Testing & QA · For data scientists

Complete agent-ready workflow for Qwen-family MTP or nextn GGUF conversion and release.

R6410418/Jackrong-llm-finetuning-guide

Builds agent evaluations in stages: inspect the repository and traces, agree a Task Spec with you, then build, audit and run a Harbor task with an independent verifier.

langchain-ai/langchain-skills

Create, edit, evaluate, and package agent skills. An agent skill from smixs/skill-conductor.

smixs/skill-conductor

Handles deduplication of YouTrack issues. An agent skill from JetBrains/ideavim.

JetBrains/ideavim

browser-based page capture and text extraction for public-opinion research.

123321kk/opinion-agent-ultimate

Browser automation, debugging, and performance analysis using Puppeteer CLI scripts.

einverne/dotfiles

A skill your agent uses when adding support for a new model to VeOmni.

ByteDance-Seed/VeOmni

Selectively monitor important long-running or resource-intensive commands with Haoleme by prefixing them with hao, so status, output, and completion notifications sync to the mobile app.

HaolemeApp/Haoleme

Guides evaluation of a RAG system by diagnosing failures in traces, building a retrieval test set and scoring retrieval and generation separately.

ai-evals-course/evals-skills

Image-to-code replication pipeline. An agent skill from Yu-369/VibeCurb.

Yu-369/VibeCurb

Builds diverse synthetic test inputs for LLM pipeline evaluation by defining failure-focused dimensions, drafting tuples with you and turning them into realistic queries.

ai-evals-course/evals-skills

Turn a user-owned coverage CSV and reviewed press-clip captures into an honest, source-linked earned-media dashboard and a motion-designed highlight reel (MP4) that scrolls each real article to the…

elvisun/newsjack

Benchmarks code generation models with the BigCode Evaluation Harness across HumanEval, MBPP, MultiPL-E and other suites using pass@k metrics.

Orchestra-Research/AI-Research-SKILLs

Checks an LLM judge against human labels using train, dev and test splits, TPR and TNR, and a bias correction applied to production data.

ai-evals-course/evals-skills

Benchmarks AMD's GAIA agent against Claude Code and across models on quality, honesty, steps, tokens, time and real cost, using gaia eval tasks.

amd/gaia

Benchmark Claude Code skill performance with variance analysis, tracking pass rate, execution time, and token usage across iterations.

AgriciDaniel/skill-forge

Creates and runs LLM evaluation suites from the omniroute CLI, follows live runs, shows scorecards, compares models and ties eval runs into CI.

diegosouzapw/OmniRoute

Sets up data quality checks with Great Expectations, dbt tests and data contracts, with checkpoints and pass-fail reports for pipelines.

wshobson/agents

Guide a tester through hipfire bring-up, serve smoke, claim-scoped harnesses, and benchmark reporting on AMD RDNA/CDNA GPUs.

warpfront/hipfire

A skill your agent uses when a Token Meter issue or approved feature needs diagnosis or implementation in the repository.

splunk/token-meter

Add or modify a Lizard language reader. An agent skill from terryyin/lizard.

terryyin/lizard

Score a Python generative-AI app's outputs on groundedness, relevance, coherence, and safety before it ships.

timothywarner-org/claude-code

Run the maclocal-api (AFM/MLX) test suite — automated assertions and smart analysis.

scouzi1966/maclocal-api

Convert messy voice input, imperfect speech recognition, half-formed product ideas, and iterative corrections into an implementation-ready software specification for Codex, Claude Code, Copilot…

FAIRY123456789/human-edge-agent-skills

Choose, inspect, validate, and report Paperclip Runner or Product E2E evaluations while preserving evidence, provenance, cost, and failure classification.

paperclipai/paperclip

Gate quantitative Mira conclusions by requiring reproducible data, formulas, calculation ledgers, or explicit downgrades when numbers drive judgment.

byteseek/Mira

Writes fictional but realistic coaching or therapy session transcripts for evals, demos and few-shot examples, in several modalities and export formats.

glebis/claude-skills

Evidence-capture protocol for verifying web/dashboard/backoffice/checkout changes in the Polar local stack by driving the real UI with Playwright.

polarsource/polar

Data quality validation and analysis accuracy verification. An agent skill from liangdabiao/claude-data-analysis-ultra-main.

liangdabiao/claude-data-analysis-ultra-main

A skill your agent uses when extending phx.gen.auth — adding registration fields, custom user attributes, extra migrations alongside generated auth, fixture updates.

j-morgan6/elixir-phoenix-guide

Project Guidelines Skill (Example)

davila7/claude-code-templates

Functional programming patterns with immutable data. An agent skill from citypaul/.dotfiles.

citypaul/.dotfiles

Review an AlbumentationsX transform for correctness, public API coherence, performance, documentation, and test coverage.

albumentations-team/AlbumentationsX

A skill your agent uses when the user asks to automate browser tasks, scrape websites, fill forms, capture screenshots, extract structured data from web pages, or build web automation workflows.

alirezarezvani/claude-skills

Stress-test a finding against the choices you did not make. An agent skill from pedrohcgs/claude-code-my-workflow.

pedrohcgs/claude-code-my-workflow

Example template for project-specific skill files covering architecture, patterns, testing, and deployment.

vibeeval/vibecosystem

用于医疗应用部署的患者安全评估工具。针对CDSS准确性、PHI暴露、临床工作流完整性和集成合规性的自动化测试套件。在安全故障时阻止部署。

affaan-m/ECC

5-stage kernel correctness verification protocol for Triton and CUDA kernels.

ZJLi2013/awesome-kernel-skills

Export a promoted fine-tuned model in the right deployment format — merged safetensors, LoRA-only, GGUF with imatrix, or FP8.

wshobson/agents

Generate PR descriptions for SDK pod packages following template and format rules.

tetherto/qvac

Use before running any confirmatory analysis or looking at outcome data, when testing a hypothesis, computing a p-value, or about to claim an effect - locks predictions and decision rules before…

K-Dense-AI/science-superpowers

Implement an approved repository change with explicit ownership, minimal scope, test-first evidence, and scoped verification.

rapidaai/voice-ai

AI-first application patterns, LLM testing, prompt management

alinaqi/maggy

Stage 1 of Clinical ASR Flywheel. An agent skill from NVIDIA/skills.

NVIDIA/skills

Create Earth2Studio diagnostic model wrappers for single-step data transformations, including simple derived diagnostics, packaged AutoModel diagnostics, and generative or diffusion diagnostics.

NVIDIA/skills

A skill your agent uses when starting empirical analysis, creating a data pipeline, generating results, or when data or model specifications change.

brycewang-stanford/Auto-Empirical-Research-Skills

QA test a live website with Firecrawl browser and scrape evidence.

firecrawl/skills

Extract battery features for degradation analysis and health monitoring in MATLAB.

matlab/matlab-agentic-toolkit