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
15,79315,840 · page 330 / 449
qdrant-minimize-latencyGuides Qdrant query latency optimization. Use when someone asks 'search is slow', 'how to reduce latency', 'p99 is too high'…githubMining Industry Interview Response GeneratorGenerates concise, role-specific answers to interview questions for mining engineering positions, strictly adhering to specified…ECNU-ICALKMining Interview Response GeneratorGenerates interview answers for mining engineering roles (drill & blast, planner, etc.) adhering to specific word counts and…ECNU-ICALKmining-pubmed-literatureSearches and fetches PubMed and PMC via NCBI E-utilities (ESearch then EFetch/ESummary) to gather biomedical evidence and build…maziyarpanahiministererlaubnis-42-gwbWenn es um Ministererlaubnis Paragraf 42 GWB in Kartellrecht — Marktabgrenzungsprüfung geht: ordnet Akteninhalt, Belege, Lücken…Klotzketteministerien-tatbestand-beweis-und-belegeWenn es um Ministerien: Tatbestandsmerkmale, Beweisfragen und Beleglage in Legistik-Werkstatt geht: ordnet Akteninhalt, Belege…Klotzketteminutes-graphPolicy-safe relationship rankings, commitments, aliases, person profiles, and topic research. Always use Minutes' bounded native…silversteinminutes-ideasSurface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my…silversteinmisq-literature-positioningUse when positioning a MIS Quarterly manuscript inside the right information-systems conversation — engaging canonical IS work…brycewang-stanfordmisra-complianceMISRA C/C++ static analysis and compliance checkinga5c-aiwritesmissbrauch-vertretungsmachtWenn es um Missbrauch der Vertretungsmacht in BGB AT Prüfer geht: ordnet Sachverhalt, Norm, Beweislast, Gegenargumente und…Klotzkettemissbrauchsaufsicht-tk-mitnutzungWenn es um TK-Missbrauchsaufsicht als Sonderkartellrecht in Telekommunikationsrecht geht: ordnet Sachverhalt, Norm, Beweislast…Klotzkettemissing-protectionsAudits a contract against type-specific protection checklists to find gaps, then provides ready-to-insert clause language for…jeremylongshoremistral-incident-runbookExecute Mistral AI incident response procedures with triage, mitigation, and postmortem. Use when responding to Mistral…jeremylongshoremistral-multi-env-setupConfigure Mistral AI across development, staging, and production environments. Use when setting up multi-environment deployments…jeremylongshorewritesmistral-observabilitySet up comprehensive observability for Mistral AI with metrics, traces, and alerts. Use when implementing monitoring for Mistral…jeremylongshorewritesmit-leasing-und-lpWenn es um Liqui mit Leasing in Liquiditätsplanung — Power geht: ordnet Sachverhalt, Norm, Beweislast, Gegenargumente und…KlotzkettemitarbeiterWenn es um Mitarbeiter in Berufsrecht Wirtschaftsprüfer geht: ordnet Sachverhalt, Norm, Beweislast, Gegenargumente und nächsten…Klotzkettemitarbeiter-need-non-solicit-permittedWenn es um NDA: Mitarbeiter/Need-to-Know in NDA-Abgleich geht: zerlegt Ergebnis, Frist, Zuständigkeit, Beweislast und…Klotzkettemitarbeiterinterview-arbeitsrechtWenn es um Mitarbeiterinterviews in Internal Investigations Praxis geht: ordnet Sachverhalt, Norm, Beweislast, Gegenargumente und…KlotzkettemitbestimmungsgesetzWenn es um Mitbestimmungsgesetz in AG/SE-Aufsichtsrat Praxis geht: ordnet Sachverhalt, Norm, Beweislast, Gegenargumente und…KlotzkettemitgliederrechteWenn es um Mitgliederrechte in Parteienrecht und Parteiorganisation geht: erstellt den passenden Entwurf aus Sachverhalt, Norm…Klotzkettemitgliederversammlung-kleine-kreisWenn es um Kleine Partei Praxis in Parteienrecht und Parteiorganisation geht: ordnet Akteninhalt, Belege, Lücken und…Klotzkettemitgliedschaftsrecht-vs-nachfolge-erbfall-ohgWenn es um Mitgliedschaftsrecht Vs Sonderrecht in Gesellschaftsrechtliche Treuepflicht geht: ordnet Sachverhalt, Norm…Klotzkettemittelstand-ma-insolvenzreifeWenn es um Freistehender Insolvenzreife- und StaRUG-Schwellencheck (Mittelstand) in Mittelstands-Corporate/M&A geht: erstellt den…Klotzkettemittelstand-ma-tabellenreviewWenn es um Freistehender Tabellenreview (Mittelstand) in Mittelstands-Corporate/M&A geht: ordnet Akteninhalt, Belege, Lücken und…Klotzkettemitwirkungspflicht-60-bis-67-sgb-iWenn es um Mitwirkungspflicht 60 Bis 67 Sgb I in selbstvertreter-sozialgericht geht: erstellt den passenden Entwurf aus…KlotzkettemitwirkungspflichtenWenn es um Mitwirkungspflichten in AGB-Recht-Prüfer geht: ordnet Sachverhalt, Norm, Beweislast, Gegenargumente und nächsten…Klotzkettemixed-integer-optimizationMixed-integer linear and nonlinear programminga5c-aiwritesmlsys-author-responseUse when drafting MLSys author responses on OpenReview under the venue's compressed rebuttal window, prioritizing…brycewang-stanfordmlsys-camera-readyUse when preparing an accepted MLSys paper for publication on proceedings.mlsys.org, covering de-anonymization of the…brycewang-stanfordmlsys-reproducibilityUse when hardening the reproducibility of MLSys performance claims, pinning the full system layer from driver to interconnect…brycewang-stanfordmlsys-submissionUse when auditing an MLSys submission for OpenReview readiness, covering the two-column 10-page body excluding references, the…brycewang-stanfordmlsys-supplementaryUse when deciding what goes into an MLSys appendix versus the 10-page body, exploiting the venue's unlimited separately-uploaded…brycewang-stanfordmobbing-konflikt-intakeWenn es um Mobbing Konflikt Intake in Start-up-HR-Personalabteilung Berlin geht: entwickelt Verhandlungsziel, Vergleichskorridor…Klotzkettemobicom-experimentsUse when designing or auditing the evaluation of a MobiCom submission — building real-device testbeds, choosing RF and channel…brycewang-stanfordmobicom-related-workUse when building or auditing the related-work of a MobiCom paper — sweeping the SIGMOBILE and networking literature lanes…brycewang-stanfordmobile-gamesMobile game development principles. Touch input, battery, performance, app stores.sickn33mobile_network_qa_concise_sauterAnswer technical questions about LTE, WLAN, and mobile networks based on the Sauter reference, strictly adhering to…ECNU-ICALKmobile-privateWenn es um Mobile-Device-Forensik in Internal Investigations in Internal Investigations Praxis geht: ordnet Sachverhalt, Norm…Klotzkettemobile-roboter-nis2-betreiberWenn es um Mobile Roboter AMR AGV in robotik-recht geht: ordnet Sachverhalt, Norm, Beweislast, Gegenargumente und nächsten…Klotzkettemobile-sensor-integrationIntegrate mobile device sensors — accelerometer, gyroscope, GPS, camera, and biometric APIs for iOS and Android.a5c-aiwritesmobisys-author-responseUse when drafting a MobiSys rebuttal after round-2 reviews — working within the scope limit (correct factual errors, answer…brycewang-stanfordmobisys-related-workUse when positioning a MobiSys submission against the mobile-systems literature — offload, on-device ML, mobile OS and runtimes…brycewang-stanfordmobisys-submissionUse when auditing a MobiSys submission for HotCRP readiness — the paper-registration prerequisite, the single December UTC…brycewang-stanfordmobisys-topic-selectionUse when deciding whether a project belongs at MobiSys — testing whether the core contribution is a mobile or embedded system…brycewang-stanfordMock Trial Direct Examination Question RefinementRefines leading questions into neutral, non-leading questions suitable for direct examination in mock trials, and advises on…ECNU-ICALKmockitoUse when generating mocks, stubbing methods, verifying interactions, capturing arguments, or choosing between mocks, fakes, and…evanca
← Prev330 / 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