One-click install
npx skills add https://github.com/Dicklesworthstone/eidetic_engine_cli --skill claim-certificate-review
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: claim-certificate-review
Source: https://github.com/Dicklesworthstone/eidetic_engine_cli/tree/main/skills/claim-certificate-review
Command: npx skills add https://github.com/Dicklesworthstone/eidetic_engine_cli --skill claim-certificate-review

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill helps you determine whether an ee claim or certificate verification report is persuasive and documentation-ready, while keeping the judgment bounded to what the mechanical evidence actually verified.

Core Features & Use Cases

  • Evidence-bounded review: Consumes only ee-generated machine JSON and side-path artifacts, separating verified facts from analyst judgment and overclaim risk.
  • Stop/Go safety gates: Blocks strengthening when hash/schema/expiry/assumption/redaction/prompt-injection quarantine requirements are missing, failed, stale, ambiguous, or degraded.
  • Explainable disposition output: Produces a structured claim-review artifact describing evidence bundle provenance, failed checks, assumptions, and a bounded review posture.

Quick Start

Use this skill when you already have ee claim or certificate verification JSON and artifacts for the target workspace, so you can ask for an evidence-bounded review of whether the claim/certificate is stale, overbroad, expired, assumption-bound, or missing evidence.

Frequently Asked Questions about claim-certificate-review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I review certificate verification JSON while separating verified facts from analyst judgment?

Evidence-bounded review consumes machine-generated verification JSON and side-path artifacts, separating mechanically verified facts from bounded analyst judgment and overclaim risk to produce documentation-ready claim assessments.

What happens during certificate verification when hash, schema, or expiry checks fail or degrade?

Stop/go safety gates block claim strengthening when hash, schema, expiry, assumption, redaction, or prompt-injection quarantine requirements are missing, failed, stale, ambiguous, or degraded, ensuring review posture remains bounded.

How do I detect stale or expired claims in a certificate verification report?

Staleness detection evaluates expiry data within verification JSON to identify stale, expired, or overbroad claims, applying explicit stop/go gates to block assessment when expiry evidence is degraded or ambiguous.

Can I use this evidence review approach for release-note-ready documentation of mechanically verified manifests?

Yes, evidence-bounded review produces structured claim-review artifacts describing evidence bundle provenance, failed checks, and assumptions, yielding documentation- or release-note-ready assessment of persuasive strength for verified manifests.

What do I need before starting a claims audit on ee certificate verification results?

You need ee-generated verification JSON and artifacts for the target workspace, as the review enforces workspace-scoped consumption and parseable JSON requirements to assess evidence bundle provenance and review posture.

Why does my claims audit require prompt-injection quarantine during evidence review?

Prompt-injection quarantine acts as a safety gate to prevent untrusted content in verification artifacts from compromising the bounded judgment process, blocking claim strengthening when quarantine requirements are missing or failed.