Parcourir le registre

Toutes les entrées, par ordre alphabétique — 56 437 au total. Page 143 sur 226.

• linkedin-post-engagersScrape LinkedIn post engagers (commenters + reactors) from any profile or set of profiles, deduplicate them,
• linkedin-post-generatorGenerate engaging LinkedIn posts with best practices, visual identity, and vault integration. Triggers: "linke
• linkedin-post-generator-operator-povGenerates publish-ready LinkedIn posts for B2B SaaS marketing leaders writing from an operator point of view:
• linkedin-post-managerManages a queue of LinkedIn posts and automates the posting process using browser automation.
• linkedin-post-maxUse when the user wants to draft or refine a LinkedIn post, develop a vague idea into a post, brainstorm post
• linkedin-post-optimizerProfessional narrative style with line breaks, hashtag strategy, and hooks in first 2 lines to avoid truncatio
• linkedin-post-styleWrites LinkedIn posts in a direct, analytical, dry-humored technical voice with visual companion guidance. Tri
• linkedin-post-writerUse when the user asks to write, draft, or rewrite a LinkedIn post, turn notes or an article into a LinkedIn p
• linkedin-postsDraft and refine LinkedIn posts. Use when the user wants to write, improve, or iterate on LinkedIn content.
• linkedin-proLinkedIn 职业社交公开数据查询 skill，通过 MaxHub API 查询公司、职位、人员资料、员工列表、帖子、评论、搜索和关联数据。适合 B2B 市场研究、招聘线索、公司画像、行业情报和职业内容分析。默认 r
• linkedin-profile-fit-assessmentScore a LinkedIn profile against a role on 5 fit dimensions and decide Reach out / Skip / Needs human review i
• linkedin-profile-optimizerAudit and rewrite your LinkedIn profile to attract the right people. Scores each section, rewrites headline an
• linkedin-profile-perfectorAudit and rewrite a LinkedIn profile into a recruiter-grade report from the user's material (PDF, resume, webs
• linkedin-profile-thheadline + summary + experience | สำหรับ นักศึกษา. Triggers when user says (Thai/EN): 'linkedin profile', 'โปร
• linkedin-readerRead LinkedIn for financial research using opencli (read-only). Use this skill whenever the user wants to read
• linkedin-roastHilarious LinkedIn profile roasting skill that delivers savage but friendly comedy burns based on someone's pr
• linkedin-url-lookupResolve LinkedIn profile URLs from name + company with strict identity validation to avoid false positives.
• linkedin-visibilityMethodology for algorithm-aware LinkedIn operation by a small expert account: topic-relevance-first content st
• linkedin-webhooksReceive and verify LinkedIn webhooks. Use when setting up LinkedIn webhook handlers, completing the challengeC
• linkedin-writerRepurpose YouTube videos, blog articles, guides, or raw insights into high-performing LinkedIn posts that matc
• linkedin-writer-vaultVault-aware LinkedIn writer. Same step-by-step LinkedIn post process as linkedin-writer, but ICP, voice, and o
• LinkedInLearning/hands-on-ai-building-ai-agents-with-model-context-protocol-mcp-and-agent2agent-a2a-6055298this repo is for linkedin learning course: Hands-On AI: Building AI Agents with Model Context Protocol (MCP) a
• linkerd-patternsImplement Linkerd service mesh patterns for lightweight, security-focused service mesh deployments. Use when s
• linkly-quote-cardsLinkly 金句卡+极简 zine 风海报引擎(光形体自研)。当用户要把金句/一句话/主题/文章立意/情绪/参考照片变成"旧纸大留白+单一高饱和色锚+印刷质感"的竖版卡片或海报时使用。触发词:金句卡、出金句卡、金句卡
• linmas-cloud-hardening-architectCloud hardening architecture skill for IAM, network segmentation, service boundaries, workload protection, and
• linmas-controls-compliance-reviewerControls and compliance review skill for evidence review, control mapping, audit preparation, and framework ga
• linmas-detection-rules-engineerDetection rules engineering skill for SIEM logic, alert design, telemetry mapping, tuning, and false-positive
• linmas-exploit-validation-specialistExploit validation skill for authorized environments, attack-surface review, and bounded proof-of-impact workf
• linmas-incident-triage-leadIncident triage skill for security-event classification, containment planning, evidence preservation, and resp
• linmas-secure-code-reviewerSecure code review skill for application risk analysis, threat modeling, scanner tuning, and developer-focused
• linmas-secure-systems-architectSecure systems architecture skill for trust zones, identity patterns, control placement, and cross-system desi
• linmas-security-domain-routerSecurity domain routing skill for choosing the right specialist workflow across secure coding, architecture, r
• linmas-security-operations-leadSecurity operations skill for monitoring, escalation readiness, operational hardening, and day-to-day defensiv
• linmas-smart-contract-reviewerSmart contract review skill for protocol risk analysis, invariant review, and Web3 design verification in auth
• linmas-threat-research-analystThreat research skill for IOC analysis, adversary tracking, campaign reporting, and intelligence-to-detection
• linode-apiLinode API Documentation
• linode-cliLinode CLI Documentation
• lintRun linting and formatting checks. Use when user asks to "run linter", "/lint", "check linting", "fix lint err
• lint-and-fixDetect available linters and formatters in the project, run them with auto-fix flags, report results, manually
• lint-fixFix linting errors systematically across the codebase
• lint-markdown-filesLint markdown files for style and link integrity.
