Skill Directory

AI Skill Directory

Browse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.

personTashanworldNo key required

evaluating-cosmos-policy

Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, running headless GPU evaluations with EGL rendering,…

download1deployed_codestar0
personTashanworldNo key required

exa-search

Web toolkit powered by Exa, tuned for scientific and technical content. Use this skill when the user needs to search the web or fetch/extract URL content. Covers: web search (semantic lookups, researc…

download1deployed_codestar0
personTashanworldNo key required

exploratory-data-analysis

Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; mi…

download1deployed_codestar0
personTashanworldNo key required

flowio

Read, inspect, and write Flow Cytometry Standard (FCS) 2.0, 3.0, and 3.1 files with FlowIO. Use for low-level FCS metadata and channel inspection, NumPy event extraction, multi-dataset files, table ex…

download1deployed_codestar0
personTashanworldNo key required

gap-to-topic

Turn a research area into a go/no-go decision dossier for ONE candidate thesis/proposal topic — a 3-gate verdict (is the gap open? is it a contribution? is it feasible?) with the evidence laid out so …

download1deployed_codestar0
personTashanworldNo key required

generate-image

Generate or edit images with AI models through the OpenRouter Image API (Gemini, Seedream, Recraft, GPT-Image, Riverflow). Use for photos, illustrations, artwork, concept art, visual assets, logos, an…

download1deployed_codestar0
personTashanworldNo key required

get-available-resources

This skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space). It creates a JSON file wi…

download1deployed_codestar0
personTashanworldNo key required

executing-workflows

Use when a workflow plan exists and stages need to be executed sequentially in the current session

download1deployed_codestar0
personTashanworldNo key required

fluidsim

Plan, configure, inspect, restart, and analyze bounded FluidSim computational-fluid-dynamics simulations with explicit numerical-validity and HPC safety checks. Use for FluidSim solver selection, para…

download1deployed_codestar0
personTashanworldNo key required

gemini-delegate

Delegates large-context reading, bilingual or Chinese (CJK / zh-TW) drafting, cross-file synthesis, and second-opinion review to Google Antigravity CLI (`agy`) or legacy Gemini CLI. Use when input exc…

download1deployed_codestar0
personTashanworldNo key required

geniml

Use Geniml for audited local genomic-interval workflows: validate BED and universe contracts, plan Region2Vec or scEmbed runs, inspect model/tokenizer compatibility, and assess consensus universes.

download1deployed_codestar0
personTashanworldNo key required

gget

Fast CLI/Python queries to 20+ bioinformatics databases. Use for quick lookups: gene info, BLAST searches, AlphaFold structures, enrichment analysis. Best for interactive exploration, simple queries. …

download1deployed_codestar0
personTashanworldNo key required

gptq

Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or…

download1deployed_codestar0
personTashanworldNo key required

evolving-ai-agents

Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. Use when building self-improving agents, optimizing agent prompts and ski…

download1deployed_codestar0
personTashanworldNo key required

experimental-design

Design experiments and studies BEFORE data is collected — choosing a design, randomizing, blocking, and laying out treatment combinations so results are interpretable. Use whenever someone is planning…

download1deployed_codestar0
personTashanworldNo key required

fine-tuning-with-trl

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align …

download1deployed_codestar0
personTashanworldNo key required

general-sr-framework

PRISMA 2020-compliant systematic review framework for non-clinical fields. For social sciences, computer science, engineering, business, education, and humanities.

download1deployed_codestar0
personTashanworldNo key required

github-deep-research

Conduct multi-round deep research on any GitHub Repo. Use when users request comprehensive analysis, timeline reconstruction, competitive analysis, or in-depth investigation of GitHub. Produces struct…

download1deployed_codestar0
personTashanworldNo key required

grant-writing-spanish

Drafting and reviewing fellowship and grant applications in the Spanish research system (PFIS-ISCIII, Joan Oró-AGAUR, FPI-AEI, FPU-MIU, Sara Borrell, Río Hortega, AECC, Marató TV3). Covers structure, …

download1deployed_codestar0