Agent skills

Other skills

21,532 skills an agent can load when the work is Other — read straight from the source repositories, with what each one does, what ships alongside it, and where it came from.

Toolclaude-code 63,296codex 9,782cursor 7,187copilot 2,384windsurf 127cline 83
CategoryWorkflow & Productivity 11,752AI & Agents 4,985Data & Analytics 4,761Code Review & Quality 2,986Security 2,828Backend & API 2,504Design & Presentation 2,373Documentation 2,183Content & Marketing 2,060Testing & QA 1,778DevOps & Cloud 1,275Databases 1,133Frontend 1,043Business & Finance 724Media & Video 514Other 21,532
21,532 found
13,72913,776 · page 287 / 449
Составление ответов для поддержки iOS-приложенияГенерация вежливых ответов на английском языке для пользователей iOS-приложения по вопросам подписок, оплаты, триального периода…ECNU-ICALKiot-anomaliesDetect and classify telemetry anomalies on Cognitum Seed devices. Use when investigating a device that's reporting odd metrics…ruvnetIoT Application Specification Report GenerationAnalyze a specified IoT application and generate a structured technical report covering links, problem statements, solutions…ECNU-ICALKiot-firmwareOrchestrate firmware rollouts with canary deployment and anomaly-gated advancementruvnetiot-fleetCreate and manage Cognitum Seed device fleets with firmware policiesruvnetiot-tk-kartellrechtWenn es um IoT, M2M und SIM-Karten in Telekommunikationsrecht geht: ordnet Sachverhalt, Norm, Beweislast, Gegenargumente und…Klotzketteiot-witness-verifyVerify witness chain integrity and detect provenance gapsruvnetip-indemnityWenn es um IP-Indemnity Software in Softwarerecht Deutschland/EU/International/USA geht: zerlegt Ergebnis, Frist, Zuständigkeit…Klotzketteip-nutzungsrechteWenn es um IP Nutzungsrechte in AGB-Recht-Prüfer geht: ordnet Sachverhalt, Norm, Beweislast, Gegenargumente und nächsten Schritt…Klotzketteipsn-author-responseUse when drafting an IPSN-lineage rebuttal, covering the double-blind response to sensor-systems reviewers on ground truth…brycewang-stanfordipsn-experimentsUse when designing or auditing IPSN-lineage evaluations, covering real testbeds and deployments, ground-truth instrumentation…brycewang-stanfordipsn-reproducibilityUse when strengthening IPSN-lineage reproducibility for a hardware/embedded/deployment artifact, covering firmware and board…brycewang-stanfordipsplan-cram-down-spezialWenn es um IPSPlan: Cram-Down in Insolvenzplan- und StaRUG-Planwerkstatt geht: entwickelt Verhandlungsziel, Vergleichskorridor…Klotzkette黄丝 / iptv / conversationGeneral SOP for common requests related to 黄丝, iptv, conversation.ECNU-ICALKir_quiz_tutorA concise quiz tutor for Information Retrieval topics, covering both Elasticsearch architecture and probabilistic models like…ECNU-ICALKiros-experimentsUse when designing or auditing IROS experiments — real-robot trial counts, success criteria set in advance, reset procedures…brycewang-stanfordiros-related-workUse when positioning an IROS submission against robotics-systems literature across ICRA, IROS, RSS, CoRL, RA-L, and T-RO…brycewang-stanfordirrefuehrende-systemwerbung-und-franchise-salesWenn es um Franchise: Irreführende Systemwerbung und Franchise Sales in Franchiserecht Praxis geht: ordnet Akteninhalt, Belege…Klotzketteirrtumsanfechtung-paragraph-119-1Wenn es um Irrtumsanfechtung — Paragraf 119 Abs. 1 BGB in BGB AT Prüfer geht: ordnet Sachverhalt, Norm, Beweislast…Klotzketteis-this-actually-goodGet an honest verdict on whether something you made is actually good — not the reflexive 'this is great!' but a real…mohitagw15856isabelle-hol-interfaceInterface with Isabelle/HOL for classical mathematics formalizationa5c-aiwritesisca-experimentsUse when designing or auditing the evaluation of an ISCA paper — pinning simulator fidelity to the claims it must carry…brycewang-stanfordisca-reproducibilityUse when making an ISCA paper's results regenerable — pinning simulator versions and local patches, archiving per-figure…brycewang-stanfordisca-supplementaryUse when deciding what accompanies an ISCA submission beyond the 11 reviewed pages — what must live inside the page budget…brycewang-stanfordisca-topic-selectionUse when deciding whether a project belongs at ISCA, the ACM/IEEE flagship architecture symposium — testing whether the machine…brycewang-stanfordiso-26262-complianceFunctional safety process and analysis support per ISO 26262a5c-aiwritesISP Technical Support RoleplayAct as a technical support operator