Development · For data scientists

Behavioral guardrails to prevent common LLM coding mistakes — enforces surgical changes, assumption verification, and scope discipline before and during implementation.

tmdgusya/engineering-discipline

Walks through fixing dbt compilation, database and test errors: read the full error, check upstream models, apply a fix, then verify with dbt build and a data preview.

AltimateAI/data-engineering-skills

Diagnoses failing ML and AI work, such as OOM, NaN, divergence, crashes, slow throughput, wrong outputs and dependency conflicts, with every claim backed by documentation citations.

Leeroo-AI/superml

Detect an existing ML workspace or scaffold a fresh one via python -m skoreskills scaffold --package <pkg.

probabl-ai/skills

Run OhMyCode benchmarks — score any provider/model with token tracking.

AlphaLab-USTC/OhMyCode

Route verl-omni training/inference consistency checks through MindStudio's MSProbe collection and root-cause analysis skills.

verl-project/verl-omni

Debug FlyDSL GPU kernels that produce NaN, inf, wrong results, or crash.

ROCm/FlyDSL

A skill your agent uses when integrating Python scripts with C++ in a DAWorkbench plugin — calling Python from C++, Python multithreading without UI conflicts, Python-to-C++ data exchange, Python UI…

czyt1988/data-workbench

Describe images (charts, diagrams, tables, screenshots) using Vision AI.

Wide-Moat/open-computer-use

Create publication-quality scientific diagrams, flowcharts, and schematics using Python (graphviz, matplotlib, schemdraw, networkx).

jimmc414/Kosmos

Analyze PerforatedAI training results and provide optimization recommendations.

PerforatedAI/PerforatedAI

A skill your agent uses when the user wants a less default, more original solution for code, design, writing, naming, architecture, debugging, or strategy, especially when progress is stuck.

Haohao-end/openagent

Monitor competitor pricing, features, changelogs, dashboards, and product changes with Firecrawl.

firecrawl/skills

A skill your agent uses when migrating a Frappe app between major versions, detecting breaking API changes, or resolving post-migration errors.

Impertio-Studio/Frappe_Claude_Skill_Package

Build figures in OpenAI's blog / research / system-card "dotcom" visual style — both (a) bar charts (monochrome bars with a darker same-hue stroke, rounded corners, a black y-axis with outward ticks…

yzlnew/infra-skills

Start or resume a requested Guardrails implementation or PR takeover in the selected linked worktree with bounded scope and verification.

openai/openai-guardrails-js

Rocky DSL (.rocky file) cross-subproject cascade. An agent skill from rocky-data/rocky.

rocky-data/rocky

Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement.

K-Dense-AI/claude-scientific-writer

Symbol-level code context for LLM coder-agents: tree-sitter extracts symbols, PageRank ranks them over the cross-file reference graph, and the top class/function signatures are fed to the LLM as a…

agentsope/SkillAlchemy

Session startup — gitignore, auto-update, memory, rules, context, CLI config, and greet.

ntorga/agent-starter-kit

Master enterprise-grade Scala development with functional programming, distributed systems, and big data processing.

davila7/claude-code-templates

Conventions for writing empirical finance R code with data.table, fixest, arrow, and ggplot2.

aspi6246/Claude-Code-Skills-for-Academics

Track session costs, set budget alerts, and optimize token spend.

rohitg00/pro-workflow

Secure AI coding agents (Claude Code, Cursor, Codex, Copilot) with permission boundaries, secret protection, code review gates, and safe sandbox configurations for team environments.

sickn33/agentic-awesome-skills

Structured content modeling guidance for schema design, content architecture, content reuse, references versus embedded objects, separation of concerns, and taxonomies across Sanity and other…

sanity-io/agent-toolkit

Complete the name framework migration in a crawler (Step 3) by removing all custom name cleaning/splitting logic and the Step 1 review scaffolding, replacing it with a single…

opensanctions/opensanctions

Run metric-driven iterative optimization loops. An agent skill from leo-kuang-ai/spec-first.

leo-kuang-ai/spec-first

A skill your agent uses for Plotly Dash app layouts, callbacks, pages, assets, configuration, clientside callbacks, Jupyter display, CSP, and app-level debugging.

VectorSpaceLab/AREX-Skill

Safely refactors dbt models with downstream impact analysis.

AltimateAI/data-engineering-skills

Align a fine-tuned model with preference data using DPO, ORPO, KTO, or SimPO.

wshobson/agents

Change the LLM Gateway request path in apps/gateway — chat and other endpoints, routing and provider selection, error and finish-reason classification, streaming, request logging, Redis use…

theopenco/llmgateway

Deep dive into flowfileframe — the Polars-LazyFrame-shaped Python API that builds an in-process flowfilecore FlowGraph as a side effect of every method call — covering the FlowFrame/Expr internals…

Edwardvaneechoud/Flowfile

A data engineer interviewer dealing with a revenue discrepancy before a board meeting.

PrepLabsAI/InterviewMentor

Orchestrate free opencode workers from Claude Code to cut token costs.

alirezarezvani/claude-skills

Create professional architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as standalone animated HTML files with SVG graphics, flowing animation effects, a built-in dark/light…

OWWZO/ai-agent

Diagnoses pipeline performance issues -- slow jobs, expensive queries, latency trends -- using Monte Carlo's cross-platform observability.

sickn33/agentic-awesome-skills

Recognize bulk-edit missions and drive the occurrence-classification guardrail on the user's behalf before modifying many matching instances.

spec-kitty/spec-kitty

Build workflows with AWS Step Functions state machines using the JSONata query language.

awslabs/agent-plugins

A skill your agent uses when writing, reviewing, or refactoring Manor code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

manor-os/manor-ai

Writing criterion benchmarks for the Rocky engine and wiring them to the perf-gated CI workflow.

rocky-data/rocky

Creating interactive data visualisations using d3.js. An agent skill from aiskillstore/marketplace.

aiskillstore/marketplace

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

tetherto/qvac

Use during planning, implementation, PR review, or /qv-qip-triage when a change may affect public SDK API, native dependency, plugin contract, model registry contract, runtime, transport, storage…

tetherto/qvac

Unified domain and data modeling for business entities, invariants, schema design, aggregate boundaries, and evolution strategy.

rsmdt/the-startup

Perform an evidence-based review of a fixed change boundary.

rapidaai/voice-ai

The engineering bar for this repo — rebuild from first principles rather than patching, the simplicity ladder, what must never be simplified away, and the one-runnable-check rule.

overmind-core/overmind

Decision tree for thiserror (library crates) vs anyhow (CLI/binary) in the Rocky engine workspace.

rocky-data/rocky

unsafe conventions in the Rocky engine — SAFETY comment rules, the legitimate unsafe categories (a memory-map, a repr(transparent) cast, and serialised test env-var mutation), and when to push back…

rocky-data/rocky