Capability
Bundles scripts agent skills
Skills that ship a scripts/ folder, so the agent runs code the author wrote instead of improvising it.
Highest-scoring with this capability: let-fate-decide from trailofbits/skills (94/100), manual-tester from tronghieu/agent-skills (92/100) and tao-run-deft-object-detection from NVIDIA/skills (92/100).
- 668 listed skills
- 77 repositories
By category
Science and Research (138) · AI Agents and LLM Engineering (111) · Video, Image, Audio and Creative (99) · DevOps and Cloud (60) · Developer Tools and Frameworks (58) · Business, Sales and Finance (33) · Frontend and Design (24) · Documents and Office Files (24) · Productivity and Knowledge Work (21) · Security (19) · Testing and QA (18) · Data, Analytics and Databases (17) · Marketing and SEO (15) · Writing and Editing (14) · Code Review and Code Quality (9) · Product Management (8)
The 100 highest-scoring of 668 skills
Ranked by Suede Skill Check score; Suede AI's own skills are not ranked. Open a category above for the full list with this filter on.
No matching skills. Try fewer words or clear your search.
| Skill | Repository | What it does |
|---|---|---|
| let-fate-decide 94/100 · A | trailofbits/skills | Draws a Tarot spread to inject entropy into planning when prompts are vague or casually delegated, and interprets the spread to guide next steps. |
| generate-image 93/100 · A | K-Dense-AI/claude-scientific-skills | Generates or edits images with AI models through the OpenRouter Image API (Gemini, Seedream, Recraft, GPT-Image, Riverflow). Use for photos… |
| hypogenic 93/100 · A | K-Dense-AI/claude-scientific-skills | Plans and audits use of ChicagoHAI HypoGeniC/HypoRefine for LLM-assisted hypothesis generation from labeled text datasets. Use for the `hypogenic`… |
| matchms 93/100 · A | K-Dense-AI/claude-scientific-skills | Processes, cleans, compares, and searches tandem mass spectra with matchms. Use for MS/MS file I/O, metadata harmonization, peak filtering, spectral… |
| ncats-arax 93/100 · A | K-Dense-AI/claude-scientific-skills | Queries the NCATS Translator ARAX production API for bounded, typed, provenance-rich one-hop and endpoint-pinned two-hop biomedical knowledge-graph… |
| neurokit2 93/100 · A | K-Dense-AI/claude-scientific-skills | Builds and audits reproducible NeuroKit2 research workflows for physiological time-series preprocessing, event/interval analysis, multimodal… |
| opentrons-integration 93/100 · A | K-Dense-AI/claude-scientific-skills | Authors, reviews, migrates, simulates, and troubleshoots official Opentrons Python Protocol API v2 protocols for Flex and OT-2 robots. Use for… |
| codeql 92/100 · A | trailofbits/skills | Scans a codebase for security vulnerabilities using CodeQL's interprocedural data flow and taint tracking analysis, with run-all and important-only scan modes. |
| open-sourcing 92/100 · A | trailofbits/skills | This skill should be used when the user asks to "open source this project", "prepare this repository for public release", "make this repo public"… |
| semgrep 92/100 · A | trailofbits/skills | Runs a Semgrep security scan over a codebase, detecting languages, selecting rulesets, requiring approval of the plan, and merging output to SARIF. |
| cloud-databases-onboarding 92/100 · A | google/skills | Guides users through discovering their database requirements, recommends a Google Cloud database based on a recommendation matrix, and assists in… |
| manual-tester 92/100 · A | tronghieu/agent-skills | Plans and runs manual test sessions of the running app in five modes, including exploratory, smoke, and assessment, and writes manual test plans. |
| tao-run-deft-aoi-cosmos3 92/100 · A | NVIDIA/skills | Run the disk-backed DEFT AOI improvement loop for NVIDIA Cosmos Reason 3 / Cosmos3 models, using Nano by default and Edge or Super when explicitly… |
| tao-run-deft-object-detection 92/100 · A | NVIDIA/skills | Runs the DEFT data augmentation loop for Grounding DINO object detection, with baseline inference, gap analysis, unique-neighbor mining, retraining, and source pool preparation. |
| docx 91/100 · A | anthropics/skills | Creates, reads, edits, and manipulates Word documents and templates, including formatting, tables of contents, tracked changes, comments, images, and find-and-replace. |
| post-patch-validation 91/100 · A | trailofbits/skills | Validates security patches with reproducible baseline-versus-patched evidence, including original exploits, root-cause variants, behavior… |