• lint-repoCheck that this skill package is internally consistent and report actionable failures.
• lint-tasksReview coder-eval task YAML that already exists — find criteria that cannot fail, prompts that give away the a
• lint-triageRun RTL lint / methodology checks and triage each violation into a real fix vs a justified, documented waiver.
• lint-wikiAudit all .claude/context/ docs against the actual codebase. Finds stale entries, missing entries, and gaps. O
• lintbaitA tiny practice skill that summarizes shell command output into one line.
• linter-docsDeep linter reference for authoring or debugging a vigiles enforce() rule — plugin tables, AST selectors, type
• linus-levelSet a 1.0-10.0 engineering working-mode dial - tunes agency, collaboration, assumption budget, decision owners
• linuss-lawApply Linus's Law when discussing code review practices, open source contributions, bug finding strategies, se
• linuxProduction-ready AI coding skills for APIs. Installable skills for Claude Code, Cursor, Codex CLI, Gemini CLI,
• linux-agent-skillsRouter and index for the Linux/DevOps agent skill library. Load this skill first to find which specialized ski
• linux-bash-scriptingDefensive Bash scripting for Linux: safe foundations, argument parsing, production patterns, ShellCheck compli
• linux-deployDeploy a service on a Linux host.
• linux-opsUse for the high-leverage Linux ops gotchas - find/xargs at scale, signals and pkill, ulimit/systemd limits, O
• liongardEvery Liongard endpoint, plus an offline copy of your whole MSP estate you can join, search, and drift-check f
• lipnardoGenerate AI avatar talking-head videos using HeyGen API. Single videos, multi-scene studio compositions, batch
• liquid-glassImplement Liquid Glass design using .glassEffect() API for iOS/macOS 26+. Covers SwiftUI, AppKit, UIKit, and W
• liquid-glass-designiOS 26 Liquid Glass design system — dynamic glass material with blur, reflection, and interactive morphing for
• liquid-glass-skillDeep knowledge of Apple's Liquid Glass design system (iOS 26+/macOS 26+): .glassEffect() modifier, .buttonStyl
• liquid-rocket-engine-engineerExpert-level Liquid Rocket Engine Engineer specializing in staged combustion and gas-generator cycle design, t
• liquidity-managementPlan and manage cash flow to ensure adequate liquidity while minimizing opportunity cost of excess cash. Use w
• listWhen the user wants to design, optimize, or audit list layouts for content display. Also use when the user men
• list-builderProspecting skill for Claude Code and Codex: build a targeted list of B2B prospects or businesses from a natur
• list-draftsList recent content drafts. Wraps `postall-agent list`. Activates when the user wish is read-only — "what draf
• list-growth-designerUse when the user asks to "grow my email list", "design a lead magnet / signup incentive", "set up double opt-
• list-hygiene-monitorUse when the user asks to "watch my list health over time", "flag decaying / unengaged subscribers on a schedu
• list-ideaslist all ideas in the ideas folder
• list-membersDisplays the roster of architecture team members with their specialties and expertise areas. Use when the user
• list-pageBespoke per-module list page pattern using DiceUI DataTable + useDataTable + nuqs URL state + RelativeTimeCard
• list-segment-builderUse when the user asks to "build email segments from my list", "make engaged / lapsed / RFM segments", "set up
• list-skillsList all installed skills and show which plugin each belongs to
• list-subsList all active skill-bus subscriptions across global and project scopes, showing merge status, insert-level a
• list-work-itemsList and filter work items from the configured work directory.
