Explorar el registro

Todas las entradas, por orden alfabético — 56.437 en total. Página 187 de 226.

• rudder-tracking-plansCreates and manages tracking plans that validate events against schema contracts. Use when creating or managin
• rudder-transformationsCreates and manages RudderStack transformations and libraries with local testing. Use when creating, editing,
• rudder-typer-workflowGenerates type-safe SDKs (Swift/Kotlin) from tracking plans with compile-time validation. Use when generating
• rudhra-swarmOrchestrate multiple specialized agents or agent roles for a project. Use when the user says "rudhra swarm", "
• rudin-real-complex-analysisProblem-solving with Rudin's Real and Complex Analysis textbook
• rudycazabon/OpenUSD-AIA collection of USD tools that use a number of AI interfaces MCP and Agent2Agent.
• ruffUse this skill when linting, formatting, or fixing Python code with ruff. Activates on mentions of ruff, ruff
• ruff-preset-applierMinimal daemon reporting service uptime metrics.
• rufloRuflo is a multi-agent orchestration platform for AI coding agents (Claude Code, Cursor, Codex, Copilot, Gemin
• rule-accessibilityMANDATORY when editing files matching ["frontend/src/**/*.tsx", "frontend/src/**/*.ts"]. Accessibility require
• rule-catalogBrowse hookify rule catalog. Use when installing pre-built rules or browsing categories. Do not use when writi
• rule-conditionsGenerate a custom Alfresco rule condition evaluator with parameter definitions, Spring bean registration, and
• rule-design-systemDesign-token rules: semantic tokens over inline colors, where tokens are defined, and the one case hardcoded c
• rule-extractionExtract a structured list of rules from all markdown files at the top level of a skill directory. Use this ski
• rule-file-organizationWhere generated files belong. Archives, backups, handoffs, reports, and screenshots go under .claude/, never t
• rule-patcherPropose, test, and promote patches to rules, workflows, and skills via replay-gated promotion
• rule-securitySecurity rules this project always applies: secret handling, input validation, parameterized queries, and Supa
• rule-verificationWhat counts as done for each kind of change: the required verification per task type, and the six cross-cuttin
• rule-windowsWindows-specific development rules: cmd /c wrappers for MCP, dev servers in an external terminal, path convent
• rulesUse when the user asks about Codex Rules behavior, injected project rules, supported rule file locations, matc
• rules-auditorAudit Claude Code rules and CLAUDE.md/AGENTS.md files for staleness, quality, and drift. Use when asked to aud
• rules-evalEvaluate Claude Code rules in .claude/rules/. Use for frontmatter, globs, and quality audits.
• rules-review変更差分をリポジトリの rules に照らしてレビューし、ルール違反だけを重大度つきで検出する。「コードレビュー」「差分レビュー」「実装をレビュー」「rules に照らして確認」「PR の差分を見て」時に使用。.agen
• rum-trackingGuides product analytics and RUM (Real User Monitoring) event tracking in web (React/Next.js) and mobile (Reac
• runRun TypeScript solution against test cases. Use when user wants to test their code.
• run-adk-evalsRuns Google Agent Development Kit (ADK) evaluations in sorted order with detailed results, failure summaries,
• run-agentConfigures and runs agents with different adapters including Claude, OpenAI, CrewAI, Lyzr, and GitHub Models.
• run-benchmark-driven-rdTurn ambitious or uncertain engineering goals into a falsifiable, benchmark-gated R&D system with calibrated e
• run-bitrouter-benchmarkUse when a user wants to run, compare, resume, audit, share, or submit a Harbor benchmark through BitRouter, i
• run-campaignЗапускает маркетинговую кампанию от начала до конца — анализ продаж, контент-бриф, генерация макетов, постанов
• run-claude-osintBuild, validate, and run the claude-osint skills repo — check SKILL.md frontmatter, run the secret_scan.py and
• run-competitive-analysisRuns an NN/g-style competitive analysis: competitive usability evaluation (holistic or focused, competitors tr
• run-contextual-researchPlans and runs research in the user's real environment or real timeline: contextual inquiry (master-apprentice
• run-evalsdo e2e tests, run e2e, validate feature, prove it works, PR proof, frame proof, pnpm evals. Launches iPolloWor
• run-first-campaignThe packaged cold-start campaign workflow - takes an owner with no list, no CRM, and no outbound history from
• run-full-suiteDiscover and run all speckit shell test suites across every feature spec in the repository, then print a conso
• run-gaussActs as a knowledge base providing environment checklists, directory/scratch management, and bash command temp
• run-heuristic-evaluationRuns an expert usability inspection without users: Nielsen's 10 heuristics operationalized with per-heuristic
• run-historyInspect CCAM dashboard-run history and relate live run handles to persisted Claude Code or Codex sessions. Use
• run-history-skill-builderTurn a completed task, browser flow, artifact pipeline, failure-recovery trace, or repeatedly refined workflow
• run-history-skill-upgraderUse real run evidence, validation failures, source drift, platform drift, and user feedback to plan and, only
• run-hugging-face-training-smokeRuns one bounded, private Hugging Face training smoke with immutable inputs, local preflight checks, explicit
• run-lint-and-formatRun linters and formatters for this project and summarize issues.
