Parcourir le registre

Toutes les entrées, par ordre alphabétique — 56 437 au total. Page 80 sur 226.

• exp-simd-vectorizationOptimizes hot-path scalar loops in .NET 8+ with cross-platform Vector128/Vector256/Vector512 SIMD intrinsics,
• exp-test-maintainabilityDetects duplicate boilerplate, copy-paste tests, and structural maintainability issues across .NET test suites
• expand-shellExpand a shell into a full implementation plan. Verifies Consumes against the current codebase, runs a fresh p
• expansion-kickoffKick off international expansion planning for a new country — gathers intake, runs EOR vs. entity framing, dra
• expansion-modelingAnalyze franchise expansion plans, model new market entry, score site selection candidates, map territory dens
• expansion-playbookUse when designing account-expansion mechanics — upsell vs cross-sell, expansion-trigger signals, NRR cognitio
• expansion-retentionWhen the user wants to reduce churn, build expansion revenue, automate customer success, or optimize net reven
• expansion-revenue-finderIdentifies upsell and cross-sell opportunities within existing customer accounts. Analyzes product usage, feat
• expansion-scanScans an account or a whole book for expansion signals — usage nearing plan limits, new teams appearing, white
• expansion-signalsIdentify upsell and cross-sell opportunities through usage patterns, growth signals, and account behavior anal
• expansion-strategyDesign and document a expansion strategy with structured process, quality checks, and system integration
• expansion-updateUpdate the status of an in-progress international expansion project — recalculates what is now unblocked, flag
• expansion-whitespace-deskmap whitespace across products business units and geographies with what is already entitled separated from wha
• expectRun adversarial browser tests against code changes. Use after any browser-facing change to verify it works and
• expense-categorizationClassify expenses by category, department, and tax deductibility from transaction data. Use when the user requ
• expense-optimizerFind recurring expenses and subscriptions to cut or reduce.
• expense-policyCreates corporate expense policies with spending limits, approval workflows, and reimbursement procedures. Use
• expense-report-builderAggregates expense receipts from email by time period, categorizes them by project or client, and returns a st
• expense-trackerCreates an expense tracking and categorization system in Notion with transaction records, category breakdowns,
• experience-and-design-systemAnti-AI-slop design system for distinctive, premium interfaces. Bold typography, dark-first #060610, fluid cla
• experience-mapMap the full ecosystem of touchpoints, channels, and relationships across a service. Use when the experience s
• experience-packTwo-layer experience system for any project: keep a per-project EXPERIENCE.md ledger (dated entries: what happ
• experience-plan機能・画面の実装着手前に「状態×見た目×周辺」を列挙する体験網羅チェックリスト。宣言外の実装を防ぐ関所として task-run/auto-task 等から使う。
• experimentRun an autonomous feature-engineering experiment loop on the statcast-gbm model (default). Analyzes residuals,
• experiment-dashboardCreate a self-hosted Python website to display simulation
• experiment-designUse when designing a new A/B test experiment is needed. Automated A/B test design, AI automatically executes h
• experiment-designerUse when planning product experiments, writing testable hypotheses, estimating sample size, prioritizing tests
• experiment-engineOtonom deney dongusu. Kod degisikligi yap, olc, karsilastir, kabul et veya geri al. Metrik bazli karar verme i
• experiment-executionUse when you need to execute A/B tests, analyze results, and generate complete reports. A/B test automated exe
• experiment-logRecord a model training run — log parameters, metrics, and artifact paths, then append a structured row to the
• experiment-loopAutonomous experimentation pattern for iterative code improvement. Describes the modify-commit-run-evaluate-ke
• experiment-orchestratorUse when designing or executing A/B test experiments. Experiment validation orchestrator dispatching experimen
• experiment-readout假设 + 指标 + 结果 + 解释 + 决策, 把 A/B 或产品实验转成行动建议
• experiment-results-interpreterInterpret A/B test results in plain language and get a ship/rollback/extend recommendation with a stakeholder
• experiment-suiteUse when the user has a research question and needs a complete experiment package — design document, runnable
• experiment-trackingAudit ML experiment tracking infrastructure for reproducibility gaps, parameter logging completeness, metric c
• experiment-tracking-reviewUse when reviewing ML training code to confirm a run could be reconstructed later -- hyperparameters, metrics,