| trailmark-finding-triage 91/100 · A | trailofbits/skills | Performs graph-assisted triage of a single security finding, SARIF result, or suspicious function using Trailmark reachability, taint, privilege-boundary, and blast-radius evidence. |
| agent-ready 91/100 · A | mblode/agent-skills | Implements agent-readiness on sites and docs from scorecards like Mintlify Agent Score or AFDocs, including llms.txt coverage and agents hitting 404s on guessed URLs. |
| agent-skills-creator 91/100 · A | mblode/agent-skills | Creates and improves portable Agent Skills using a validator and routing scenarios, with evidence-based decisions to keep, cut, merge, or retire skills. |
| chat-history 91/100 · A | mblode/agent-skills | Recovers decisions, previous fixes, and research from past AI conversations with source evidence, reading local Claude Code, Codex, Grok, and Cursor history. |
| ci-speedup 91/100 · A | mblode/agent-skills | Cuts CI wait by measuring a pipeline's critical path from run timestamps, then splitting, sharding, and trimming setup, with a before and after ledger. |
| pr-babysitter 91/100 · A | mblode/agent-skills | Monitors or repairs an open GitHub PR, handling CI failures, conflicts, review threads, and merge readiness while reporting state changes. |
| iso-standards-readiness 91/100 · A | K-Dense-AI/claude-scientific-skills | Prepares and structurally reviews readiness evidence for ISO 13485, ISO 14971, ISO/IEC 17025, and ISO 15189 standards, covering scope, controlled documents, and risk files. |
| treatment-plans 91/100 · A | K-Dense-AI/claude-scientific-skills | Formats and structurally validates treatment-plan documentation after licensed professionals have supplied and verified clinical decisions, without making clinical decisions itself. |
| tao-finetune-anomalygennext 91/100 · A | NVIDIA/skills | Validate a user AnomalyGenNext dataset and recipe, freeze its validation set, and prepare a canonical texture fine-tuning recipe. Use when… |
| tao-prepare-anomalygennext-inputs 91/100 · A | NVIDIA/skills | Prepare normalized object-detection false negatives, source masks, and clean-image embedding inputs for AnomalyGenNext. Use when turning box-level… |
| warp-compile-time-optimizer 91/100 · A | NVIDIA/skills | Use when compile time or startup time is the problem in code that uses Warp: a request to improve, optimize, or cut compile times; an app that is… |
| agent-platform-deploy 90/100 · A | google/skills | Deploys open models or custom weights from Model Garden to Agent Platform endpoints, checks deployment status and cost, troubleshoots errors, and undeploys models. |
| assuredworkloads-environment-assessor 90/100 · A | google/skills | Discovers Google Cloud resource telemetry and effective Org Policies, evaluates workloads against sovereign data boundary and compliance standards, and recommends the Assured Workloads Framework. |
| google-cloud-filestore-log-troubleshooting 90/100 · A | google/skills | Diagnoses and resolves Filestore client mount failures, EACCES permission errors, and ETIMEDOUT network timeouts on Google Cloud, including NFS mounts that hang or fail. |
| statistical-power 90/100 · A | K-Dense-AI/claude-scientific-skills | Calculates sample sizes and statistical power for study planning. Applies when someone asks "how many subjects/samples/replicates do I need", wants… |
| uncertainty-and-units 90/100 · A | K-Dense-AI/claude-scientific-skills | Tracks physical units and propagates measurement uncertainty in scientific calculations using pint and uncertainties. Use for unit conversion and… |
| kaggle 90/100 · A | shepsci/kaggle-skill | Handles Kaggle tasks when explicitly requested, covering competitions, datasets, models, notebooks, forums, benchmarks, hackathons, badges, and account setup. |
| bmad-run-inspector 90/100 · A | tronghieu/agent-skills | Inspects and explains bmad-loop run artifacts for live health checks and post-run forensics, such as why a story failed or where tokens went. |
| critical-thinking 90/100 · A | tronghieu/agent-skills | Audits reasoning in a document or argument, covering claims, evidence, unstated assumptions, logical gaps, fallacies, and what would falsify it, anchored to quoted text. |
| deep-reader 90/100 · A | tronghieu/agent-skills | Reads and answers questions about long books and papers without loading the whole text into one context window, keeping page-anchored notes. |