• run-nx-checksRun nx format, lint, test, and build on affected or specified projects, then fix unambiguous failures
• run-oikosBootstrap, launch, and smoke-test the Oikos (Futari) Next.js 16 dev server. Use when the user asks to "run the
• run-optimizerDrives any shell-invokable coding agent (Claude Code, Codex, Gemini CLI, opencode, Cursor, Factory Droid, GitH
• run-pipelineExecute and monitor Harness pipeline runs via MCP tools. Find pipelines, provide runtime inputs, trigger execu
• run-protocolStep-by-step execution of the OWC protocol with mandatory checkpoint at each step. Prevents skipping steps (in
• run-review-repair-loopConduct a bounded, repository-grounded code self-review and repair loop with objective 1-5 scoring, exact scop
• run-sdlcNavigate the AI-SDLC workflow for a given work item or artifact: report where it is in the lifecycle and what
• run-seo-page-loopRun an SEO page observation-action-review loop with persistent Memory by coordinating demand research, page cr
• run-simulatorBuild and launch the app in the iOS Simulator. Automatically selects an appropriate simulator device, boots it
• run-skill-tunerRun, smoke-test and debug skill-tuner. Use when asked to run skill-tuner, probe a document, compare two runs,
• run-smoke-testsInspect an unfamiliar repository, interpret a broad Markdown user journey at runtime, operate the real product
• run-tamaguiRun or rebuild the local Tamagui/Next.js frontend (frontends/tamagui). Use when the user wants to start the Ta
• run-tasksOrchestrate task execution via beads and sub-agents. Gets ready work from beads, spawns appropriate agents bas
• run-telemetryEmit structured workflow telemetry for AI agent runs. Use for run metrics, step latency, cost, tokens, model,
• run-testsRun or recommend the exact .NET test command. ALWAYS USE when asked to run, filter, or troubleshoot .NET tests
• run-wwtt-websiteRun, start, build, screenshot, or test the WanderWave Travel & Tours website (React/Vite frontend + Node/Expre
• run.chromeflow/chromeflowLets Claude Code or Codex CLI drive your real Chrome — sessions intact, 28 browser tools.
• run.cityheart/heart-routesHeart-shaped GPS running routes in 200+ cities — charity, gift, memorial, anniversary.
• run.parlay/parlayRead-only MCP server for live Polymarket, Kalshi, Limitless odds; Manifold sentiment.
• run.stas/stasConnect Claude to your Intervals.icu watch data for fitness, workout review, and plan writing.
• runax-software-nuget-managerManage NuGet packages in .NET projects/solutions. Use this skill when adding, removing, or updating NuGet pack
• runbook[UDS] 引導 Runbook 撰寫、維護、演練和覆蓋率報告
• runbook-creationCreate operational runbooks and standard operating procedures. Document troubleshooting guides and recovery pr
• runbook-skillclaude private skills md
• runbooksPre-built scenario configurations for common multi-agent workflows. Quick-start templates for MVPs, features,
• runeRegistry manager for skills, agents, and rules. Keeps .claude/skills/, .claude/agents/, and .claude/rules/ syn
• rune-kit-auditComprehensive project audit — security, dependencies, code quality, architecture, performance, infra, docs, an
• rune-kit-councilGathers N independent, decorrelated perspectives across model families (external CLIs when present, subagents
• rune-kit-dbDatabase workflow specialist. Generates migration files with rollback scripts, detects breaking schema changes
• rune-kit-debugRoot cause analysis for bugs and unexpected behavior. Traces errors through code, uses structured reasoning, a
• rune-kit-designDesign system reasoning. Maps product domain to style, palette, typography, and platform-specific patterns. Ge
• rune-kit-docsAuto-generate and maintain project documentation. Creates README, API docs, architecture docs, changelogs, and
• rune-kit-fixApply code changes and fixes. Writes implementation code, applies bug fixes, and verifies changes with tests.