• experiment-tracking-swanlabProvides guidance for experiment tracking with SwanLab. Use when you need open-source run tracking, local or s
• experimental-designDesign experiments and studies BEFORE data is collected — choosing a design, randomizing, blocking, and laying
• experimental-design-dsA/B testing, randomization, sample size calculation, confounding control, and causal inference for data scienc
• experimentation-analyticsHow to read experiment results without fooling yourself. Confidence intervals, p-values, multiple testing, seq
• experimentation-and-ab-testingA/B testing and experimentation for social media content — evidence over opinion, at honest organic-scale rigo
• experimentation-measurementHow to validate sales-page decisions with real experiments - traffic floor, sample-size/MDE procedure, peeking
• experimentation-platform-orchestratorA platform decision framework for experimentation. When to use Statsig vs PostHog vs GrowthBook vs Optimizely
• expert-interviewUse when extracting first-party expertise from a subject-matter expert before writing content. Produces a know
• expert-panelAssemble 2-3 complementary experts to collaboratively analyze anything. Experts work together to explore topic
• expert-povExtract a founder's or expert's point of view — core beliefs, contrarian takes, origin stories, taste — and sy
• expert-secretsApply Russell Brunson's Expert Secrets framework to build a mass movement around expertise — create a charisma
• expertise-exchangeTeam expertise billboard via `adept exchange`: ask teammates for expertise and stack responses. Apply when the
• expertsAssemble a panel of experts to assess a problem from multiple professional perspectives, surface agreement and
• explainQuick code explanation - understand specific files, functions, or concepts
• explain-as-you-goUse when the user is learning and wants to understand the code, not just receive it — they're new to the langu
• explain-branch-changesExplain the current git branch's changes in plain product language for a non-technical audience — no file path
• explain-codeExplains code with visual diagrams and analogies. Use when explaining how code works, walking through a codeba
• explain-codebaseOnboard to an unfamiliar codebase by mapping its architecture, entry points, and data flow. Use when starting
• explain-conceptUse when a concept needs making clear rather than practising: build the intuition, explain why it exists and w
• explain-errorExplain a stack trace or error message and suggest concrete fixes.
• explain-for-grandmaRe-explain the previous response in plain, beginner-friendly language — decode the jargon, buzzwords, and tech
• explain-lptsComprehensive reference for the LPTS pipeline — LogicalPlan to AST to CTE List to SQL string. Covers AST node
• explain-new-projectUse when the user adds a project to the workspace, opens an unfamiliar repo, asks "what is this project", "exp
• explain-plainlyDefault to explaining technical work in plain language for a non-technical audience, using an existing project
• explain-prExplain a GitHub Pull Request (PR) or GitLab Merge Request (MR) to the user in plain, easy-to-understand langu
• explain-thisExplain whatever the user is pointing at right now in plain language: a pending question, a piece of code, an
• explain-this-prTakes a GitHub PR URL or the current branch and writes a plain-English explanation of what it does and why, th
• explain-visuallyCreates a responsive HTML explainer with source-grounded copy, teaching diagrams, and browser-verified layout.
• explainabilityProduce or audit the interpretability/explainability analysis of a medical-imaging model — Grad-CAM / Grad-CAM
• explainerCreate explainer videos with narration and AI-generated visuals. Triggers on: "解说视频", "explainer video", "expl
• explainer-videoCreate finished explainer videos from a topic, script, outline, voiceover, product logic, data, technical conc
• explainer-writerExplain complex topics simply — analogies, Feynman technique breakdowns, and layered explanations for any audi
• explaining-codeExplains code with visual diagrams and analogies. Use when explaining how code works, teaching about a codebas
• explaining-codebasesUse when creating an interactive explainer about a codebase, repository, or source files. Handles onboarding o
• explanation-docsExplanation documentation patterns for understanding-oriented content - conceptual guides that explain why thi
• explanation-guidanceSurfaces Han's shared standard for explaining technical work to a reader who will not implement it into the ca
• explanation-tracesQuery and display structured decision traces from routing, agent selection, and skill execution.
