Skills directory · page 25

Guides Microsoft Entra ID app registration, OAuth 2.0 authentication, and MSAL integration. USE FOR: create app registration, register Azure AD app, configure OAuth, set up authentication, add API permissions, generate service principal, MSAL example, console app auth, Entra ID setup, Azure AD authentication. DO NOT USE FOR: Key Vault secrets (use azure-keyvault-expiration-audit), general Azure resource security guidance.

Use when auditing .env files, planning credential rotation, chasing a missing env var in production or hardening a repo against leaked secrets. Scans for committed secrets and drift with env_auditor.py.

Guide developers through setting up development environments with proper tools, dependencies, and configurations

Use for any landing page, hero section or scroll-driven web design that should feel cinematic (parallax, scrollytelling, overlapping sections, text reveals, Apple-style animation), before coding. Inspects assets with inspect-assets.py, then builds with 45+ 2.5D techniques, no WebGL.

TypeScript、Python、Goにわたる堅牢なエラー処理のパターン。型付きエラー、エラー境界、リトライ、サーキットブレーカー、ユーザー向けエラーメッセージをカバーします。

Patterns for robust error handling across TypeScript, Python, and Go. Covers typed errors, error boundaries, retries, circuit breakers, and user-facing error messages. Use when designing error types, retries, circuit breakers, or user-facing failure messages in TypeScript, Python, or Go.

Deterministic method for placing signature, date, and text fields in a web e-signature composer through a browser automation session, using a fixed signature page, numeric Location panel coordinates instead of drag, and a save-as-draft default. Use when automating envelope preparation for generated agreements and you need repeatable field positions, correct per-recipient ownership, and a hard gate before anything is sent or signed.

Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel proteins; generating protein embeddings; performing inverse folding; or conducting protein engineering tasks. Supports both local model usage and cloud-based Forge API for scalable inference.

Phylogenetic tree toolkit (ETE). Tree manipulation (Newick/NHX), evolutionary event detection, orthology/paralogy, NCBI taxonomy, visualization (PDF/SVG), for phylogenomics.

Use for EU AI Act (Regulation 2024/1689) compliance work: classifying an AI system's risk tier, planning the Art. 43 conformity route and Annex IV file, or listing obligations by role. Runs ai_system_risk_classifier.py, conformity_assessment_planner.py and ai_act_obligation_tracker.py, citing Articles.

Rank finished AgentHub agents by metric or judge. Use when asked which agent won.

Decide whether an AI/LLM/agent/retrieval system needs an eval, where it fits in the dev process, which one to run, and how to read the result; then design, gate, judge, and defend it. Not ordinary unit tests.

Framework formal de evaluación para sesiones de Claude Code que implementa principios de desarrollo orientado a evals (EDD)

Eval-driven development (EDD) framework for AI coding sessions — define capability and regression evals before coding, grade with code-based, model-based, rule, or human graders, and track pass@k and pass^k reliability. Use when defining pass/fail criteria for agent tasks, measuring agent reliability, building regression suites for prompt or agent changes, or benchmarking across model versions.

Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles

Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles. Use when a Claude Code workflow needs a formal eval before it is trusted or changed.

Eval-driven development (EDD) ilkelerini uygulayan Claude Code oturumları için formal değerlendirme çerçevesi

Eval and improve a skill against golden cases — run the target skill blind in a fresh, context-free subagent on each example input, grade the artifact against a per-case bar, and let the gaps drive the edits. Use when the user wants to test/eval/improve/harden a skill, says "this skill keeps producing X / keeps missing Y", or hands a skill plus cases with a bar for what good looks like. Pairs with write-skills (the authoring principles every fix obeys). Judgment-first and harness-free — prefer skill-creator for harness-based benchmarking, variance analysis, or description-optimization loops.

Prove that a skill, rule or prompt changes what the agent does - blind prompts, runs with and without it, graded on outcomes, never on the agent's own account. Use when writing or changing a skill, an AGENTS.md or CLAUDE.md rule, a system prompt or a plugin.

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.

Expert in event sourcing, CQRS, and event-driven architecture patterns. Masters event store design, projection building, saga orchestration, and eventual consistency patterns. Use PROACTIVELY for event-sourced systems, audit trail requirements, or complex domain modeling with temporal queries.

Write an evidence-backed analytical report — Chinese policy briefs, capability assessments, or technical arguments that combine supplied claims with retrieved sources — by classifying every load-bearing number, building an evidence map, and drafting a uniform claim → evidence → mechanism → limitation spine. Use when the deliverable is prose whose every figure must survive an audit. Not for citation mechanics (that is grounded-citations), social posts, changelogs, or any piece where the claims are already verified and only the wording needs work.

State only what a dated source actually supports: fix the tense to the dateline, carry one provenance label across every surface, give every factual paragraph its own citation, and never let absence escalate into "does not exist". Use when writing or revising a knowledge page, monitor delta, entity section, or delivery table built from reports, press releases or partial legal text. Not for collecting or grading sources (that is claim auditing), and not for prose whose every claim is already primary-sourced.