• rune-kit-mcp-builderBuild Model Context Protocol servers from specifications. Use when creating an MCP server for a tool, resource
• rune-kit-onboardAuto-generate project context for AI sessions. Use when starting on a new repo for the first time, or when CLA
• rune-kit-planCreate structured implementation plans from requirements. Produces master plan + phase files for enterprise-sc
• rune-kit-researchWeb search and external knowledge lookup. Gathers data on technologies, libraries, best practices, and competi
• rune-kit-retroEngineering retrospective. Analyzes commit history, work patterns, and code quality metrics with trend trackin
• rune-kit-reviewCode quality review — patterns, security, performance, correctness. Finds bugs, suggests improvements, trigger
• rune-kit-testTDD test writer. Writes failing tests FIRST (red), then verifies they pass after implementation (green). Cover
• rune-kit-worktreeGit worktree lifecycle management. Use when team needs parallel isolated workspaces for multi-stream developme
• runecraftai-code-simplificationSimplifies code for clarity while preserving exact behavior (Chesterton's Fence, Rule of 500). Use when refact
• runecraftai-idea-refineRefines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use wh
• runecraftai-interview-meExtracts what the user actually wants through one-question-at-a-time interview until ~95% confidence about the
• runecraftai-typescript-patternsTypeScript best practices and patterns for type-safe, maintainable code. Covers discriminated unions, generics
• runesleo/x-readerUniversal content reader MCP Server for 10+ platforms
• runnableUse when the user asks for a one-word acknowledgement drill — replies with exactly the word the drill names.
• runnerHub for 3D endless-runner games — list control templates, recommend a pattern, point to live demos and /runner
• runner-newScaffold a new endless-runner game folder from a control template (ski|moto|ski-side|wing|loop). Trigger `/run
• runner-tuneTune an existing runner game — CONFIG difficulty, theme CSS, bloom — without rewriting architecture. Trigger `
• running-bug-review-boardRuns real-user QA, manual test plans, UX bug hunts, build sign-off, bug filing, and bug triage for web or iOS/
• running-claude-code-via-litellm-copilotUse when routing Claude Code through a local LiteLLM proxy to GitHub Copilot, reducing direct Anthropic spend,
• running-coachWeekly running coaching sessions that analyze training logs against the training plan, with primary focus on r
• running-decision-processesRun a decision process end-to-end: RAPID/DACI roles, options matrix, decision log, comms.
• running-design-reviewsRun high-signal design reviews: brief, feedback log, decision record, follow-up plan.
• running-effective-1-1sProduce a 1:1 Operating System Pack (agendas, coaching prompts, career conversation plan). See also: running-e
• running-effective-meetingsRun effective meetings: brief, agenda, facilitation script, decision log. See also: running-effective-1-1s (1:
• running-marketing-campaignsPlans, creates, and optimizes digital marketing campaigns including content strategy, social media, email mark
• running-meetingsHelp users master the art of facilitating productive, decision-oriented meetings that unblock teams, strengthe
• running-offsitesPlan and run a team offsite/retreat: agenda, facilitation guide, logistics, post-offsite action plan.
• running-programmer运用《奔跑吧，程序员》(Hello Startup) 的进化式增长理念，指导创业期的产品、技术与团队决策。适用于用户想验证新产品想法、做技术选型或架构设计、担心过度设计、组建创业团队或招聘把关、制定产品迭代节奏时使用。
• runtime-adapterOfficial catalog registry for skill-hub
• runtime-adaptersUse when creating Codex, Claude Code, Gemini CLI, Cursor, or AGENTS.md runtime adapters from one canonical age
• runtime-attempt-report-writerProduce an evidence-bound runtime attempt report with truth labels and next steps; does not certify upstream s
• runtime-bridge-conflict-resolverDetect and resolve MCP bridge conflicts (Path 1 Lab MCP + Path 2 ahujasid running together, port 9876 collisio
• runtime-installAgent-native course marketplace and skill registry for executable AI-agent curricula
• runtime-path-pickerChoose Path 1 Lab MCP, Path 2 ahujasid bridge, or CLI appendix from constraints; Connector hosts Path 1 only w
• runwayAgent-callable Runway tools — generate images and video from text or images, edit and upscale media, animate c
• runway-calculatorCalculate months of cash runway at current burn rate.