• explicit-checkerScans lyrics for explicit content and verifies that explicit flags match actual content. Use before Suno gener
• explicit-identityAI software team for Claude Code - 138 agents, 295 skills, 73 hooks. Self-learning, multi-agent swarm, autonom
• exploit-development-payload-engineeringProof-of-concept development, payload crafting, shellcode analysis, and exploitation technique research for au
• exploit-file-downloadArbitrary file download vulnerability detection and exploitation using path traversal techniques, bypass metho
• exploit-lfi本地文件包含 (LFI) 漏洞检测和利用工具。使用 curl、ffuf 等工具测试 LFI 漏洞，支持路径遍历、PHP 伪协议利用、日志投毒 RCE、敏感文件读取。当用户需要检测 LFI 漏洞、利用文件包含漏洞读取服务器
• exploit-sqliSQL injection detection and exploitation using sqlmap, manual techniques, and custom payloads. Use this skill
• exploit-xssCross-site scripting (XSS) vulnerability detection and exploitation. Supports reflected XSS, stored XSS, DOM-b
• exploitability-analyzerAnalyze detected vulnerabilities to assess realistic exploitability by examining control flow, input sources,
• exploiting-active-directory-with-bloodhoundBloodHound is a graph-based Active Directory reconnaissance tool that
• explorationUse when exploring an unfamiliar codebase -- architecture analysis, pattern detection, dependency mapping, rap
• exploratory-autoresearchUse when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbi
• exploratory-data-analysisPerform comprehensive exploratory data analysis on scientific data files across 200+ file formats. This skill
• exploratory-testExecute multi-level exploratory testing of the app covering basic functionality, complex operations, adversari
• exploratory-testingDesign and execute structured exploratory testing sessions. Covers Session-Based Test Management (SBTM), chart
• exploreSearch the marketplace, analyze competition, discover gaps, and find inspiration. Use when: 'explore', 'search
• explore-before-actingAutocreates skill.md files from Claude Code logs dataset
• explore-before-refactorAutocreates skill.md files from Claude Code logs dataset
• explore-codebaseNavigate and understand codebase structure using the knowledge graph
• explore-conceptPROVISIONAL / EXPERIMENTAL — committed for the record, not a blessed workflow (its first run produced the shel
• explore-dataProfile and explore a dataset to understand its shape, quality, and patterns. Use when encountering a new tabl
• explore-divergent-conceptsGenerates genuinely different design directions in parallel, documents the exploration, and converges on one w
• explore-homecoreMap a Homecore capability to reviewed source, tests, ADRs, and limitations.
• explore-orgUse whenever the user asks what's in their SquaredUp tenant, what integrations are connected, what data is ava
• explore-structure-firstAutocreates skill.md files from Claude Code logs dataset
• explorerQuickly search and navigate the codebase - Use when you need to quickly find files, search for patterns, or lo
• exploring-an-ideaUse at the very start of a new product idea — before a PRD, PCD, repo, or name exists, and any time someone sa
• exploring-approachesUse when starting a new project or significant feature from a vague idea — before clarifying details or planni
• exploring-codebasesFirst-encounter codebase orientation. Chains tree-sitting (structural inventory) and featuring (feature synthe
• exploring-dataExploratory data analysis. Use when users upload .csv/.xlsx/.json/.parquet files or request "explore data", "a
• explorium-ai-browser-extension-builderBrowser extension builder skill for Claude Code and Codex: scaffolds a local, unpacked Chrome extension that r
• expo-api-routesGuidelines for creating API routes in Expo Router with EAS Hosting
• expo-architectScaffold a production-ready Expo React Native app with working screens, navigation, and optional Clerk auth. G
• expo-brownfieldIntegrate Expo and React Native into an existing native iOS or Android app. Use when the user mentions brownfi
• expo-cicd-workflowsHelps understand and write EAS workflow YAML files for Expo projects. Use this skill when the user asks about
• expo-deploymentDeploying Expo apps to iOS App Store, Android Play Store, web hosting, and API routes
• expo-dev-clientBuild and distribute Expo development clients locally or via TestFlight
• expo-moduleGuide for creating and writing Expo native modules and views using the Expo Modules API (Swift, Kotlin, TypeSc
• expo-native-uiBuild beautiful native iOS/Android apps with Expo Router. Covers route structure, native tabs, animations, blu
• expo-observeUse for anything related to EAS Observe — adding `expo-observe` to an Expo project (AppMetricsRoot/ObserveRoot
• expo-sdkThis skill should be used when users need to work with Expo SDK and Expo Router for building React Native appl
• expo-skillsOfficial Expo skills for working with Expo projects and Expo Application Services (EAS). Fine-tuned for Opus m
• expo-tailwind-setupSet up Tailwind CSS v4 in Expo with react-native-css and NativeWind v5 for universal styling
• expo-uiThis skill should be used when users need to work with Expo UI (@expo/ui) for integrating SwiftUI components i
• expo-ui-jetpack-compose`@expo/ui/jetpack-compose` package lets you use Jetpack Compose Views and modifiers in your app.
