Agent Skills Hub

data-cleaning-pipeline-generator

Generates data cleaning pipelines for pandas/polars/PySpark, handling missing values, duplicates, outliers, type conversions, and validation.

RFP Analyzer

Analyze RFPs and requirements to identify stakeholders, decompose functional modules, extract constraints, and generate high-priority clarification questions.

requirements-clarity

Clarify ambiguous requirements through systematic dialogue and scoring to ensure high-quality, actionable PRDs before starting implementation.

task-search

Accelerate task retrieval with a high-performance, debounced search engine supporting multi-token AND logic, relevance ranking, and real-time text highlighting across task titles, descriptions, and tags.

taide-botrun

A RAG-based AI solver for high school Chinese GSAT exams, featuring structured knowledge retrieval, reasoning templates, and explainable AI outputs.

Global Coding Style

Apply reality-first coding standards: intentional naming, focused functions, guard clauses, and deterministic side effects, with no speculative features.

memcontext-autopilot

An automated memory middleware for AI agents, implementing a Retrieve-Respond-Save loop to maintain long-term persistent context across conversations.

evaluating-code-models

Evaluate code generation models using BigCode Evaluation Harness. Benchmarks include HumanEval, MBPP, and MultiPL-E with pass@k metrics for multi-language coding models.

subagent-driven-development

Execute implementation plans using isolated subagents for each task, featuring a rigorous two-stage review process for spec compliance and code quality.

karpathy-guidelines

Behavioral guidelines for LLMs to reduce coding mistakes, follow best practices, and improve output quality by enforcing simplicity, surgical changes, and goal-driven verification.

ReasoningBank Intelligence

Implement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement in AI agents.

autoresearch

Autonomous multi-team codebase improvement agent with specialized modes: narrow (goal-directed), broad (hypothesis-divergent), and sweep (quality-focused).