| design-thinking 90/100 · A | tronghieu/agent-skills | Facilitate a full design-thinking engagement (Empathize, Define, Ideate, Prototype, Test) grounded in real user evidence. Use whenever the user… |
| scrum-master 90/100 · A | tronghieu/agent-skills | Acts as the team's Scrum Master or copilot to one, planning sprints, running daily pulses, preparing retrospectives, tracking impediments, and detecting process anti-patterns. |
| slidewright 90/100 · A | tronghieu/agent-skills | Builds interactive presentation websites for slide decks projected to a room, including slide editing, deck restyling, phone remote control, and PDF export. |
| tao-analyze-detection-kpi 90/100 · A | NVIDIA/skills | Runs TAO Data Services KPI analysis for object detection, comparing inference annotations with ground truth to compute per-class TP/FP/FN/TN, precision, recall, accuracy, and AP. |
| tao-analyze-gaps-od-map 90/100 · A | NVIDIA/skills | Run TAO Data Services object-detection gap analysis from ground-truth and inference annotations. Use when an object detection workflow needs to… |
| tao-analyze-gaps-vlm-bcq 90/100 · A | NVIDIA/skills | Extract false-positive and false-negative gaps from VLM binary-classification-question (BCQ, yes/no) predictions. Use when the user asks to "analyze… |
| tao-generate-image-embeddings 90/100 · A | NVIDIA/skills | Run TAO Data Services image embedding to turn a parquet of image filepaths into an embedding parquet using CLIP, SigLIP, or a TAO checkpoint. Use… |
| tao-run-automl 90/100 · A | NVIDIA/skills | Run container-backed AutoML / hyperparameter optimization (HPO) for NVIDIA TAO networks using AutoMLRunner. Handles algorithm selection (bayesian… |
| tao-token-efficient-execution 90/100 · A | NVIDIA/skills | Token-efficient execution kit for repeated TAO agentic workflows. Compiles a skill into stage cards once (with a strong model), then executes them… |
| tao-train-optical-inspection 90/100 · A | NVIDIA/skills | Optical Inspection for defect detection using Siamese networks. Compares image pairs to detect manufacturing defects, anomalies, or quality issues… |
| tao-train-visual-changenet 90/100 · A | NVIDIA/skills | Visual ChangeNet for binary image classification and segmentation in AOI defect detection. Use when training, evaluating, exporting, or running… |
| vss-deploy-detection-tracking-2d 90/100 · A | NVIDIA/skills | Deploys, runs, debugs, tears down, and calls the REST API of the RTVI-CV 2D detection and tracking microservice. |
| mcp-builder 89/100 · B | anthropics/skills | Guides building MCP servers that let LLMs use external services through tools, in Python with FastMCP or TypeScript with the MCP SDK. |
| diagramming-code 89/100 · B | trailofbits/skills | Generates Mermaid diagrams from Trailmark code graphs, including call graphs, class hierarchies, module dependency maps, complexity heatmaps, and attack surface data flow visualizations. |
| graph-evolution 89/100 · B | trailofbits/skills | Compares Trailmark code graphs at two source snapshots to surface security-relevant structural changes, including new attack paths, complexity shifts, and blast radius growth. |
| interpreting-culture-index 89/100 · B | trailofbits/skills | Interprets Culture Index (CI) surveys, behavioral profiles, and personality assessment data. Supports individual profile interpretation, team… |
| slicing-code-context 89/100 · B | trailofbits/skills | Selects bounded, graph-informed source slices with Trailmark and delegates focused code analysis or patch-proposal work to a smaller subagent. |
| render-proof-points-overlay 89/100 · B | gooseworks-ai/goose-skills | Builds proof-point pill overlays for a perfect-score UGC video ad and composites them onto a base clip, then adds the music bed. |
| auteur 89/100 · B | agiwhitelist/auteur | Designs and builds complete web experiences, including landing pages, cinematic scroll-directed sites, and multi-screen products, as one consistent design system with generated assets. |
| agent-platform-alert-configuration 89/100 · B | google/skills | Configures best-practice alerting policies for AI agents using OpenTelemetry (OTel) metrics, generating output as Terraform (.tf) configuration… |
| api-gateway-backend-security-and-rate-limiting 89/100 · B | google/skills | Secures and rate limits backend services behind Google Cloud API Gateway across OpenAPI 2.0 and OpenAPI 3.0.x API configurations, including… |
| api-gateway-mcp-server 89/100 · B | google/skills | Configures Google Cloud API Gateway to act as a remote Model Context Protocol (MCP) server (Public Preview) that exposes REST APIs as agent tools… |