• runxGoverned runtime for agent skills: discover and install portable skills, run bounded skill graphs with explici
• runzeroEvery runZero query, plus a local SQLite copy of your whole attack surface that diffs over time, joins assets
• russian-abbreviationsПравила сокращений в русском тексте по справочнику Мильчина и Чельцовой. Используй при работе с любым русским
• russian-citations-bibliographyПравила цитирования, оформления примечаний и библиографических ссылок в русском тексте по справочнику Мильчина
• russian-editorial-reviewКомплексная проверка оформления русского текста по справочнику Мильчина и Чельцовой. Это мета-навык, который о
• russian-lists-punctuationПравила оформления перечней (списков) в русском тексте по справочнику Мильчина и Чельцовой. Используй при созд
• russian-names-capitalizationПравила написания имён собственных, прописных букв и кавычек в русском тексте по справочнику Мильчина и Чельцо
• russian-numbers-datesПравила оформления чисел, дат, времени и знаков в русском тексте по справочнику Мильчина и Чельцовой. Использу
• russian-text-qualityUse when reviewing or writing code that contains Russian-language UI strings, i18n locale files (ru.json, ru.y
• russian-typography-formattingПравила типографики и оформления русского текста по справочнику Мильчина и Чельцовой: выделения (курсив, полуж
• rustInstall the right AI skills for your project stack in one command
• rust-architectUse when designing or architecting Rust applications, creating comprehensive project documentation, planning a
• rust-async-internalsUse when authoring or reviewing async Rust that may run inside tokio::select! / tokio::time::timeout / Futures
• rust-best-practice[Critical] Best practice for Rust coding. Always activate this skill before authoring Rust code or answering q
• rust-best-practicesAI Best Practices Audit Skills
• rust-buildBuild Rust native libraries for the FFI plugin
• rust-code-expertEngineer idiomatic Rust with ownership, borrow checker, lifetimes, traits, cargo, clippy, async/Tokio, unsafe,
• rust-devPractical day-1 guide to building applications in Rust well. Covers the mental model (ownership, errors as val
• rust-engineerWrites, reviews, and debugs idiomatic Rust code with memory safety and zero-cost abstractions. Implements owne
• rust-expert-best-practices-code-reviewRust best practices and code quality guidelines for writing idiomatic, safe, and performant Rust code. This sk
• rust-masterRust expert for async systems, unsafe code, and zero-cost abstractions
• rust-migrationC/C++ to idiomatic Rust conversion patterns and pipeline. Covers pointer translation, memory management, error
• rust-ownershipBorrow checker fluency: lifetimes that actually need naming, when to reach for Rc/RefCell, and the clone that
• rust-patternsRust best practices, patterns, and idioms. Covers ownership, error handling with Result/Option, traits, lifeti
• rust-proMaster Rust 1.75+ with modern async patterns, advanced type system features, and production-ready systems prog
• rust-projectModern Rust project architecture guide for 2025. Use when creating Rust projects (CLI, web services, libraries
• rust-reviewPerforms comprehensive Rust security review for safe/unsafe boundary issues, memory safety in unsafe blocks, c
• rust-safety写 Rust 时使用。所有权、错误处理、unsafe 的正确实践。
• rust-skillsComprehensive Rust coding guidelines with 265 rules across 26 categories. Use when writing, reviewing, or refa
• rust-standardsCoding standards for Rust projects. Apply when writing or reviewing Rust code. Covers error handling (`anyhow`
• rust-systemsRust patterns for CLI tools, backend services, and general application code. Use when working with Rust, Cargo
• rust-testingRust testing patterns including unit tests, integration tests, async testing, property-based testing, mocking,
• rustdesk-doctor诊断 RustDesk 连接问题。当用户说 RustDesk 连不上、无法远程、ID 不显示、注册失败时使用
• ruthless-cv-optimizerRewrite a CV/resume against a specific job description with zero fluff, zero fabrication, and ATS-safe output.
