Skill rating

Audits React code for performance, bundle size, and best practices. Use when reviewing React code, auditing bundle size, finding performance issues, checking React 18+ patterns, or evaluating a React

Mandatory adversarial review of all agent outputs. After drafting any response, a second AI instance (sub-agent) reviews and challenges the draft before delivery. Note: this sends draft text to the co

A comprehensive procurement coaching system designed for global buyers sourcing from 1688.com. Transform from novice to confident importer with practical frameworks for supplier assessment, strategic

Determine whether an incident in a clinical trial is a "major deviation" or "minor deviation". Function: Automatically classify protocol deviations in clinical trials based on GCP/ICH E6 standards, as

Use this skill when a quality engineer, supplier-quality engineer, or manufacturing engineer needs to draft an 8D corrective action report for a nonconformance, SCAR, customer complaint, or recurring

AI-powered code review assistant that analyzes pull requests, identifies potential bugs, security issues, code quality problems, and provides actionable improvement suggestions. Use when reviewing PRs

Self-contained PluginEval quality evaluation engine. Measures 6 dimensions, detects anti-patterns, assigns badges. No external dependencies.

Proactive context monitoring with smart 3-level alerts. Know when to restart before quality degrades.

Mandatory quality assurance for all dev work before publishing. Use BEFORE deploying any project to production. Validates build, tests browser functionality, checks mobile responsiveness, and ensures

ISO 9001:2015 Quality Management System implementation, internal audit, and CAPA management. Use when implementing a QMS from scratch, conducting gap assessment against ISO 9001:2015 clauses 4–10, pla

AI-powered manufacturing knowledge management. Search work orders, quality inspections, production schedules, and equipment maintenance records with structured extraction.

Machine-readable service contracts for autonomous AI agent commerce. Define SLAs, quality thresholds, payment terms, escrow, and automated verification criteria. Agents negotiate, sign, and enforce ag

Systematic task implementation using TDD, phase checkpoints, and structured commits. Ensures quality through red-green-refactor cycles, 80% coverage gates, and verification protocols before proceeding

Score an AI agent response 0-100 across 6 quality dimensions (depth, recommendations, citations, formatting, trust, monetization-readiness) with improvement suggestions. Use when evaluating agent outp

Six Sigma methodology reference — DMAIC process, statistical tools, control charts, and capability analysis. Use when running improvement projects, analyzing process variation, or preparing for Six Si

Use when you need a practical testing playbook for turning product or code changes into a clear test strategy, test cases, and execution checklist.

Prevent premature completion claims, repeated same-pattern retries, and weak handoffs. Use this skill to improve verification, strategy switching, and blocked-task reporting without changing personali

Deploy a quality assurance pipeline with 3 agents that automate test generation, execution, and reporting. Use this skill when: 1. User wants to set up an automated QA or testing pipeline 2. User is c

Review code for quality, security, and maintainability following team standards. Use when reviewing pull requests, examining code changes, or when the user asks for a code review.

Professional AI-powered translation with optional human verification. Supports 100+ languages. Quality boost for existing translations. Enterprise-grade security and privacy by straker.ai.

Use when composing multi-step DeFi workflows from FarmDash tools: plan, run, inspect supervised pipelines. Wallet steps stay policy-gated, preview-only.

Universal React dashboard audit — detect hardcoded values, tier bypasses, stale components, and onboarding inconsistencies before users see them.

Multi-asset investment portfolio management framework with A/B/C asset-class differentiated rules, 7 red-line portfolio risk controls, and 4-factor QMS quality scoring. Covers US, A-share (China), and

CPU-based autonomous optimization loop for skill quality improvement. Runs experiments, evaluates results, keeps improvements. Use when: 自主优化, skill optimization, 达尔文优化, autoresearch.

Skill discovery engine for AI coding agents. Recommends and installs the right skill when you need it — code review, test generation, debugging, commit messages, PR preparation, security scanning, dep

Diagnose why an AI response failed, identify missing context, and prepare a safer retry prompt with acceptance checks and a go/no-go recommendation.

