SkillVaultskills Browse all 500 skills

Maintenance · Version 1.3.0 · Reviewed 2026-08-02

Documentation Decay Auditor

Reduce change risk for staleness detection and impact ranking with evidence, explicit trade-offs, and a verification plan.

4 method steps 5 documented failure modes 5 diagnostic checks 7 quality gates

Finds documentation that has silently diverged from the system and prioritizes what to fix or delete.

₹149 one-time

Get this skill archive

What this skill helps you do

  • Staleness detection
  • Impact ranking
  • Deletion decisions

How Documentation Decay Auditor works

You provide

Obligations, data inventory, and current controls

It inspects

Requirement type and implemented control for staleness detection

It decides

A impact ranking gap register with accountable owners

You verify

Each control mapped to evidence an auditor would accept

What it checks first

Documentation Decay Auditor finds documentation that has silently diverged from the system and prioritizes what to fix or delete. Use it when the work involves Staleness detection, Impact ranking, Deletion decisions.

  1. Whether the obligation is a legal requirement, a contractual commitment, or an internal policy — the escalation path differs.
  2. The specific data categories and lawful basis, rather than a general statement about compliance.
  3. Data flows across jurisdictions and processors, which determine transfer obligations.
  4. Retention and deletion behavior in every downstream copy, including backups and analytics.
  5. Who is accountable for the decision, since a compliance analysis without an owner is not actionable.

Failure modes it recognizes

  • Deletion implemented in the primary store while copies persist in backups, exports, logs, and warehouses.
  • Consent collected for one purpose and reused for another without a valid basis.
  • A subprocessor added without a data-processing agreement or customer notification.
  • Retention policy defined but never enforced by an automated job.
  • A control documented in policy but not implemented in the system it describes.

Answers it will reject

  • Providing a definitive legal conclusion rather than a structured analysis for qualified review.
  • Treating a compliance certification as evidence that a specific control works.
  • Relying on contractual language to mitigate a technical risk that is technically preventable.
  • Presenting risk without severity, likelihood, and the accountable owner.

Decision rules it applies

  • Separate legal requirement, contractual obligation, and internal policy in every finding.
  • Escalate to qualified counsel for anything that constitutes legal advice, and say so plainly.
  • Map every obligation to a specific implemented control and its evidence, or mark it as a gap.
  • Prefer technical enforcement over documented intent, because documented intent is not a control.

Evidence it asks for

  • Build a data inventory: category, source, purpose, basis, location, retention, and downstream copies.
  • Trace one deletion request end to end and enumerate every store it must reach.
  • Record the evidence artifact that would satisfy an auditor for each control.

The method inside

  1. Map the artifact, actors, boundaries, and invariants relevant to staleness detection.
  2. Trace concrete failure or abuse paths for impact ranking; do not report checklist items without a mechanism.
  3. Prioritize deletion decisions findings by impact, likelihood, confidence, and cost of correction.
  4. Recommend the smallest defensible change, then define how an independent reviewer can verify it.

Deliverables

  • Staleness detection assessment
  • Impact ranking decision and action plan
  • Deletion decisions verification checklist

Evidence requirements

  • Current and target versions
  • Dependency graph and changelogs
  • Tests, compatibility constraints, and rollout environment

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

Our internal docs are large and partially wrong, and people have stopped trusting any of it.

Expected output

Partial correctness is worse than absence because readers cannot tell which parts to trust. Rank by traffic and consequence, verify the top pages against the system, and delete rather than preserve anything unverifiable, since deletion restores trust faster than rewriting...

Boundaries and compatibility

Ideal for

  • Staleness detection: produce a decision or artifact grounded in supplied evidence.
  • Impact ranking: produce a decision or artifact grounded in supplied evidence.
  • Deletion decisions: produce a decision or artifact grounded in supplied evidence.

Out of scope

  • Blindly upgrading across multiple major versions
  • Assuming semantic versioning guarantees compatibility

Agent compatibility

  • GitHub Copilot custom agents
  • Claude Agent Skills / SKILL.md
  • Any instruction-following chat model

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.