SkillVaultskills Browse all 1,000+ skills

Productivity · Version 1.1.0 · Reviewed 2026-08-02

Pull Request Media Curator

Turn engineering context into a reliable artifact for visual evidence selection and sensitive-data redaction with evidence, explicit trade-offs, and a verification plan.

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

Selects, redacts, captions, and sequences screenshots or recordings that demonstrate a UI change across required states without exposing customer or credential data.

₹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

  • Visual evidence selection
  • Sensitive-data redaction
  • Before-and-after captioning

How Pull Request Media Curator works

You provide

Repository access, entry points, and the target change

It inspects

Real execution path for visual evidence selection, not naming

It decides

A sensitive-data redaction explanation with safe change seams

You verify

Claims confirmed against code paths or a test

What it checks first

Pull Request Media Curator selects, redacts, captions, and sequences screenshots or recordings that demonstrate a UI change across required states without exposing customer or credential data. Use it when the work involves Visual evidence selection, Sensitive-data redaction, Before-and-after captioning.

  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 visual evidence selection from the supplied evidence, and mark what is missing.
  2. Identify the mechanism behind sensitive-data redaction rather than restating the symptom.
  3. Choose the smallest defensible change for before-and-after captioning, weighing impact, confidence, effort, and reversibility.
  4. Check every claim against the source

Deliverables

  • Visual evidence selection assessment
  • Sensitive-data redaction decision and action plan
  • Before-and-after captioning 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

Prepare the screenshots for this UI pull request so reviewers can compare desktop, mobile, loading, error, and keyboard-focus behavior.

Expected output

Capture matched viewport and data states, label before and after clearly, and include the interaction that changed rather than only the polished endpoint. Redact identifiers and tokens at the source, verify focus and reflow remain visible, and omit redundant images that add no review evidence...

Boundaries and compatibility

Ideal for

  • Visual evidence selection: produce a decision or artifact grounded in supplied evidence.
  • Sensitive-data redaction: produce a decision or artifact grounded in supplied evidence.
  • Before-and-after captioning: 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.