• expo-ui-swiftui`@expo/ui/swift-ui` package lets you use SwiftUI Views and modifiers in your app.
• expo/skillsA collection of AI agent skills for working with Expo projects and Expo Application Services
• exportExport knowledge base content to PDF, Markdown, or HTML files saved under _data/exports/. Use when a user want
• export-agentConverts agent definitions between frameworks — exports to Claude Code, OpenAI, CrewAI, Lyzr, and GitHub Model
• export-html-reportGenerate a self-contained, presentation-ready HTML report from any completed analysis or conversation output.
• export-open-issuesAudit and export open issues from any project tracker with summary analysis and vault archival
• export-pipelineProduction export from Blender to FBX, GLTF, OBJ, USD, and Alembic with scale, pivot, rotation, normals, mater
• export-review-packReads a transaction or order description and produces a DRAFT export review pack — a parties-to-screen list an
• export-session-as-markdownUse when the user wants to export a Claude Code session transcript as a readable Markdown file — converts the
• exposure-coachUse this skill to combine market breadth, uptrend participation, and account drawdown state into one summarize
• exposure-risk-quantificationFAIR-aligned exposure quantification: turns a pile of recon findings into a defensible 0-100 + A-F org risk sc
• expressProduction-ready AI coding skills for APIs. Installable skills for Claude Code, Cursor, Codex CLI, Gemini CLI,
• express-backendSkill de backend para Express.js com TypeScript. Contém arquitetura em camadas (Controllers, Services, Reposit
• express-backend-devAgente Dev Backend Sênior para Express. Responsável por rotas, controladores, services, middlewares customizad
• express-qaSkill de Quality Assurance para Express. Checklist de testes de rotas com Supertest, validação de middlewares
• express-qa-engineerAgente QA Engineer para Express. Responsável por validar a qualidade das rotas, rodar testes automatizados (Su
• express-rest-api-generatorGenerates production-ready Express.js REST API route handlers from natural language descriptions, including Zo
• expressiveVibrant, personality-driven design with bold colors, playful graphics, and dynamic layouts that balance creati
• extendIWE extensibility catalog: what can be customized, which extension points exist, which parameters are availabl
• extended-no-toolsExtended dialect skill that uses Bash but forgets allowed-tools. Use when running shell commands to deploy.
