17th-task-inspector

Name: 17th-task-inspector
Availability: InStock
Author: seventeenthearth

Inspect implementation compliance against TASK.md and produce a PASS/FAIL verdict report.

Updated Jan 23, 2026

Search Tags:#verification #code-review #cross-model #inspect #GPT-5.2-Codex #TASK.md

Ready to run

npx skills add https://github.com/SeventeenthEarth/glm-worker-mcp --skill 17th-task-inspector

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: 17th-task-inspector
Source: https://github.com/SeventeenthEarth/glm-worker-mcp/tree/main/skills/17th-task-inspector
Command: npx skills add https://github.com/SeventeenthEarth/glm-worker-mcp --skill 17th-task-inspector

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill performs deep inspection of an implementation against a TASK.md specification using GPT-5.2-Codex, delivering a robust pass/fail assessment and remediation guidance.

Core Features & Use Cases

Deep cross-model verification: Validates code semantics against the TASK.md with GPT-5.2-Codex and an optional secondary model for comparison.
Structured verdicts: Produces a clear PASS / PARTIAL / FAIL verdict with a reason and recommended actions.
Use Case: Before declaring project completion, run this skill to ensure all critical requirements are satisfied and risk is minimized.

Quick Start

Use the 17th-task-inspector to validate the current implementation against TASK.md and generate the inspection report.

Frequently Asked Questions about 17th-task-inspector

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

FAQPage Schema

How do I verify code implementation against TASK.md specifications?▼

Verifying code against TASK.md involves inspecting implementation compliance for critical features and edge cases, producing a formal PASS/FAIL verdict with rationale and remediation notes suitable for PR review.

What is cross-model code review for pass/fail criteria?▼

Cross-model code review validates code semantics against TASK.md using GPT-5.2-Codex and an optional secondary model, comparing outputs to ensure all critical requirements and pass/fail criteria are satisfied before project completion.

How do I generate a PR review report with a PASS or FAIL verdict?▼

Generating a PR review report requires inspecting implementation compliance against TASK.md, evaluating critical features and edge cases, then outputting a detailed archival report with a structured PASS, PARTIAL, or FAIL verdict and recommended actions.

Can I use GPT-5.2-Codex to inspect edge cases in my codebase?▼

Yes, GPT-5.2-Codex can inspect codebase edge cases by validating implementation compliance against TASK.md scope, identifying potential failures, and providing remediation guidance to minimize project risk.

When do I need a formal pass/fail assessment for code review?▼

A formal pass/fail assessment is needed before declaring project completion to ensure all critical TASK.md requirements are satisfied, verify edge cases, and produce a structured verdict with rationale for archival and PR review.

Does cross-model verification work without dependencies?▼

Cross-model verification operates with no dependencies, using GPT-5.2-Codex as the primary model and an optional secondary model to compare code semantics against TASK.md specifications for a robust compliance assessment.