spec-kitty-mission-review

Review merged Spec Kitty missions for spec-to-code fidelity and risks.

1|Updated Sep 19, 2025

Search Tags:#security review #code audit #spec-to-code #drift analysis #spec-kitty #mission review #fr-traceability

Ready to run

npx skills add https://github.com/kentonium3/kg-automation --skill spec-kitty-mission-review

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: spec-kitty-mission-review
Source: https://github.com/kentonium3/kg-automation/tree/main/.claude/skills/spec-kitty-mission-review
Command: npx skills add https://github.com/kentonium3/kg-automation --skill spec-kitty-mission-review

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a structured, adversarial post-merge review to determine whether a completed Spec Kitty mission's merged code faithfully and completely implements the specification, and to surface unstated risks or gaps before release.

Core Features & Use Cases

FR traceability: map each Functional Requirement from spec to owning WP, test(s), and implementation diffs.
Review history and coverage: analyze WP review cycles, event logs, and git diffs to find unresolved review items and missing changes.
Drift, risk, and security analysis: detect locked-decision violations, non-goal invasions, boundary-condition risks, error-paths, dead code, and security issues like subprocess or path risks.
Deliverable report: produce a self-contained, evidence-backed markdown mission review report with findings, severity, and a final pass/fail verdict for release gating.

Quick Start

Review the merged mission 'my-mission-slug' and produce a structured spec-to-code fidelity and risk report.

Frequently Asked Questions about spec-kitty-mission-review

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

FAQPage Schema

How do I verify spec-to-code fidelity after merging a completed specification mission?▼

To verify spec-to-code fidelity after merging, you need an adversarial post-merge audit that maps each functional requirement to owning work packages, tests, and implementation diffs to detect drift and surface unstated risks before release.

What is an adversarial post-merge code audit for functional requirement traceability?▼

An adversarial post-merge code audit for functional requirement traceability is a structured review process that analyzes merged code against its original specification, ensuring every requirement is backed by test evidence and checking for locked-decision violations or non-goal invasions.

How do I detect specification drift and security risks in merged code before tagging a release?▼

To detect specification drift and security risks before tagging a release, analyze git diffs and event logs to identify boundary-condition risks, error-paths, dead code, and subprocess or path risks, then compile the findings into an evidence-backed report.

Can I map functional requirements directly to git diffs and tests for a completed mission?▼

Yes, you can map functional requirements directly to git diffs and tests by reviewing merged work packages and event logs, producing a self-contained markdown report that cites specific git diffs to verify complete implementation of the specification.

What is the best way to generate an evidence-backed pass/fail verdict for a release gate?▼

The best way to generate an evidence-backed pass/fail verdict for a release gate is to perform a comprehensive cross-work-package integration check, enumerate all drift and risk findings with severity levels, and map them directly to functional requirements and test coverage.

When should I not use a post-merge spec-to-code fidelity audit?▼

You should not use a post-merge spec-to-code fidelity audit on incomplete missions, as the process requires all work packages to be marked done and fully merged to accurately analyze cross-work-package integration, trace functional requirements, and detect specification drift.