• extension-analyzeAudit Chrome extensions for security issues, best practice violations, performance problems, and CWS complianc
• extension-assetsGenerate and manage all Chrome extension assets: icons (16–128px), CWS listing images, promotional tiles, and
• extension-backendBuild backend APIs for Chrome extensions. NestJS + MongoDB (Mongoose) recommended stack. Auth, webhooks, licen
• extension-createAuto-scaffold Chrome extensions with WXT or Plasmo. Ask user for name/features, scaffold, configure entrypoint
• extension-devDetect Chrome extension framework/stack, find proper docs, implement features, and debug across service worker
• extension-manifestGenerate and validate manifest.json with optimal permissions for Chrome MV3 extensions. Analyzes code to deter
• extension-migrationMigrate Chrome extensions from MV2 to MV3. Service workers, declarativeNetRequest, API replacements. Use when:
• extension-paymentIntegrate payment gateways into Chrome extensions. Stripe, Paddle, Lemon Squeezy, Polar, PayPal, and more. Lic
• extension-pointsGuide for MSBuild extensibility: CustomBefore/CustomAfter hooks, wildcard imports with alphabetic ordering, im
• extension-publishPrepare, submit, and optimize Chrome Web Store listings. Covers workflow, checklist, rejection reasons, listin
• extension-reviewScan extension source code for Chrome Web Store rejection risks. Generates report with issues, root causes, an
• extension-testSet up and run unit, integration, and E2E tests for Chrome extensions. Covers Jest mocks for chrome.* APIs and
• extension-uiBuild polished Chrome extension UIs (popup/sidepanel/options). Analyze existing UI, suggest improvements, set
• extensionsUse when you need the Codex Copilot equivalent of Claude Copilot /extensions: inspect knowledge repositories,
• external-browser-driverControl a user-paired external browser through a Chrome extension, explicit typed targets, and semantic operat
• external-error-preserving-refresh-mergeMerge fresh refresh diagnostics with externally owned errors so one subsystem reload does not erase valid adja
• external-lib-flowWorkflow for onboarding an external private library so AI can use it without source access.
• external-linkSynthetic audit fixture for external-link.
• external-pr-review외부 기여자 PR 검토 절차를 적용한다. PR 정보 수집, mydocs/pr/pr_{N}_review.md 작성, 검증, pr_{N}_report.md 작성, 처리 완료 시 archives/ 이동을
• external-resource-contextRecords where resources outside the repository live (design source, design system, API schema, IaC source, sec
• external-skillSkill installed via a Claude Code marketplace external_plugin
• external-skill-acquisitionUse when no installed skill covers the task domain and external acquisition is needed. Provides a 3-tier decis
• external-skill-fixture-builderTurn external skill, rule, plugin, MCP, task-memory, and multi-agent workspace patterns into safe fixture cove
• external-skills-catalogCurated catalog of 60+ external Claude Code skills across 8 categories with quality rankings, install instruct
• external-tool-coordinationCoordinate external AI tool integration (OpenAI Codex, Google Gemini) for cross-model adversarial review and d
• externe-meldung-offenlegungExterne Meldung und Offenlegung nach §§ 7, 19, 28, 32 HinSchG – Wahlrecht zwischen interner und externer Meldu
• extlinkLinks build docs across the workspace. Use when the user asks about cross-project build references or shared s
• extra-fieldsA skill with extra frontmatter fields.
• extra-keyEvaluate reusable sample skills when checking a complete rubric workflow.
• extractExtract and consolidate reusable components, design tokens, and patterns into your design system. Identifies o
• extract-adrsExtract architecture decision records from existing meta documents
• extract-approachThe recorder — after every non-trivial solved problem, write ONE learnings note capturing the approach, the ju
• extract-brand-paletteRecursively Self-Improving Module — persistent memory + structured improvement loop for Claude Code
• extract-claude-code-promptExtract Claude Code system prompt from its compiled binary or JS bundle into a structured template file. Produ
• extract-codex-promptExtract Codex system prompt from its compiled binary or JS bundle into a structured template file. Produces a
• extract-componentThis skill should be used when the user asks to "extract skill", "extract command", "extract agent", "extract
• extract-conventionsObserve a scope's dominant code conventions and write a project-tier conventions.md rule overriding universal
• extract-designExtract a complete design system — colors, typography, spacing, components, shadows, and W3C design tokens — f
• extract-design-mdExtract Google Stitch design specifications into DESIGN.md format. Creates a structured design document from S
• extract-design-systemReverse-engineers design tokens (colors, typography, spacing, border radius, shadows) from any public website
• extract-diagramsExtract CeTZ diagrams to SVG from Typst files. For TikZ extraction, configure at project level.
• extract-documentsExtracts structured data from batches of invoices, receipts, statements, and similar documents (PDF, photo, sc
• extract-errorsUse when adding new error messages to React, or seeing "unknown error code" warnings.
