Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
48,622 skills from 2,355 repositories · updated 1 hour ago
6,268 skills
- epilot-webhooksNewhookdeck/webhook-skillsReceive and verify epilot (epilot.cloud) webhooks, signed per Standard Webhooks. Use when setting up an epilot webhook endpoint, getting the whsec_ signing secret, debugging webhook-id / webhook-timestamp / webhook-signature verification (including the extra v1a Ed25519 entry), or handling events like automation_trigger_webhook, customer_request_created and FileCreated.EngineeringNo warnings★ 97↓ —
- large-file-refactorPaulRBerg/agent-skillsDiscover large source-file refactor candidates and propose split plans based on cohesion and risk, using available semantic tooling.EngineeringNo warnings★ 104↓ —
- alterlab-pytorch-lightningAlterLab-IEU/AlterLab-Academic-SkillsScalable deep-learning training with PyTorch Lightning — organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, build data pipelines and callbacks, log to W&B or TensorBoard, and run distributed training (DDP, FSDP, DeepSpeed). Use when structuring PyTorch training loops, scaling neural-network training across GPUs/TPUs, or adding checkpointing, logging, and distributed strategies. Part of the AlterLab Academic Skills suite.EngineeringNo warnings★ 82↓ —
- alterlab-literature-reviewAlterLab-IEU/AlterLab-Academic-SkillsConducts comprehensive, systematic literature reviews across multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar), with PRISMA 2020 flow tracking, study screening (title/abstract and full-text), evidence-table extraction, and risk-of-bias assessment (RoB 2, ROBINS-I, AMSTAR 2), producing professionally formatted markdown documents and PDFs with verified citations in multiple styles (APA, Nature, Vancouver). Use when running a systematic or scoping literature review, research synthesis, or broad literature search, building a PRISMA flow diagram, screening studies, extracting an evidence table, or assessing risk of bias across biomedical, scientific, and technical domains. For quantitative pooling of effect sizes (forest/funnel plots) use alterlab-meta-analysis; for an open-ended multi-agent investigation, fact-check, or Socratic research-question work use alterlab-deep-research. Part of the AlterLab Academic Skills suite.EngineeringNo warnings★ 82↓ —
- alterlab-rnaseq-quantAlterLab-IEU/AlterLab-Academic-SkillsQuantifies bulk RNA-seq transcript abundance with salmon 2.x (the Rust rewrite; selective alignment or --sketch) and kallisto (v0.52.0, kb-python workflow), builds a decoy-aware gentrome index, runs quant with --gcBias -l A, then imports estimates via tximport/tximeta with a tx2gene map and hands differential expression to alterlab-pydeseq2. Warns that salmon 2.0 cannot read C++/pufferfish indices (rebuild every index), that --validateMappings is now accepted-but-ignored, and that 'salmon alevin' was REMOVED (single-cell now uses piscem + alevin-fry). Use when quantifying RNA-seq transcript abundance, running salmon or kallisto, building a decoy-aware index, or wiring tximport to DESeq2; for differential expression use alterlab-pydeseq2, for FASTQ-to-VCF variant calling use alterlab-nf-core-sarek. Part of the AlterLab Academic Skills suite.EngineeringNo warnings★ 82↓ —
- alterlab-scikit-learnAlterLab-IEU/AlterLab-Academic-SkillsClassical machine learning in Python with scikit-learn — algorithms, preprocessing, pipelines, and best-practice reference documentation. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, feature preprocessing, or building ML pipelines. Part of the AlterLab Academic Skills suite.EngineeringNo warnings★ 82↓ —
- alterlab-trdizinAlterLab-IEU/AlterLab-Academic-SkillsSearches TR Dizin (TÜBİTAK ULAKBİM national citation index) and verifies a journal's current national-index status through its confirmed unauthenticated REST/Elasticsearch API at https://search.trdizin.gov.tr/api/defaultSearch/{publication|journal|author|institution}/ (params q, order e.g. relevance-DESC, page), parsing hits.hits[]._source plus faceted aggregations, and derives indexing status from a journal record's isActive + journalYear coverage vs rejectYearList. Use when the user wants to search TR Dizin, check if a journal is TR Dizin indexed (TR Dizin'de var mı / taranıyor mu), find Turkish-indexed publications, verify national-index status before submitting, or audit doçentlik-eligible venues. For DergiPark hosting prefer alterlab-dergipark; for doçentlik points prefer alterlab-docentlik-eligibility; for teşvik scoring prefer alterlab-akademik-tesvik. Part of the AlterLab Academic Skills suite.EngineeringNo warnings★ 82↓ —
- dub-webhooksNewhookdeck/webhook-skillsReceive and verify Dub webhooks. Use when configuring Dub webhook endpoints, debugging dub-signature signatures, or handling link.created, lead.created, sale.created.EngineeringNo warnings★ 97↓ —
- n8n-webhookshookdeck/webhook-skillsReceive and authenticate webhooks sent by n8n's HTTP Request node. Use when building an endpoint that an n8n workflow calls, securing it with a Header auth shared secret (X-Webhook-Secret), Bearer auth or Basic auth, debugging 401s from n8n, or routing workflow payloads by an event field such as order.created or workflow.failed.EngineeringNo warnings★ 97↓ —
- hidden-code-skillclaude-world/claude-skill-antivirusA perfectly innocent-looking skill whose manifest hides nothing.EngineeringNo warnings★ 82↓ —
- bvnk-webhooksNewhookdeck/webhook-skillsReceive and verify BVNK webhooks. Use when setting up BVNK webhook listeners, debugging x-signature verification (base64 HMAC-SHA256), or handling payment, customer and ledger events like payment:v2:payin:status-change and bvnk:ledger:report:ready.EngineeringNo warnings★ 97↓ —