| cloud-monitoring-promql-query 89/100 · B | google/skills | Generates valid PromQL queries from Cloud Monitoring metric descriptors and resource parameters. Use when asked to create, generate, write, or… |
| cloud-trace-querying 89/100 · B | google/skills | Queries Cloud Trace spans, filters by latency or error status, correlates distributed traces with Cloud Logging, and diagnoses latency bottlenecks across Google Cloud services. |
| dbt-sf-to-bq-translator 89/100 · B | google/skills | Translates Snowflake dbt SQL models to BigQuery SQL, handling SQL compilation, Jinja macro masking, BigQuery Translation Service workflows, config transformations, type casting, and deduplication. |
| developer-device-platform-basics 89/100 · B | google/skills | Provides guidance and instructions on managing remote devices on Developer Device Platform (DDP). Use when reserving remote Android devices… |
| gke-ai-troubleshooting-jobset-interruption 89/100 · B | google/skills | Diagnoses GKE JobSet interruptions, restarts, and preemptions for AI/ML training workloads autonomously. Use when troubleshooting JobSet restart… |
| gke-ai-troubleshooting-tpu-dynamic-slices-monitoring 89/100 · B | google/skills | Monitors, troubleshoots, and manages GKE TPU Dynamic Slices custom resources. Use when checking TPU slice lifecycle states, troubleshooting slice… |
| gke-ai-troubleshooting-tpu-metrics-monitoring 89/100 · B | google/skills | Monitors and troubleshoots GKE TPU workloads, nodes, and node pools using GKE system metrics and PromQL. Use when monitoring TensorCore duty cycle… |
| gke-ai-troubleshooting-tpu-vbar-oom 89/100 · B | google/skills | Diagnoses and prevents vbar_control_agent segfaults, out-of-memory (OOM) errors, and TPU device initialization failures on TPU v6e nodes in GKE… |
| gke-alert-configuration 89/100 · B | google/skills | Configures alerting policies in Terraform for Google Kubernetes Engine (GKE) clusters, workloads, and services using PromQL and Google Cloud Managed… |
| google-cloud-filestore-auditing 89/100 · B | google/skills | Audits Filestore instances on Google Cloud for disaster recovery readiness, overly permissive NFS export rules, and reliability compliance with Physical Zone Isolation and Separation. |
| google-cloud-filestore-nfs-browser 89/100 · B | google/skills | Inspects, searches, and reads files and POSIX metadata on Filestore (NFS) instances on Google Cloud without local NFS client packages or root… |
| iam-helper-for-privileged-access-management 89/100 · B | google/skills | Manages the lifecycle of on-demand temporary access with Privileged Access Manager, including entitlements, access requests, and approving or denying pending grants. |
| autoskill 89/100 · B | K-Dense-AI/claude-scientific-skills | Analyzes user-requested Screenpipe history windows to detect repeated research workflows, match existing scientific skills, and stage new skill… |
| citation-management 89/100 · B | K-Dense-AI/claude-scientific-skills | Manages academic citations by searching OpenAlex, PubMed, and Google Scholar, extracting metadata, validating references, and generating formatted BibTeX entries. |
| diffdock 89/100 · B | K-Dense-AI/claude-scientific-skills | Predicts protein-small-molecule binding poses with DiffDock and DiffDock-L from PDB or sequence plus SMILES/SDF/MOL2. Covers batch docking, pose… |
| flowio 89/100 · B | K-Dense-AI/claude-scientific-skills | Reads, inspects, and writes Flow Cytometry Standard (FCS) 2.0, 3.0, and 3.1 files with FlowIO. Use for low-level FCS metadata and channel… |
| fluidsim 89/100 · B | K-Dense-AI/claude-scientific-skills | Plans, configures, inspects, restarts, and analyzes bounded FluidSim computational-fluid-dynamics simulations with explicit numerical-validity and… |
| infographics 89/100 · B | K-Dense-AI/claude-scientific-skills | Creates and reviews infographics with Nano Banana 2 via OpenRouter. Use for statistical summaries, timelines, comparisons, processes, and visual… |
| latchbio-integration 89/100 · B | K-Dense-AI/claude-scientific-skills | Builds, registers, debugs, and operates bioinformatics workflows on Latch using the Python SDK, CLI, Latch Data and Registry, Nextflow, Snakemake… |
| latex-posters 89/100 · B | K-Dense-AI/claude-scientific-skills | Creates research posters in LaTeX using beamerposter, tikzposter, or baposter. Use for conference posters, academic presentations, multi-column… |