• extract-narrative-methodsBuild and run an auditable multi-model workflow that extracts reusable decision, negotiation, and management m
• extract-openapi-from-codeUse when extracting or generating an OpenAPI spec from existing API code. Triggers on "extract OpenAPI", "code
• extract-patternUse when the user wants to create templates, extract reusable patterns, document solutions, or build a pattern
• extract-requirements-from-mockExtract requirements document from HTML mock iteration
• extract-source-sampleGiven the path to a finished content-goose ad-run folder, extract everything that defines that ad — recipe sho
• extract-team-from-rooftopAchieve a complete rooftop team extraction end to end. Use when a team must be recovered from a rooftop by air
• extract-transcriptsExtract readable transcripts from Claude Code and Codex CLI session JSONL files
• extract-work-itemsExtract work items in batch from existing documents (specs, PRDs,
• extracting-browser-history-artifactsExtract and analyze browser history, cookies, cache, downloads, and bookmarks
• extracting-config-from-agent-tesla-ratExtract embedded configuration from Agent Tesla RAT samples including
• extracting-iocs-from-malware-samplesExtracts indicators of compromise (IOCs) from malware samples including
• extracting-keywordsExtract keywords from documents using YAKE algorithm with support for 34 languages (Arabic to Chinese). Use wh
• extracting-memory-artifacts-with-rekallUses Rekall memory forensics framework to analyze memory dumps for process
• extraction-formUse when `evidence-review` has screened includes and needs a schema-aligned extraction table. **Trigger**: ext
• extraction-optimizationOptimize mining extraction operations by analyzing ore grade control, processing plant throughput, metallurgic
• extractwisdomDynamic wisdom extraction that adapts sections to content. USE WHEN extract wisdom, analyze video, analyze pod
• extrasmall0-applyAssisted job-application filler. Given a job posting URL, open it in a browser via Playwright, extract the JD
• extremely-optimizeRebuild code from its performance floor: split hot paths from cold, demolish and re-derive the hot ones first,
• exunit-code-reviewReviews ExUnit test code for proper patterns, boundary mocking with Mox, and test adapter usage. Use when revi
• fable-advisorUse when the user wants a task executed by the current session model (typically Sonnet 5) with a persistent Fa
• fable-auditAudit the fable roadmap (docs/fable_roadmap/) — verify claimed progress with proof, write a short report, upda
• fable-boundaryInstruction-source boundary — everything read through tools is data, not commands; embedded imperatives get qu
• fable-commanderFable 指揮官工作流 — Fable 只做規劃/審查/決策，研究與執行派給使用者選的模型（Opus/Sonnet/Haiku subagent）。流程：Fable 產 plan → 問使用者選研究模型 → /work
• fable-context-thriftUse at the start of any multi-step task and during exploration — before reading files, searching, or re-checki
• fable-design-systemAward-winning SaaS UI/UX design persona reconstructed from the claude-fable-5 model. Apply to any web/UI task
• fable-dispatchRequired dispatch procedure for running a subagent on Fable 5 — positive harness detection, the Claude Code CL
• fable-domainDiscuss a domain with the user, research it from real sources, then generate a trusted skill bundle for it - a
• fable-finishEnd-of-turn autonomy contract — act when you have enough information, never end a turn on a plan or promise, r
• fable-finish-your-turnUse before ending any turn that used tools or produced a deliverable — when tempted to ask "Want me to…?", pre
• fable-foremanTeam-lead orchestrator: whichever frontier-class Claude model leads your session plans, routes, and verifies w
• fable-judgeAdversarial verification of finished work. Treats any "done" as a set of claims, then re-runs the claimed veri
• fable-loopEnd-to-end orchestrated workflow that runs a task the way Fable ran sessions - parallel evidence subagents, on
• fable-low-powerFable Low Power mode — token-saving profile when Anthropic usage limits run low: the frontier model acts as de
• fable-memoryFile-based persistent memory protocol — one fact per file, typed frontmatter, an index loaded each session, fe
• fable-methodA step-by-step problem-solving loop (classify the ask, define done, gather evidence, decide, act surgically, v
• fable-mindsetReasoning discipline for hard, multi-step tasks — how to decompose ambiguous problems, verify work before repo