- dots-webhooksNewhookdeck/webhook-skillsReceive and verify Dots webhooks (payouts API, delivered via Svix). Use when setting up Dots webhook handlers, debugging svix-signature verification, or handling events like transfer.updated, payout_link.updated, flow.updated, and user.onboarded.EngineeringNo warnings★ 97↓ —
- hunting-for-supply-chain-compromise26zl/cybersec-toolkitHunt for supply chain compromise indicators including trojanized software updates, compromised dependencies, unauthorized code modifications, and tampered build artifacts.EngineeringNo warnings★ 87↓ —
- hume-webhooksNewhookdeck/webhook-skillsReceive and verify Hume EVI (speech-to-speech) webhooks. Use when setting up a Hume webhook handler, debugging X-Hume-AI-Webhook-Signature HMAC-SHA256 signature verification, or handling chat_started, chat_ended and tool_call events from Hume's emotionally intelligent voice AI.EngineeringNo warnings★ 97↓ —
- linq-webhooksNewhookdeck/webhook-skillsReceive and verify Linq webhooks (iMessage, RCS and SMS partner API, signed with Standard Webhooks). Use when setting up Linq webhook handlers, debugging webhook-signature verification, or handling events like message.received, message.sent, message.delivered, reaction.added, and phone_number.status_updated.EngineeringNo warnings★ 97↓ —
- session-relayclaude-world/director-mode-liteContinue real repository work between Claude Code, Codex CLI, and Grok Build with a privacy-bounded, drift-aware handoff packet. Use for cross-vendor takeover, context-limit checkpoints, multi-hop Claude→Codex→Grok relays, or receiving an existing Director packet. Use native resume commands for same-CLI history; never treat another vendor's session ID as portable.EngineeringNo warnings★ 80↓ —
- mono-webhooksNewhookdeck/webhook-skillsReceive and authenticate Mono webhooks. Use when setting up a Mono (open banking: Connect and DirectPay) webhook endpoint, verifying the mono-webhook-secret header, debugging 401s, or handling events like mono.events.account_connected, mono.events.account_updated, direct_debit.payment_successful and direct_debit.payment_failed.EngineeringNo warnings★ 97↓ —
- slurm-job-script-generatorHeshamFS/materials-simulation-skillsGenerate correct, copy-pasteable SLURM sbatch job scripts and sanity-check HPC resource requests — configure nodes, MPI tasks, OpenMP threads, memory (per-node or per-cpu), GPUs, walltime, partitions, modules, and environment variables, with automatic detection of conflicting directives and oversubscription. Use when preparing a SLURM submission script, deciding between pure MPI and hybrid MPI+OpenMP layouts, standardizing #SBATCH directives across a team, debugging why a job won't launch or gets killed, or setting up GPU-accelerated simulation jobs, even if the user only says "I need to run this on the cluster" or "my job keeps getting killed."EngineeringNo warnings★ 83↓ —
- pax8-webhooksNewhookdeck/webhook-skillsReceive and authenticate Pax8 webhooks. Use when setting up a Pax8 partner Webhooks API endpoint, checking the Authorization header Pax8 sends back, debugging 401s, or handling SUBSCRIPTION, INVOICE, CLIENT, PRODUCT, QUOTE and USER topic events such as SUBSCRIPTION CREATE.EngineeringNo warnings★ 97↓ —
- code-reviewerTestAny-io/testany-agent-skillsCode review, implementation review, 源码评审、实现复审。Use when: implementation Candidate 已形成，需要基于已批准需求/设计和精确 Git 边界做首次完整 Code Review 或整改 delta 复审。Do not use for API/HLD/LLD/Test/Runbook review or deployment approval.EngineeringNo warnings★ 82↓ —
- testany-debugTestAny-io/testany-agent-skills分析 Testany 测试失败原因 - 排查问题、查看日志、定位根因；处理签名日志前先单独加载本 skill，勿回显原始请求。EngineeringNo warnings★ 82↓ —
- redo-webhooksNewhookdeck/webhook-skillsReceive and authenticate Redo returns webhooks. Use when setting up a Redo webhook endpoint, checking the Authorization Bearer header sent with every delivery, debugging 401s, or handling return.created and return.updated events (plus backfill events) for e-commerce returns.EngineeringNo warnings★ 97↓ —
- simulation-failure-triageHeshamFS/materials-simulation-skillsFirst-response triage for cross-code (LAMMPS/VASP/QE/MOOSE) simulation failures: classifies the failure signature (nonconvergence, NaN/Inf, exploding energy, unstable timestep, pressure blow-up, missing potentials/pseudopotentials, memory exhaustion, process crash/segfault, corrupted output, incomplete runs) and proposes a SAFE one-change-at-a-time RETRY LADDER with explicit STOP CONDITIONS, prioritizing evidence preservation. Use as the immediate first response to a failed or suspicious run. For deep per-stage validation, conservation/physical-bounds checks, and "can I trust these results" analysis, defer to the simulation-validator skill.EngineeringNo warnings★ 83↓ —
- nonlinear-solversHeshamFS/materials-simulation-skillsSelect and configure nonlinear solvers for root-finding f(x)=0, optimization min F(x), and least-squares problems — choose among Newton, Newton-Krylov, quasi-Newton (BFGS, L-BFGS), Broyden, Anderson acceleration, and Levenberg-Marquardt methods, configure line search or trust-region globalization, diagnose convergence rate (quadratic, linear, stagnated), and assess Jacobian quality and conditioning. Use when a Newton solver converges slowly or diverges, choosing between line search and trust region, debugging nonlinear iteration failures in FEM or phase-field codes, or selecting a solver for large-scale unconstrained optimization, even if the user only says "my Newton iterations aren't converging."EngineeringNo warnings★ 83↓ —