Use for targeted EVM chain, account, transaction, RPC, explorer, bridge, and DEX evidence: chain name/ID, native symbol, RouteMesh, wallet balances and DeFi positions via DeBank/Blockscan in Chromium, cross-chain USD portfolio value or net worth, token/NFT holdings/transfers, tx history, funding origin via Etherscan/Blockscout/Chainscout. Covers Arbitrum canonical withdrawals, Across, Bungee, deBridge, Gas.zip, Hop, Layerswap, LayerZero, LI.FI, Relay, Socket, Symbiosis. Covers Uniswap v1-v4, Universal Router, Permit2, 1inch Classic/Fusion/Fusion+, and CoW Swap, CoWSwap, CoW Protocol, or GPv2 swaps, orders, liquidity, approvals, permits, rewards, migrations, wrapping, cancellations, and refunds.

Prevent silent decimal mismatch bugs across EVM chains. Covers runtime decimal lookup, chain-aware caching, bridged-token precision drift, and safe normalization for bots, dashboards, and DeFi tools. Use when handling token amounts across EVM chains, or when a balance, price, or transfer amount is off by orders of magnitude.

EVMチェーン全体でサイレントな小数点不一致バグを防ぐ。ランタイムでの小数点照会、チェーン対応キャッシング、ブリッジドトークンの精度ドリフト、ボット・ダッシュボード・DeFiツール向けの安全な正規化をカバーします。

Prevents silent decimal mismatch errors across EVM chains. Covers runtime decimal lookup, chain-aware caching, bridged token precision drift, and safe normalization for bots, dashboards, and DeFi tools.

Semantic search, similar content discovery, and structured research using Exa API

Neural search via Exa MCP, suitable for web, code, and company research. Use when the user needs web search, code examples, company intelligence, people lookup, or AI-driven deep research using the Exa neural search engine.

Neural search via Exa MCP for web, code, and company research. Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research with Exa's neural search engine.

Neural search via Exa MCP for web, code, and company research. Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research with Exa's neural search engine.

Exa MCPによるウェブ、コード、企業調査のためのニューラル検索。ユーザーがウェブ検索、コード例、企業情報、人物検索、またはExaのニューラル検索エンジンを使ったAI駆動の詳細調査を必要とする場合に使用します。

Use when working with *.excalidraw or *.excalidraw.json files, user mentions diagrams/flowcharts, or requests architecture visualization - delegates all Excalidraw operations to subagents to prevent context exhaustion from verbose JSON (single files: 4k-22k tokens, can exceed read limits)

Analyze Excel spreadsheets, create pivot tables, generate charts, and perform data analysis. Use when analyzing Excel files, spreadsheets, tabular data, or .xlsx files.

Use for /c-level-agents:execute, or to turn an approved decision into a 90-day plan with weekly milestones and owners.

Plans, creates, and optimizes marketing campaigns including content strategy, social media, email, and analytics. Helps develop go-to-market strategies, campaign messaging, and performance measurement.

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available

Implements a planned task test-first, through to a merge-ready PR. Use when the user is building what a plan describes. Not for one-off scripts.

Use when a founder or executive needs a plan stress-tested, a dreaded decision made, a hard board meeting prepared or an honest post-mortem. Adversarial thinking partner; scores options with decision_matrix_scorer.py and maps stakeholders with stakeholder_mapper.py.

Create C-suite and VP-level resumes emphasizing strategic leadership, P&L ownership, and board-level impact. Use when the user mentions executive, C-suite, CEO, CFO, CTO, VP, director, or senior leadership resume.

Plan A/B tests and product experiments: hypotheses, sample size, priority, reading results. Use whenever the user asks if a test won, how long to run it or what to test.

Explains how a website, a visual effect or an animation was built, from a live URL or a screenshot.

Creates a human-facing doc about a repo — pitch, deep-dive, interview prep, onboarding or status brief. Use when the user wants a repo explained. Not for finding bugs.

Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats. This skill should be used when analyzing any scientific data file to understand its structure, content, quality, and characteristics. Automatically detects file type and generates detailed markdown reports with format-specific analysis, quality metrics, and downstream analysis recommendations. Covers chemistry, bioinformatics, microscopy, spectroscopy, proteomics, metabolomics, and general scientific data formats.

Shapes a vague idea one question at a time with a decision log, then hands off to specify. Use when the user has an idea but no stated problem, or ideas to sort. Not for a stated problem.

Build animations in React Native and Expo, making the decisions in the order that determines whether they feel right — should it animate, which thread it runs on, which properties, spring or timing, how the gesture hands off, how it degrades. Writes the implementation with Reanimated, Gesture Handler, Expo Router and expo-haptics. Use when animating anything in an Expo app, adding gestures, sheets, screen transitions, press feedback or haptics, or fixing motion that stutters on device. For web animation use `animate`.

Add an iOS App Clip target to an Expo app. Use when the user mentions App Clip, AASA, apple-app-site-association, appclips, smart app banner, or wants to ship a lightweight iOS Clip invoked from a URL alongside their parent app.