用户在纠结"要不要装UV镜保护镜头"、问"UV镜有没有用"、或发现照片有炫光 想排查原因时调用。不适用于滤光镜创意使用（应调用其他滤光镜相关skill） 或纯器材购买建议。 Invoke when the user is debating "should I put a UV filter on my lens," asks "is a UV filter useful," or has lens

Autonomous skill optimizer inspired by Karpathy's autoresearch. 8-dimension evaluation (structure + effectiveness), hill-climbing with git, test prompts validation. Use when: optimize skill, skill eva

Peer review system for task results before acceptance. Use this skill when: 1. You need quality control on task results before accepting them 2. You want independent verification from trusted reviewer

Convert PDF to editable Word and automatically verify the conversion quality. Runs a four-way reconciliation (character count, table count, image count, table-cell count) plus a page-count reference a

Track sleep habits and analyze rest patterns over time. Use when logging bedtimes, planning schedules, tracking streaks, reviewing weekly patterns.

Audit code for "vibe coding sins" — patterns that indicate AI-generated code was accepted without proper review. Produces a scored report card with fix suggestions.

Write a factory acceptance test (FAT) plan or report — test coverage matrix against spec, AQL sampling plan, pass/fail criteria, golden-sample handling, deviation log, and sign-off structure. Use when

Write audit-safe NDIS progress notes with goal referencing, generate compliant shift note templates, identify correct support catalogue line item codes, and troubleshoot NDIS claiming errors for Austr

Finds what human code reviewers miss — not style issues or formatting, but logical errors, silent edge cases, performance cliffs, implicit assumptions, and the bugs that hide in code that "looks right

AI编程四大原则 - 源自Karpathy法则 (forrestchang/andrej-karpathy-skills 94.2k⭐)。用于在AI编程时强制执行先思考、保持简单、精准修改、目标驱动四大原则。适用于AI代码审查、代码生成、修复bug等场景。

Guides structured help for Code Review Checklist using clear templates, checks, and safe defaults (category: Software Quality).

知识技能型 Skill 创建流水线。将官方文档蒸馏为结构化知识技能的完整方法论——从源分析、爬取/蒸馏、内容结构化、评估打分到 A 级达成。当用户要求创建 skill、蒸馏知识技能、整理 skill、提升 skill 质量、评估 skill 分数时触发。

Skill Quality Evaluator - Score any skill on 6 dimensions. Catch 30% of skills that look good but fail silently. Based on Tessl Research 2026 findings.

Guides structured help for Bug Report Formatter using clear templates, checks, and safe defaults (category: Software Quality).

Experiential benchmark for AI reasoning — measures calibration, epistemic flexibility, risk assessment, and metacognition through interactive concert experiences. Agents stream mathematical data, resp

Stop AI agents from secretly bypassing your rules. Mechanical enforcement with git hooks, secret detection, deployment verification, and import registries. Born from real production incidents: server

Systematic debugging framework. 4-phase root-cause analysis with defense-in-depth. Never guess, never patch symptoms. From Claude Code + Superpowers.

Editorial Refinement Engine — transforms LLM-generated text into editorially refined prose: more natural, less predictable, with varied rhythm, lexicon, structure and style, preserving facts, entities

电机装配工艺助手 | 生成军用电机装配作业指导书，覆盖转子装配、定子嵌线、轴承装配、动平衡、终检全流程

Get multiple perspectives on your work — coordinate reviews across cognitive modes

军用电机质量检验助手 | 根据GJB标准生成检验规程，覆盖来料检验、过程检验、成品检验、出厂检验全流程

Remove AI-generated jargon and restore human voice to text. Built from analyzing 1,000+ AI vs human content pieces.

Three-tier code quality defense: L1 quick scan, L2 deep audit (via bug-audit), L3 cross-validation with adversarial testing. 三级代码质量防线。

面向A股个股财务质量分析，聚焦盈利能力、利润质量、成长持续性、现金流与财务安全性。基于今日投资金融数据接口，自动识别股票代码并输出结构化财务分析报告。触发词：财务分析、盈利能力、现金流、资产负债、偿债能力、利润质量。