// AI Reviewed Skills
Skills evaluated and scored by AI for quality and usefulness
Each skill has been evaluated by an AI reviewer on a structured rubric: instruction quality, usefulness, technical soundness, and description precision. Scores range from 0 to 100 — skills scoring 75+ (green badge) are high quality, 50–74 (gold badge) are solid with targeted value.
View Review StatisticsShowing 1-12 of 13948 skills
Custom hook and composable patterns — naming, composition, stable return shapes, lifecycle cleanup, and testing strategies. Use when writing reusable logic units (React hooks, Vue composables), refactoring logic into hooks, debugging hook behavior, or reviewing hook implementations.
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.
Implement PCI DSS compliance requirements for secure handling of payment card data and payment systems. Use when securing payment processing, achieving PCI compliance, or implementing payment card security measures.
SkillsBench contribution workflow. Use when: (1) Creating benchmark tasks, (2) Understanding repo structure, (3) Preparing PRs for task submission.
Use when you see 'actor-isolated', 'Sendable', 'data race', '@MainActor' errors, or when asking 'why is this not thread safe', 'how do I use async/await', 'what is @MainActor for', 'my app is crashing with concurrency errors', 'how do I fix data races' - Swift 6 strict concurrency patterns with actor isolation and async/await
Use when implementing privacy manifests, requesting permissions, App Tracking Transparency UX, or preparing Privacy Nutrition Labels - covers just-in-time permission requests, tracking domain management, and Required Reason APIs from WWDC 2023
Use when auditing content pages for citation quality, suggesting authoritative sources to link for factual claims, or reviewing whether a page's external link attributes (nofollow, noopener) are correctly set.
The encrypted social network for AI agents. Post, comment, upvote, and create communities with E2E encrypted private groups.
Chat with your finances from Treeline Money. Query balances, spending, budgets, and transactions.
Migrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
Triage a dotnet/source-build GitHub issue. Reads the issue body, classifies it by area/kind/severity, checks for blocking impact, suggests an owner based on recent issue activity, and posts a structured triage comment in restricted mode. Use when asked "triage issue", "triage #1234", "classify this issue", or "run triage pass".
Page 1 of 1163
