Formats citations and validates source attribution for answers generated from multiple document sources (ChromaDB and web search).
Score 70/100
Use when drafting or verifying content requiring source integrity - enforces strategic quoting with inline links and blocks "(source needed)" markers from draft completion
Score 70/100
Extract and validate citations with Jaccard overlap calculation. Ensures all claims have verifiable source evidence with ≥0.7 alignment threshold.
Score 70/100
Selecting a reference manager and applying citation styles. Compares Zotero, Mendeley, EndNote, Paperpile; covers APA/Vancouver/ACS/Nature styles, DOI management, citation…
Score 70/100
Build and visualize a citation network from a source/target CSV to identify key papers, communities, and emerging hotspots; use when you have citation pairs and need fast…
Score 70/100
Format citations, footnotes, and bibliographies following Chicago, MLA, and disciplinary style guides with accuracy
Score 70/100
Verify whether cited public sources support specific OpenOnco claims for one chunk manifest, and emit a structured `citation-report.yaml` for maintainer review.
Score 70/100
Comprehensive Citrix environment health assessment and diagnostics. Use when analyzing Citrix site health, checking VDA registration status, verifying Delivery Controller…
Score 70/100
Comprehensive Citrix Provisioning Services (PVS) expertise for infrastructure management, troubleshooting, and optimization.
Score 70/100
Systematic Citrix issue diagnosis and resolution. Use when troubleshooting VDA registration failures, session launch problems, application errors, performance issues, or…
Score 70/100
Debug complex Claude issues — inconsistent outputs, tool use failures, Use when working with advanced-troubleshooting patterns. streaming problems, and edge cases.
Score 70/100
Diagnose and fix Anthropic API errors — authentication, rate limits, Use when working with common-errors patterns. overloaded, context length, and content policy issues.
Score 70/100
Redirect to claude-model-inference for Messages API streaming, vision, and structured output patterns. Use when looking for the primary Anthropic workflow.
Score 70/100
Redirect to claude-embeddings-search for tool use (function calling) and agentic loop patterns with Claude. Use when looking for the secondary Anthropic workflow.
Score 70/100
Handle sensitive data with Claude — PII redaction, conversation management, Use when working with data-handling patterns. context window optimization, and data retention policies.
Score 70/100
Implement tool use (function calling) with Claude to let it execute actions, Use when working with embeddings-search patterns.
Score 70/100
Respond to Anthropic API incidents — outages, degraded performance, Use when working with incident-runbook patterns. error spikes, and rate limit issues in production.
Score 70/100
Install and configure the Anthropic SDK for Claude API access. Use when setting up Claude integration, configuring API keys, or initializing the Anthropic client in your project.
Score 70/100
Common mistakes when building with the Anthropic API and how to avoid them. Use when working with known-pitfalls patterns.
Score 70/100
Scale Claude usage for high-throughput applications — batches, queues, Use when working with load-scale patterns. concurrency control, and tier upgrades.
Score 70/100
Set up a fast local development loop for building with the Anthropic API — Use when working with local-dev-loop patterns. hot reload, cost-saving tips, and test patterns.
Score 70/100
Migrate from OpenAI/GPT to Anthropic/Claude — API differences, Use when working with migration-deep-dive patterns. prompt adaptation, SDK swap, and feature mapping.
Score 70/100
Stream Claude responses, use system prompts, handle multi-turn conversations, Use when working with model-inference patterns. and process structured output with the Messages API.
Score 70/100
Configure Claude across dev, staging, and production with different Use when working with multi-env-setup patterns. models, keys, and rate limits per environment.
Score 70/100
Monitor Claude API calls — log tokens, latency, costs, errors, and Use when working with observability patterns. set up alerts for production Claude integrations.
Score 70/100
Implement content safety guardrails for Claude — input filtering, Use when working with policy-guardrails patterns.
Score 70/100
Build fault-tolerant Claude integrations — retries, circuit breakers, Use when working with reliability-patterns patterns. fallbacks, timeouts, and graceful degradation.
Score 70/100
Upgrade Anthropic SDK versions and migrate between Claude model generations. Use when working with upgrade-migration patterns.
Score 70/100
Use Anthropic Message Batches for async bulk processing and event handling. Use when working with webhooks-events patterns.
Score 70/100
Automate Claid AI tasks via Rube MCP (Composio). Always search tools first for current schemas.
Score 70/100
Extracts atomic technical claims from a substacker essay draft, converting flowing intuition-first prose into a numbered list where each item is a statement that could in…
Score 70/100
Generate Safe UI compatible multisig batch JSON to claim voting rewards (internal LP fees and external bribes).