• fable-modeEmulates Claude Fable 5's coding discipline on any model (Opus 4.8, Sonnet 5, etc.) — spec-first planning, a s
• fable-native-codeUse when writing or editing code in an existing codebase — before adding comments, docstrings, try/catch block
• fable-new-issueUse when the user wants a GitHub issue created by a Fable 5 subagent. Spins up a read-only subagent running on
• fable-new-issue-loopUse when the user asks to have a Fable 5 subagent draft and file a GitHub issue, then autonomously drive it al
• fable-orchestrateUse when the user wants a task decomposed and driven by a Fable 5 orchestrator delegating implementation to So
• fable-orchestrationDelegation policy for a multi-model agent stack where the main loop runs on a scarce top-tier model (e.g. Clau
• fable-outcome-firstUse when writing any user-facing reply — answers, status updates, summaries, or final reports — especially aft
• fable-protocolAn advanced, autonomous AI agent skill designed to execute complex, multi-step, and long-horizon tasks with hi
• fable-prove-itUse before claiming anything works, is fixed, is done, or passes; before status updates on changes you haven't
• fable-reconExploration-before-action contract — read before writing, scale recon to blast radius, stop exploring when you
• fable-ruki-agentyФейбл руки-агенты — ручной режим оркестрации, где Fable не пишет код, а пишет спеки в тела GH issues и раздаёт
• fable-scope-disciplineUse when implementing any change in existing code — when tempted to clean up nearby code, add unrequested vali
• fable-validateUse when the user wants a GitHub issue validated by a Fable 5 subagent. Spins up a read-only subagent running
• fable-validate-fableplanUse when the user asks to validate a GitHub issue with Fable 5 and always plan it with Fable 5, stopping once
• fable-validate-fableplan-loopUse when the user asks to validate a GitHub issue with Fable 5, always plan it with Fable 5, and autonomously
• fable-validate-loopUse when the user asks to validate a GitHub issue with Fable 5 and then autonomously drive it to a reviewed PR
• fable-verifyVerification contract — done means executed and observed, not written and plausible. Use before declaring any
• fable-voiceCommunication contract for agent output — lead with the outcome, readable over concise, prose for simple answe
• fableplanUse when the user wants a task planned by a Fable 5 planning subagent before building it. Spins up a Plan suba
• fableplan-loopUse when the user wants a GitHub issue planned by Fable 5 and then autonomously driven to a reviewed PR in one
• fableplan-work-on-issueUse when the user wants a GitHub issue planned by Fable 5 and then implemented in one shot, without validation
• fabric240+ specialized prompt patterns for content analysis, extraction, and transformation — run patterns, sync fro
• fabric-cliExpert guidance for using the Fabric CLI (`fab`) to fully interact with Fabric workspaces, items, and configur
• fabric-data-agentCreate, configure, and manage Microsoft Fabric Data Agents that enable natural language Q&A over lakehouses, w
• fabric-data-agent-perf-remediateDiagnose and resolve Microsoft Fabric Data Agent performance issues including slow query generation, capacity
• fabric-data-agent-remediateDiagnose and resolve Microsoft Fabric Data Agent issues including tenant settings, data source configuration,
• fabric-data-factory-perf-remediateDiagnose and resolve Microsoft Fabric Data Factory pipeline performance issues. Use when pipelines are slow, c
• fabric-dataflows-perf-remediationDiagnose and resolve Microsoft Fabric Dataflow Gen2 performance issues including slow refresh times, Fast Copy
• fabric-delta-spark-perfTroubleshoot and optimize Delta Lake and Apache Spark performance in Microsoft Fabric. Use when diagnosing slo
• fabric-iqGuide for working with Microsoft Fabric IQ (preview), the semantic intelligence workload for unified data and
• fabric-lakehouse-access-controlTroubleshoot Microsoft Fabric Lakehouse access control issues including OneLake security roles, SQL analytics
• fabric-lakehouse-perf-remediateDiagnose and resolve Microsoft Fabric Lakehouse performance issues including slow Spark queries, small file pr
• fabric-lakehouse-views-perf-remediateTroubleshoot Microsoft Fabric materialized lake views (MLV) performance issues including slow refresh, increme