| liteparse 89/100 · B | K-Dense-AI/claude-scientific-skills | Local document and PDF parsing that returns spatial text with bounding boxes. Use for extracting text from PDFs, DOCX, Office files, and images… |
| literature-review 89/100 · B | K-Dense-AI/claude-scientific-skills | Conducts systematic, scoping, and narrative literature reviews using sources such as PubMed, arXiv, and bioRxiv, tracking search coverage and evidence limitations. |
| matlab 89/100 · B | K-Dense-AI/claude-scientific-skills | Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT… |
| openpiv 89/100 · B | K-Dense-AI/claude-scientific-skills | Performs Particle Image Velocimetry (PIV) analysis with OpenPIV. Use when extracting velocity fields from PIV image pairs, analyzing fluid dynamics… |
| pathml 89/100 · B | K-Dense-AI/claude-scientific-skills | Supports local computational pathology research with PathML: slide loading and tiling, preprocessing and QC, h5path storage, multiplex… |
| pathogen-variant-surveillance 89/100 · B | K-Dense-AI/claude-scientific-skills | Queries public GenSpectrum LAPIS data for pathogen genomic surveillance, current lineage nomenclature, weekly sequence proportions, reporting… |
| pydeseq2 89/100 · B | K-Dense-AI/claude-scientific-skills | Performs bulk RNA-seq differential expression analysis with PyDESeq2, including count validation, formula designs, explicit contrasts, Wald tests… |
| pymatgen 89/100 · B | K-Dense-AI/claude-scientific-skills | Analyzes, validates, converts, and transforms materials structures and computed materials data with pymatgen. Use for local phase diagrams, symmetry… |
| pymc 89/100 · B | K-Dense-AI/claude-scientific-skills | Builds and checks Bayesian models with PyMC, including hierarchical models, NUTS MCMC, variational inference, mutable-data predictions, posterior… |
| pytdc 89/100 · B | K-Dense-AI/claude-scientific-skills | Provides Therapeutics Data Commons workflows through PyTDC for registry discovery, dataset access, task-aware splits, evaluator metrics, benchmark… |
| scholar-evaluation 89/100 · B | K-Dense-AI/claude-scientific-skills | Provides qualitative-first, evidence-traceable developmental review of scholarly works and audit low-stakes research-assessment rubrics with… |
| scientific-visualization 89/100 · B | K-Dense-AI/claude-scientific-skills | Creates and audits truthful, accessible, publication-ready scientific figures with Matplotlib, Seaborn, or Plotly. Use it for figure design… |
| scikit-learn 89/100 · B | K-Dense-AI/claude-scientific-skills | Supports machine learning in Python with scikit-learn. Applies when working with supervised learning (classification, regression), unsupervised… |
| shap 89/100 · B | K-Dense-AI/claude-scientific-skills | Explain and audit machine-learning predictions with SHAP. Use for selecting SHAP explainers and maskers, computing and validating feature… |
| simpy 89/100 · B | K-Dense-AI/claude-scientific-skills | Builds, inspects, tests, and analyzes bounded process-based discrete-event simulations with SimPy. Use for event scheduling, resource queues… |
| hsb-ip-def 89/100 · B | NVIDIA/skills | Generates, validates, compares, or explains HSB HOLOLINK_def.svh macros, running bundled local Python scripts and writing validated .svh output files after the user confirms paths. |
| nvflare-autofl 89/100 · B | NVIDIA/skills | Use for agent-assisted Auto-FL optimization of an existing NVFLARE job in simulation, POC, or production. Do not use for code conversion… |
| skill-card-generator 89/100 · B | NVIDIA/skills | Use only to generate or update a governance skill card for a specified existing agent skill directory. Do not use for explaining, listing… |
| tao-run-deft-aoi 89/100 · B | NVIDIA/skills | Run the full DEFT AOI improvement loop for NVIDIA TAO VisualChangeNet / ChangeNet PCB inspection models: baseline evaluate, RCA, Cosmos AnomalyGen /… |
| tao-run-deft-pas 89/100 · B | NVIDIA/skills | Run iterative improvement for NVIDIA TAO CLIP / SigLIP image-text retrieval on attribute-labelled data. Use when a request combines retrieval… |
| burpsuite-project-parser 88/100 · B | trailofbits/skills | Searches and explores Burp Suite project files (.burp) from the command line. Use when searching response headers or bodies with regex patterns… |
| goal-prompt 88/100 · B | trailofbits/skills | Drafts copy-paste-ready /goal commands for goal mode in Claude Code and Codex. Use when the user asks to create, write, rewrite, improve, compress… |