Execute coding tasks with a strict delivery workflow: build a full plan, implement one step at a time, run tests continuously, and commit by default after each step (`per_step`).
Use the decomp-permuter to automatically find C code variations that match target assembly. Useful when stuck at 99%+ match with stubborn register allocation issues.
Compare images with SSIM similarity scoring, pixel difference highlighting, and side-by-side visualization. — from majiayu000/claude-skill-registry
Query Open Targets Platform for target-disease associations, drug target discovery, tractability/safety data, genetics/omics evidence, known drugs, for therapeutic target — from…
CLI for AI agents to search and lookup books for their humans. Uses Open Library API. No auth required. — from majiayu000/claude-skill-registry
Full-corpus reasoning gauntlet. 12 cognitive tools run consecutively on all 105 framework skill files.
Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and run — from…
Performs financial ratio analysis, DCF valuation, budget variance analysis, and rolling forecast construction for strategic decision-making — from majiayu000/claude-skill-registry
Generate and update project documentation following acidApps standards. Includes templates for README, USER_MANUAL, TERMINOLOGY, and CHANGELOG.
Filter and screen stocks by financial metrics like P/E ratio, market cap, dividend yield, and growth rates. Analyze and compare stocks from CSV data.
Generate Playwright configuration files for cross-browser E2E testing. Triggers on "create playwright config", "generate playwright configuration", "playwright setup", "browser…
Public and Indigenous consultation, stakeholder feedback analysis, response strategy. Categorizes themes, performs sentiment analysis (support/opposition/neutral), generates…
Access Human Metabolome Database (220K+ metabolites). Search by name/ID/structure, retrieve chemical properties, biomarker data, NMR/MS spectra, pathways, for metabolomic — from…
Translation and localization guidelines for KoboToolbox content from English to Arabic. Use when translating KoboToolbox materials including: (1) Academy courses and educ — from…
图片生成, 架构图, 流程图, 时序图, 泳道图, diagram, architecture, flowchart, sequence, swimlane, image generation, nano banana, 生图, 画图, 画一个, 生成图片, generate image, draw diagram — from…
Create and manage N8N workflows in Orchestrator AI. Use Helper LLM pattern for all LLM calls, configure webhook status tracking, handle API responses.
Interpret ML model predictions using SHAP, LIME, attention visualization, and probing techniques. Use when explaining model decisions, debugging model behavior, or building trust…
meadow Docstring Format (MDF) specification for Python documentation. Use when writing, editing, or reviewing docstrings for Python code.
Verifies factual claims in documents using web search and official sources, then proposes corrections with user confirmation.
Assess technical patterns, integrations, and constraints in the domain to inform feasibility and strategy.
Diagnose agent failures by identifying missing capabilities. Use when an agent fails a task, produces wrong output, or needs escalation.
Train and fine-tune LLMs using HuggingFace TRL, Transformers, and cloud GPU infrastructure with SFT, DPO, GRPO methods — from majiayu000/claude-skill-registry
Element is a zero dependency library to efficiently generate HTML programmatically, without templates in Go
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects the agent ('No, t — from…
Financial Modeling Prep API for stocks, fundamentals, SEC filings, institutional holdings (13F), and congressional trading.
Orchestrates comprehensive audits of Claude Code customizations using specialized auditors. Use when auditing multiple components, asking about naming/organization best practices,…
Start a Ralph Wiggum autonomous task loop that keeps Claude working until a task is complete. Uses the Stop hook pattern to re-inject prompts when Claude tries to exit before…
Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claude Agent SDK.
Use when inserting new records into a Bknd entity via the SDK or REST API. Covers createOne, createMany, creating with relations ($set), response handling, error handling — from…
Technical research methodology with YAGNI/KISS/DRY principles. Phases: scope definition, information gathering, analysis, synthesis, recommendation.
Skill for configuring localization and multi-language support in Orchard Core. Covers culture settings, content localization, PO file translations, and localization configuration.
Error handling patterns for ERPNext/Frappe API development (v14/v15/v16). Covers whitelisted method errors, REST API errors, client-side handling, external integrations — from…
Swift 6+ development specialist covering SwiftUI, Combine, Swift Concurrency, and iOS patterns. Use when building iOS apps, macOS apps, or Apple platform applications.
Use Hugging Face Transformers for local model inference, embeddings, and fine-tuning. Covers pipelines, model selection, quantization, and optimization.
Conduct enterprise-grade research with multi-source synthesis, citation tracking, and verification. Use when user needs comprehensive analysis requiring 10+ sources, veri — from…
Conduct thorough research with proper citations and source verification for academic and professional content
Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like…
Achieve and maintain low input latency by engineering event-to-render pipelines. — from majiayu000/claude-skill-registry
Systematically challenge current assumptions before major decisions. Counters confirmation bias, groupthink, and overconfidence. — from majiayu000/claude-skill-registry
Use when selecting between MCP tools based on task complexity and requirements - provides a structured selection workflow and decision rationale.
Creates detailed technical specifications including architecture, data models, APIs, and technology choices.
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration.
Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search.
Explains code clearly and thoroughly. Use when asked to explain, clarify, or teach about code snippets, functions, or concepts.
Autonomous crypto trading with technical and sentiment analysis. Use when executing trades, analyzing markets, or managing positions on Coinbase.
Generate TypeScript CLIs. USE WHEN create CLI, build CLI, command-line tool. SkillSearch('createcli') for docs. — from majiayu000/claude-skill-registry
Autonomous task execution with testing and security. Works through all tasks without stopping.
Analyze ENCODE functional genomics screens including CRISPR screens, MPRA (Massively Parallel Reporter Assays), and STARR-seq.
General-purpose agent for researching complex questions and executing multi-step tasks. Versatile problem-solver that combines research capabilities, analytical thinking — from…
Expert DevOps engineer bridging development and operations with comprehensive automation, monitoring, and infrastructure management.
Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat.
Manually add individual YouTube URLs to a custom collection CSV. Use when adding one-off videos to folders like library-of-minds or random, not from a channel extraction.
Account-level profit and loss analysis via Longbridge Securities — simple return, time-weighted return (TWR), per-symbol P&L breakdown, and P&L by market.
Manages all git operations (commit, push, branch management, PR creation) in a standardized, safe, and consistent way.
Use AgentPMT external API to run the Global Digital Economy & Connectivity Data tool with wallet signatures, credits purchase, or credits earned from jobs.
Schedule a delayed or interval-based action with minimal heartbeats. Use to wait before running a check (e.g., GH Actions, PR status, CI pipeline) or to poll on a bounded — from…
Apply SY2 System Boundaries to define what is inside versus outside system scope for analysis or design.
Multi-project portfolio analytics dashboard. Aggregate KPIs across projects, track portfolio health, compare performance, and support executive decision-making.
設計一致的錯誤碼，遵循 PREFIX_CATEGORY_NUMBER 格式。 使用時機：定義錯誤碼、建立錯誤處理、設計 API。 關鍵字：error code, error handling, error format, API errors, 錯誤碼, 錯誤處理。 — from majiayu000/claude-skill-registry
Use when building provider-agnostic AI applications with Microsoft.Extensions.AI. Covers IChatClient, IEmbeddingGenerator, middleware pipelines, caching, telemetry, and DI…