim about behavior against the code path or a test, and label unverified claims.
  • Identify the smallest safe change point rather than the theoretically correct structure.

Evidence it asks for

  • Follow a concrete input through the system and name each file and function it reaches.
  • Use call hierarchies and references rather than text search alone to establish coupling.
  • Confirm behavior with an executable test before changing it.

The method inside

  1. Establish what is actually true about path-to-knowledge mapping from the supplied evidence, and mark what is missing.
  2. Identify the mechanism behind context retrieval routing rather than restating the symptom.
  3. Choose the smallest defensible change for knowledge overlap detection, weighing impact, confidence, effort, and reversibility.
  4. Check every claim against the source

Deliverables

  • Path-to-knowledge mapping assessment
  • Context retrieval routing decision and action plan
  • Knowledge overlap detection verification checklist

Evidence requirements

  • Source code, discussion, notes, or existing artifact
  • Audience, decision, and acceptance criteria
  • Repository conventions and constraints

Quality gates

  • Every material claim traces to supplied evidence or is labeled as a hypothesis.
  • The response follows the declared deliverable contract.
  • No execution, access, measurement, or verification is invented.
  • Secrets and personal data are redacted rather than repeated.
  • The user receives a concrete independent verification step.
  • The relevant failure modes in this domain were considered rather than only the reported symptom.
  • No listed anti-pattern was recommended as a solution.

Example task

Input

Apply the repository knowledge router to our current path-to-knowledge mapping work. We need a concrete decision, bounded changes, and evidence that the result is correct.

Expected output

Start with repository paths, ownership, instruction files, architecture documents, rule metadata, and representative questions. The highest-risk failure is loading every knowledge file for every task, causing conflicts, context waste, and stale guidance leakage. Prefer deterministic path and symbol rules, then use semantic fallback only when the route remains ambiguous. Verify the result by running a labeled question and change-set corpus and checking both missed context and unnecessary context.

Boundaries and compatibility

Ideal for

  • Path-to-knowledge mapping: produce a decision or artifact grounded in supplied evidence.
  • Context retrieval routing: produce a decision or artifact grounded in supplied evidence.
  • Knowledge overlap detection: produce a decision or artifact grounded in supplied evidence.

Out of scope

  • Inventing repository behavior or decisions
  • Replacing review by the accountable owner

Agent compatibility

  • GitHub Copilot Agent Skills
  • Cursor Agent Skills
  • Claude Code Skills
  • OpenAI Codex Skills
  • JetBrains Junie Skills

Tool policy: Advisory by default. No tools are assumed. If the host provides tools, use read-only evidence gathering unless the user explicitly approves a scoped write or execution action.