Quality

Evaluates AI agent skills in isolation to measure activation accuracy, outcome quality, and false-activation avoidance. Use for regression testing and baseline uplift evidence.

Audits and scores Amazon listings across four engines (CDQ, A9, COSMO, Alexa) for content quality, indexability, intent coverage, and Alexa discoverability, plus a compliance check. Outputs a health report with prioritized fixes. Does not rewrite copy.

Audits one skill or a skill library for structural, safety, linkage, size, and trigger-boundary issues. Provides evidence-backed findings without modifying files.

Enforces the First-Time Principle for AI-assisted development: write code, docs, and memory as if from scratch, avoiding patches, residue, and drift. Use when starting any implementation, refactor, or bug fix to maintain codebase purity.

A toolkit for reviewing AI-generated text, code, and citations. Detects padding, vendor residue, and vague language, and verifies references with deterministic scanners and structural tests.

Scaffolds and operates an Obsidian vault-based brain that detects and repairs AI slop in prose, code, documentation, and agent output, relying on corpus evidence instead of authorship detection. Use it for quality assurance in AI-generated content.

Scans codebases for common AI-generated code patterns like duplicated helpers, try-import fallbacks, and speculative abstractions. Helps clean up AI slop through guided refactoring with test safety.

Code Review reviews changes since a fixed point along Standards and Spec axes. Use it for branch, PR, or work-in-progress reviews, including requests to review since a given commit or tag.

Diagnosing Bugs helps you build tight repro loops for hard bugs, failures, and performance regressions. Use it when debugging broken, throwing, failing, or slow behavior and you need to isolate the cause.

Reviews videos, images, posts, audio, articles, subtitles, and live scripts before publishing to Douyin, Xiaohongshu, Weixin Video Accounts, or Kuaishou. Use it to check risk, required disclosures, sources, rights, and platform-specific edits.

Reviews AI-generated code for quality defects like hallucinated imports, ceremonial comments, and non-functional tests. Runs deterministic scanners and load-bearing tests to report impact-based severity without authorship claims.

Diagnoses prose quality issues like fabricated facts, padding, and stylistic tells, producing a structured findings report with severity and confidence ratings. Used for reviewing drafts, documents, agent output, commit messages, and more.