• ruview-advanced-sensingAdvanced RuView capabilities — RuvSense multistatic sensing (attention-weighted fusion, geometric diversity, p
• ruview-applicationsRun RuView sensing applications — presence/occupancy, breathing & heart rate, activity & fall detection, 17-ke
• ruview-cli-apiUse the RuView `wifi-densepose` CLI binary (incl. MAT scan/status/zones/survivors/alerts/export subcommands),
• ruview-configureConfigure RuView — ESP32 sdkconfig variants, NVS provisioning, WiFi channel / MAC filter overrides (ADR-060),
• ruview-hardware-setupESP32-S3 / ESP32-C6 firmware build, flash, WiFi provisioning, and serial monitoring for RuView CSI sensing nod
• ruview-mmwaveSet up and run RuView mmWave / FMCW radar sensing — ESP32-C6 + Seeed MR60BHA2 (60 GHz, heart rate / breathing
• ruview-model-trainingTrain RuView models — camera-free WiFlow pose (10 sensor signals, no labels), camera-supervised pose (MediaPip
• ruview-quickstartOnboarding and first-run for RuView (WiFi-DensePose) — Docker demo with simulated data, repo build, and the fa
• ruview-rvagentExplore and prototype rvAgent + RVF integration for RuView agentic flows. Use when working on cross-cog coordi
• ruview-verifyVerify a RuView build — full Rust workspace tests, the deterministic Python pipeline proof (SHA-256 Trust Kill
• ruvnet-agentdb-memory-patternsImplement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage,
• ruvnet-github-project-managementComprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and s
• ruvnet-onboardZero-to-sensing path picker for RuView (WiFi-DensePose) — pick docker-demo, repo-build, or live-esp32 and run
• ruvnet-reasoningbank-with-agentdbImplement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory trac
• ruvnet-v3-ddd-architectureDomain-Driven Design architecture for claude-flow v3. Implements modular, bounded context architecture with cl
• ruvnet-v3-mcp-optimizationMCP server optimization and transport layer enhancement for claude-flow v3. Implements connection pooling, loa
• ruvnet-verifyProve a RuView result is real — run the deterministic SHA-256 proof and the witness bundle (ADR-028), and lint
• ruvnet/ruflo🌊 The leading agent meta-harness for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous wor
• ruya-ai-diagnoseAnalyze Claude Code session bloat — shows token count, context usage %, and bloat breakdown. Use when the user
• ruzzyRuzzy is a coverage-guided Ruby fuzzer by Trail of Bits. Use for fuzzing pure Ruby code and Ruby C extensions.
• rvt-to-excelConvert RVT/RFA files to Excel databases. Extract BIM element data, properties, and quantities.
• rvt-to-ifcConvert RVT files to IFC format. Support IFC2x3, IFC4, IFC4.3 with customizable export settings.
• rwkv-architectureRNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parall
• rybkr-docs-writerWrite and revise clear, accurate, task-oriented documentation for software projects. Use when your agent needs
• rybkr-frontend-designCreate distinctive, production-grade frontend interfaces with genuine design intention. Use this skill when th
• rylai-pptCreate editable PowerPoint decks from a local JSON specification using Rylai's visual system, python-pptx, det
• rylaispirit-copywritingPlan, draft, and review persuasive copy for landing pages, product pages, ads, email, headlines, offers, calls
• rylaispirit-deep-researchConduct systematic source-backed research with scoped questions, triangulation, contradiction handling, and ci
• rylaispirit-docxCreate, inspect, edit, and verify Word DOCX files with python-docx, including Markdown conversion, text replac
• rylaispirit-frontend-designDesign, implement, and verify production frontend interfaces while respecting the existing repository, accessi
• rylaispirit-pdfCreate, inspect, extract, merge, split, rotate, and render PDF files with local open-source tools, including s
• rylaispirit-pptxCreate, inspect, extract, edit, render, and verify PowerPoint presentations with python-pptx and optional Libr
• rylaispirit-xlsxCreate, inspect, edit, and verify Excel XLSX workbooks with openpyxl, including CSV import, formulas, styling,
• sWrite a short, plain-English summary of the previous message, or with `all` of the whole conversation, issue,
• s-one68 plug-and-play, best-practice product management skills for AI agents: 30 Triple Diamond phase + 11 foundati
• s-releasePrepare and execute an addon release, including version bumping, changelog updates, git tagging, and validatio
• s-three68 plug-and-play, best-practice product management skills for AI agents: 30 Triple Diamond phase + 11 foundati
• s-two68 plug-and-play, best-practice product management skills for AI agents: 30 Triple Diamond phase + 11 foundati
• s3AWS S3 object storage for bucket management, object operations, and access control. Use when creating buckets,
• s3-estate-calibration-auditorAudit an estate of AWS S3 buckets for the one bucket that is genuinely publicly or cross-account exposed, with
• saas-demo-script-writerWrites demo scripts for sales, onboarding, and product marketing. Use when the user asks for demo talk tracks,
• saas-economics-efficiency-metricsEvaluate SaaS unit economics and capital efficiency. Use when deciding whether the business can scale efficien
• saas-funnelBuilds a 4–6 page SaaS trial/signup funnel. Converts visitors into free trial users or freemium signups, then
• saas-landingSingle-page SaaS landing with hero, features, social proof, pricing, and CTA. Respects the active DESIGN.md co
