spec-kitty-mission-review

Name: spec-kitty-mission-review
Availability: InStock
Author: kimprobably

Trace merged Spec Kitty mission implementations from spec artifacts to tests and code diffs.

Updated May 13, 2026

Search Tags:#security audit #traceability #release gating #spec-to-code #code drift #mission review #test adequacy

Ready to run

npx skills add https://github.com/kimprobably/maestro-os --skill spec-kitty-mission-review-kimprobably

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

It helps you determine whether a fully merged Spec Kitty mission actually matches the promised spec contract, including functional requirement coverage, drift from locked decisions, test adequacy, and hidden security risks.

Core Features & Use Cases

Spec-to-code evidence review: Traces each promised FR to the owning WP, the relevant tests, and the exact implementation diffs, looking for broken links in the delivery chain.
Drift and gap detection: Finds violations of non-goals and locked decisions and flags punted or uncovered approved FRs, including “passing test, failing system” patterns.
Operational risk and security scrutiny: Identifies boundary-condition failures, silent error/silent empty-result candidates, dead code risks, cross-WP integration gaps, and security issues around paths, subprocesses, HTTP calls, and locking.

Quick Start

Run a post-merge acceptance review for a merged mission by loading its mission spec artifacts and then auditing FR traceability, drift, risks, and security evidence before tagging a release.

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 feature implementation?▼

To verify spec-to-code fidelity after a merge, trace functional requirements and locked decisions from spec artifacts directly to owning work packages, test suites, and exact git diffs. This post-merge audit produces structured markdown evidence highlighting any broken links in the delivery chain.

What is a mission-level acceptance audit for release gating?▼

A mission-level acceptance audit is a post-merge review that confirms a fully merged implementation faithfully realizes its spec contract. It checks functional requirement coverage, identifies drift from locked decisions, evaluates test adequacy, and surfaces hidden security risks before tagging a release.

How do I detect code drift and hidden security risks in merged spec implementations?▼

Detect code drift and security risks by mapping git diffs to owned work and checking for violations of non-goals or locked decisions. The review flags boundary-condition failures, silent empty-result candidates, dead code, and security issues around paths, subprocesses, HTTP calls, and locking.

How do I trace functional requirements to tests and code diffs for coverage checks?▼

Trace functional requirements by absorbing spec, plan, task, and contract artifacts, then mapping each promised requirement to its owning work package and relevant tests. This cross-WP coverage check assesses FR trace quality and identifies punted or uncovered approved requirements.

Can I find passing test but failing system patterns during a post-merge code review?▼

Yes, this review specifically identifies "passing test, failing system" patterns. By adversarially verifying the implementation against the spec contract, it finds silent error candidates and cross-WP integration gaps that basic test suites might miss.

What do I need to run a spec-to-code traceability audit?▼

You need the merged mission implementation and its associated spec artifacts, including the mission identity, status, spec, plan, tasks, and contracts. The audit reads these inputs to perform FR trace quality assessment and output a structured markdown report with cited evidence.