for an Internet Service Provider, handling connectivity inquiries and ticket requests while…ECNU-ICALKisr-contribution-framingUse when turning results into an explicit contribution to IS for an Information Systems Research (ISR) manuscript and when…brycewang-stanfordisr-submissionUse when running the final pre-submission preflight for an Information Systems Research (ISR) manuscript — INFORMS ScholarOne…brycewang-stanfordisr-topic-selectionUse when shaping or sanity-checking a research question for Information Systems Research (ISR) — testing sociotechnical…brycewang-stanfordissta-related-workUse when positioning an ISSTA submission against the testing and analysis literature, covering the sibling venues (ICSE, FSE…brycewang-stanfordissta-reproducibilityUse when strengthening ISSTA reproducibility and verifiability evidence, covering pinned subject programs and benchmark versions…brycewang-stanfordissta-supplementaryUse when deciding what lives in the ISSTA 18-page body versus the artifact and any appendix, covering the no-unlimited-appendix…brycewang-stanfordissue-reporter只在用户明确要求提交 GitHub Issue、GitHub Bug Report 或 GitHub Feature Request 时使用。用户只说“提交问题”“提交反馈”“上报 bug”“这是个 bug”或描述功能建议但未点名 GitHub…CherryHQissue-trackerTrack and manage project issues with escalation and resolution workflowsa5c-aiwritesissue-tree-generatorGenerate and validate issue trees for structured problem solving with MECE validationa5c-aiwritesissue-triage-liveTriage the user's REAL issue tracker — read open issues via the GitHub/Linear connector, label / prioritise / dedupe / flag them…mohitagw15856issues-list-and-roadmapWenn es um Issues List in commercial-courts-deutschland geht: ordnet Sachverhalt, Norm, Beweislast, Gegenargumente und nächsten…KlotzketteissuesInteract with GitHub issues - create, list, and view issues.sickn33istio-traffic-managementComprehensive guide to Istio traffic management for production service mesh deployments.sickn33istio-traffic-managementConfigure Istio traffic management including routing, load balancing, circuit breakers, and canary deployments. Use when…wshobsonit-cloud-kammeraufsicht-ruegeWenn es um IT, Cloud, digitale Werkzeuge und Outsourcing in Berufsrecht Anwälte geht: ordnet Sachverhalt, Norm, Beweislast…Klotzketteit-freelancer-agil-projektWenn es um IT-Freelancer im agilen Projekt in Sozialversicherungsstatus-Prüfer / DRV-Statusfeststellung geht: ordnet Sachverhalt…Klotzketteit-hardware-refreshWenn es um IT Hardware Refresh im Leasing in Leasingrecht Praxis geht: ordnet Sachverhalt, Norm, Beweislast, Gegenargumente und…Klotzketteit-leasing-hardware-software-cloud-bundleWenn es um IT-Leasing: Hardware, Software und Cloud-Bundle in Leasingrecht Praxis geht: ordnet Sachverhalt, Norm, Beweislast…Klotzketteit-prozess-versandmappe-endfertigenEndfertigt IT-rechtliche Klagen, Eilanträge und Erwiderungen: fixiert Vertrags- und Softwareversionen, ordnet Tickets…Klotzketteit-sicherheit-cloud-vertraegeWenn es um IT-Sicherheit und Cloud in Bank-Rechtsabteilung geht: ordnet Sachverhalt, Norm, Beweislast, Gegenargumente und…Klotzketteit-system-lieferketten-lksg-lebensmittelWenn es um Franchiserecht: IT-System, POS-Kassendaten und Datenzugriff in Franchiserecht Praxis geht: ordnet Sachverhalt, Norm…Klotzkette
← Prev287 / 449Next →
How the catalog works
What is an agent skill?

A folder with a SKILL.md inside — instructions, and often scripts and assets, that an AI agent loads when the task matches. Claude Code, Codex, Cursor and Copilot all read the same format, so one skill usually works across them.

Where does this catalog come from?

We read 655 source repositories straight from their file trees rather than from submitted listings — what you see is what is actually published. 103 repositories were rejected because they advertise skills but contain none: link lists, not folders.

Why is there no install counter?

Because install counts live in the registry that serves `npx skills add`, and that is not ours — publishing a number we cannot verify would be worse than showing none. Instead we show where a skill comes from and whether attention around its source is actually growing, measured from our own weekly snapshots.

Do you deduplicate?

Yes, and it matters more than expected. Aggregator repositories republish the same skill in several places — one source carried 6,317 SKILL.md files for 2,001 actual skills. We collapse by folder name and keep the canonical copy, so the catalog counts things, not copies.

Keep going