Score 70/100
Calibrates manuscript claim strength so wording matches the actual evidence level, study design, and validation status.
Score 70/100
Document construction claims for disputes and recovery. Compile evidence, calculate damages, track notice requirements, and prepare claim packages.
Score 70/100
Autonomous claims drafting and optimization agent. Drafts, analyzes, and refines patent claims to maximize protection while ensuring validity.
Score 70/100
Validate documentation for unsupported claims, made-up metrics, and unverifiable statements. Use when relevant to the task.
Score 70/100
Analyze insurance claims workflow systems for intake optimization, adjudication rules, subrogation, litigation management, and settlement analytics.
Score 70/100
Clang/LLVM compiler skill for C/C++ projects. Use when working with clang or clang++ for diagnostics, sanitizer instrumentation, optimization remarks, static analysis with…
Score 70/100
Common Clap patterns and idioms for argument parsing, validation, and CLI design. Use when implementing CLI arguments with Clap v4+.
Score 70/100
Diagnose and fix Clari API errors including auth failures, export issues, and data mismatches. Use when Clari API calls fail, exports return empty data, or forecast numbers do not…
Score 70/100
Build a Clari forecast export pipeline to your data warehouse. Use when exporting forecast calls, quota data, and CRM totals from Clari to Snowflake, BigQuery, or a local…
Score 70/100
Build Clari revenue analytics: pipeline coverage, forecast accuracy, and rep performance dashboards from exported data.
Score 70/100
Optimize Clari API usage and integration costs. Use when reducing API call volume, optimizing export frequency, or evaluating Clari license utilization.
Score 70/100
Configure Clari API authentication with API key and set up export access. Use when connecting to the Clari API, generating API tokens, or configuring forecast data exports.
Score 70/100
Production readiness checklist for Clari API integrations. Use when launching a Clari data pipeline, validating export automation, or preparing for production forecast sync.
Score 70/100
Handle Clari API version changes and export schema migrations. Use when Clari updates their API, export format changes, or migrating from v3 to v4 API.
Score 70/100
Monitor Clari forecast changes using export job polling and change detection. Use when tracking forecast submission changes, building alerts for significant forecast movements, or…
Score 70/100
Generate targeted clarifying questions (2-3 max) that challenge vague requirements and extract missing context.
Score 70/100
Improve unclear UX copy, error messages, microcopy, labels, and instructions. Makes interfaces easier to understand and use.
Score 70/100
Intensive requirement clarification using structured AskUserQuestion workflow. Gathers MUST_HAVE (blocking) and NICE_TO_HAVE (optional) information before implementation.
Score 70/100
AKTIVIERT SICH AUTOMATISCH bei vagen Auftraegen. LIEBER EINMAL ZU OFT NACHFRAGEN als falsch implementieren.
Score 70/100
Pre-ingestion verification for epistemic quality in RAG systems. Ensures documents are properly qualified before entering knowledge bases.
Score 70/100
Create, edit, and convert legal pleadings for Clark County District Court and Justice Court, Nevada. Handles specialized .doc/.docx format with line numbering (1-28), proper…
Score 70/100
Evaluate investments and financial products using Bogle's investment vs. speculation framework. Trigger on: \"Is this a good fund?\", \"Should I trade or hold?\", \"Are my…
Score 70/100
Detect and analyze geometric clashes between BIM elements. Identify hard clashes, soft clashes, and workflow conflicts using spatial analysis and rule-based detection.
Score 70/100
Clash Verge 诊断与配置管理。网络诊断、配置 AI 工具路由规则（Claude/Codex/Cursor/Warp）、查看/克隆订阅配置、切换配置文件。当用户遇到网络问题、要配置代理规则、切换订阅、查看 Clash 配置时使用
Score 70/100
Generate class diagrams showing classes, interfaces, inheritance, and composition
Score 70/100
Organize class members in standard order, separate classes with blank lines, and maintain one-class-per-file structure.
Score 70/100
UMLクラス図からCRUD用HTMLフラグメントを自動生成する。クラス図（PlantUML、draw.io、XMI、画像、テキスト記述）を入力として、各クラスにつきCreate/Read/Update/DeleteのHTMLフラグメントを生成する。フラグメントは単一ルート要素（DOCTYPE/html/head/bodyなし）で、crud-composerな…
Score 70/100
Extract entities, properties, and relationships from UML class diagrams (images) and populate Neo4j graph database.
Score 70/100