• saas-msa-reviewReference: review of SaaS subscription agreements under English contract law with attention to the terms that
• saas-payments
• saas-productivityUse when designing animations for business tools, project management, collaboration software, or productivity
• saas-revenue-growth-metricsCalculate SaaS revenue, retention, and growth metrics. Use when diagnosing momentum, churn, expansion, or prod
• saas-securityWiring your application to a third-party SaaS platform: verifying an inbound webhook against the vendor's own
• saas-security-postureAudit and harden your SaaS tool stack — enforce SSO, review OAuth grants, manage shadow IT, and secure admin a
• saas-valuation-compressionAnalyze SaaS company valuation compression between funding rounds. Use this skill whenever the user asks about
• saasifyConvert a regular/single-user app into a multi-tenant SaaS — add authentication, organizations/teams, role-bas
• saatavien-perintaSaatavan perinnän elinkaari Suomen oikeuden mukaan: vapaaehtoinen perintä ja hyvä perintätapa (perintälaki 513
• sabnzbdManage Usenet downloads with SABnzbd. Use when the user asks to "check SABnzbd", "list NZB queue", "add NZB",
• sacred-g-docUse when the task involves reading, creating, or editing `.docx` documents, especially when formatting or layo
• sacred-g-docxUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Trig
• sacred-g-internal-commsA set of resources to help me write all kinds of internal communications, using the formats that my company li
• sacred-g-mcp-builderGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with externa
• sacred-g-pdfUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text
• sacred-g-pptxUse this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creati
• sacred-g-skill-creatorGuide for creating effective skills. This skill should be used when users want to create a new skill (or updat
• sacred-g-theme-factoryToolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing page
• sacred-g-web-artifacts-builderSuite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web tech
• sacred-g-xlsxUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user
• safe-ai-dlcPlan and run programs using the SAFe x AI-DLC fusion. Use when turning an audit, epic, or initiative into Line
• safe-backend-21Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts befo
• safe-backend-33Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts befo
• safe-backend-45Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts befo
• safe-backend-57Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts befo
• safe-backend-9Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts befo
• safe-browserBuild local constrained-browser agents with a safe_browser tool that owns CDP, enforces a domain allowlist wit
• safe-calculatorA safe calculator for mathematical expressions
• safe-code-review-12Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts befo
• safe-code-review-24Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts befo
• safe-code-review-36Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts befo
• safe-code-review-48Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts befo
• safe-code-review-60Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts befo
• safe-database-10Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts befo
• safe-database-22Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts befo
• safe-database-34Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts befo
• safe-database-46Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts befo
• safe-database-58Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts befo
• safe-debugging-17Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts befo
• safe-debugging-29Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts befo
• safe-debugging-41Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts befo
• safe-debugging-5Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts befo
• safe-debugging-53Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts befo
• safe-deploymentDiscipline for shipping changes reversibly, decouple deploy (code reaches production) from release (users see
• safe-deployment-11Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts befo
• safe-deployment-23Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts befo
• safe-deployment-35Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts befo
• safe-deployment-47Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts befo
• safe-deployment-59Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts befo
• safe-documentation-15Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts befo
• safe-documentation-27Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts befo
• safe-documentation-3Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts befo
• safe-documentation-39Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts befo
• safe-documentation-51Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts befo
• safe-file-deletionEnforces explicit user permission before any file deletion. Activates when you're about to use rm, unlink, fs.
• safe-file-readerRead files from documents directory safely
• safe-first-taskA zero-risk first Cowork experience for discovering what Cowork does differently. Use when onboarding to Cowor
• safe-frontend-20Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts befo
• safe-frontend-32Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts befo
• safe-frontend-44Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts befo