Skills
A skill is a folder of instructions a compatible client loads when it becomes relevant. Filter by what a skill ships and what its author declares, then read it before you install it.
Ordered one entry per publisher in turn, so a page shows as many publishers as it has rows. Every skill is listed.
- repo-cve-exploitabilityby mappedskyFind the CVEs recorded against one GitHub repository, then read that repository's manifests and source through the…
- mariadb-callby mariadb-corporationMariaDB-specific syntax and behavior for CALL — optional parentheses when a procedure takes no arguments, OUT/INOUT…
- crew-initby mark22013333CREW 一鍵首次設定 —— 把 bug-workflow 與 feature-workflow 的初次設定整合成單一指令。當使用者提到 /crew-init、「CREW 一鍵設定」、「初始化 CREW」時觸發此 Skill。
- create-formal-verification-skillby marketplace-labsGenerate a project-local skill that formally verifies the code where a bug costs the most and tests reach the least, in…
- negative-keyword-sweepby markifactFind wasted spend in Google Ads search terms and add negatives at the right scope (account list, campaign, or ad…
- OctoparseSponsoredNo-code web scraping, on a schedule.Scrape with Octoparse
- appkit-modern-inputby markmalsUse when modernizing input handling in a macOS AppKit app — overriding mouseDown:/rightMouseDown:, hand-rolling mouse…
- evolve-design-systemby marshallhereSafely change established component APIs or tokens, with migration and regression coverage.
- reverse-engineeringby martinhwolchRead how a game actually works so a mod can hook it. Decompile .NET/Mono (ILSpy), IL2CPP (Cpp2IL, Il2CppDumper), Java…
- gitby martinsbrezauckisGit in Vibe Work - the user's Commit, Push, Create PR and Bring into main buttons; which git commands the agent's tools…
- computer-useby mashirokai观测并操控 macOS 本机桌面。用 Bash 通道 + 系统自带工具读取应用/窗口/屏幕截图/剪贴板,按「观测一次—动作一次—复核」纪律执行,权限缺失时呈引导卡后收口。当需要桌面自动化、操控鼠标键盘、点击、输入、截图、窗口与界面元素读取、…
- masthead-storage-savings-with-datasetsby masthead-dataOptimize BigQuery storage costs at the dataset level by switching storage billing models and setting expiration…
- tddby matoousFix a bug with a focused failing-before and passing-after regression check. Use when the user requests TDD or a…
- grillingby matsubaraiGrill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or…
- kotlin-springbootby matteocodognoKotlin and Spring Boot development. Trigger for ANY Kotlin, Spring Boot, JVM, Maven, jOOQ, Liquibase,…
- create-formal-verification-skillby matthew110703Generate a project-local skill that formally verifies the code where a bug costs the most and tests reach the least, in…
- log-inbox-boss-maxxingby matthewdonsemail-labBossmaxxing: giving out tasks to the team. A log play (docs/useCases/inbox/bossMaxxing.md): Give out tasks to the…
- principle-experience-firstby matthewyjiangApply when product, UX, or feature-scope tradeoffs come up. Choose user delight over implementation convenience; ship…
- interface-contractsby mattlane66Define plain-language inputs, outputs, branches, errors, and open decisions when a selected slice crosses a meaningful…
- create-formal-verification-skillby mattsp1290Generate a project-local skill that formally verifies the code where a bug costs the most and tests reach the least, in…
- grillby mattwag05Settle unclear intent before doing any work, by asking the human numbered questions with recommended answers. Use when…
- funding-landscapeby mavenbioMap capital flow across a space: who is funding an indication, mechanism, target, or investor set, how much, and how it…
- clarity-flowby maxi3777The ClarityKit design flow — activate ONLY when the user explicitly asks for it (mentions clarity-flow / the ClarityKit…
- handoffby mbourmaudUse automatically when an accepted review must be summarized for a fresh agent, a task is being paused or resumed, or a…
- reuse-reviewby mcampbellrReview changes for duplicated implementations and missed compatible reuse, with evidence for both locations. Use for…
- troubleshootingby mcsockUses Chrome DevTools MCP and documentation to troubleshoot connection and target issues. Trigger this skill when…
- councilby megamen32Ask several suitable models to compare approaches for a requested council or a consequential unresolved decision.
- renoolab-piloter-receptionner-travauxby mehdimicraÀ charger avant de répondre dès qu'un client indique que les entreprises sont choisies ou que le chantier est préparé,…
- koto-qualifyby mehrdadxzakerEvaluate an existing local Responses route with bounded task, structured-output and tool-use probes; detect stale model…
- document-risks-and-debtby mehtrickCreate or update arc42 section 11 architecture risks and technical debt, including impact, mitigation, and lifecycle…
- observability-and-instrumentationby meisijiyaInstruments code so production behavior is visible and diagnosable. Use when adding logging, metrics, tracing, or…
- video-genby memesmakemillionsGenerate original AI video footage through Memelord with Higgsfield video models (Higgsfield Kling 3.0, Higgsfield…
- create-formal-verification-skillby mendeldamianGenerate a project-local skill that formally verifies the code where a bug costs the most and tests reach the least, in…
- desk-signal-scanby mendurimHow the desk finds and times opportunities without being asked - the Market Analyst's universe scan across every…
- story-videoby mengtoMake a short story video in Fil. Write the shots, make a picture for each, bring them to life as videos, add a voice or…
- react-reviewby mensononesSupplement an Argus review of changed React components or hooks with React state and effect semantics. Load only after…
- swiz-hooksby mherodRun `swiz hooks` in Claude Code or Codex
- rwalkby mhpdigitalUse when a recorded review needs working through with a human — walks a QR's rows one turn at a time, pre-reads and…
- handoffby michalmarCompact the current conversation into a handoff document for another agent to pick up.
- test-xunitby michelschepDiscover and run existing xUnit unit or integration tests in .NET solutions using their existing frameworks, fixtures,…
- wait-whatby microsoftStop. That last message did not land: re-pitch it.
- generate-avatarby mike-demo
- primitivesby mike-diffEnumerate all native Claude Code tools, modes, and configuration primitives available in the current session
- toolkit-ui-reviewby mikemoore1337Use for creating or critiquing UX/UI, landing pages and substantial visual redesigns; route through UX/UI Design…
- doc-auditby mili-ssmRuns the doc-curator agent to verify docs against code and compress them; edits only with 'apply'.
- create-formal-verification-skillby mineru98Generate a project-local skill that formally verifies the code where a bug costs the most and tests reach the least, in…
- create-formal-verification-skillby minghinmatthewlamGenerate a project-local skill that formally verifies the code where a bug costs the most and tests reach the least, in…
- check-compiler-errorsby mingsterRun compile and type-check commands and report failures
- quantitative-researchby minimax-aiDesign or review statistical, mixed-model, Bayesian, or machine-learning analyses for life-science data. Use when the…