• listenhubListenHub CLI skills router. Routes to the correct skill based on user intent. Triggers on: "make a podcast",
• listenhub-cliListenHub CLI skills router. Routes to the correct skill based on user intent. Triggers on: "make a podcast",
• listenhub-tts使用 ListenHub API 将文本转换为语音（TTS）。支持三种模式：快速合成（/v1/tts）、 多角色脚本（/v1/speech）、长文本流式合成（/v1/flow-speech/episodes）。 音色未指
• listenhub-voiceEnd-to-end audio generation with ListenHub-Voice-1.0 (text / image → audio). Supports sound effects, multi-voi
• listicle-and-roundupThe list/roundup content type — design honestly-curated, scannable, AI-citable listicles ("7 ways to X", "best
• listing-auditAudit existing product listings for SEO improvements, missing data, and platform compliance. Trigger with "aud
• listing-expiry-trackerFinds every active listing agreement referenced in email and surfaces those approaching expiry — including the
• listing-scrapeScrape a rental or real-estate listing page with lightpanda and turn it into facts on a prospect file. Use whe
• listing-searchUse when the user wants to find for-sale (or sold) homes matching criteria in an area — location, price range,
• lists-gridsUse when animating lists, grids, tables, or collections of items to create smooth ordering, filtering, and loa
• listtoolsRuns the project test suite and reports failures. Use when the user asks to run tests or check the current tes
• lit文献调研入库：检索论文、产出 notes/papers/<citekey>.md 结构化笔记并追加 lit/literature-log.md 索引。引用必须来自真实检索结果并附 DOI 或 arXiv ID。查文献、读
• lit-dedupStage 5 of the lit review pipeline: merge and deduplicate papers from all prior stages (Undermind, Scholar Lab
• lit-review根據使用者的文章或論文草稿，自動用 Semantic Scholar、Crossref、arXiv API 搜尋相關文獻，並查核既有引用(文獻是否真實存在、書目欄位是否正確、內容是否支持文中論點)，也能從主題出發寫出「每
• lit-review-orchestratorMaster controller for the lit-review pipeline, driven by a document. Give it a .tex or .docx file describing a
• lit-screenStage 6 of the lit review pipeline: screen paper abstracts against the research prompt. The orchestrator's age
• lit-statusQuery the Obsidian literature library: counts by status, tags, projects; orphans; gaps; reading queue. Use /li
• lit-syncSync research references from .bib files to Zotero library + Obsidian literature notes. Extract cross-cutting
• lite-cge-holy-trifectaBuild a quick Holy Trifecta for a YouTube video — title, thumbnail concept, and intro — using a packaging meth
• lite-constraintsGenerates synthesis-constraints.json for the Diffmode growth-tactics pipeline by reasoning in-context over the
• liteparseLocal document and PDF parsing that returns spatial text with bounding boxes. Use for extracting text from PDF
• literate-guideCreate a narrative guide to a codebase or feature in the style of Knuth's Literate Programming — code and pros
• literature-engineALWAYS activate when the user needs to find, organize, review, or synthesize academic literature. Uses academi
• literature-engineerMulti-route literature expansion + metadata normalization for evidence-first surveys. **Trigger**: evidence co
• literature-researchUse when the user wants to find related work, survey a research area, identify literature gaps, or discover op
• literature-reviewSystematic literature review workflow: scope, search (arXiv, Semantic Scholar, Google Scholar), screen, extrac
• literature-review-agentStep 3 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the literature search strategy from outline.
• literature-review-plannerStructured literature review planning with systematic methodology, source evaluation, and synthesis frameworks
• literature-review-thliterature review structured + gap | สำหรับ นักศึกษา. Triggers when user says (Thai/EN): 'literature review',
• literature-reviewerLiterature review agent - systematic evidence gathering and appraisal for drug-target-disease hypotheses, with
• literature-searchUse when a loop needs scholarly literature — paper discovery, novelty checks, full-text snippet search, citati
• literature-searcherSearch CrossRef, OpenAlex, PubMed, Semantic Scholar, and optional Scopus; deduplicate results, download open-a
• literature-surveyUse when the user wants a structured, saturating literature survey on a question — not a one-shot summary, but
• literature-trackerTracks every paper, study, dataset, and source that has been shared, recommended, or discussed across research
• lithic-webhooksReceive and verify Lithic webhooks. Use when setting up Lithic event subscriptions, debugging Standard Webhook
• litigation-analysis-qcc诉讼风险评估 SKILL · 企查查 MCP V2.0 增强版。 对目标企业执行"企业现状 + 企业历史 + 核心人员"三层诉讼全景扫描，输出可直接用于立案决策、授信决策、投资决策的司法风险评估报告。
• litigation-chronologyUse when building a factual timeline for litigation from provided source documents, producing a structured chr
• litigation-drafting-coreThe universal workflow for litigation drafting—from intake to filing-ready draft.
• litmus-testCreative direction Litmus Test for evaluating ideas, concepts, and messaging against a rigorous differentiatio
• littleben/awesomeAgentskillsA curated collection of skills for Claude Code and other AI agents | 精选的 Claude Code 和其他 AI 智能体技能集合
• littlefs-integrationUse when integrating, porting, configuring, or debugging littlefs on MCU flash, external NOR/NAND, SD-backed b
• liu-xiaoyan-english模拟刘晓燕老师的英语教学风格和方法论，用于四六级/考研英语辅导（已用2026年6月CET-6真题校准）。触发场景：用户提到刘晓燕、晓燕老师、四六级英语、CET-4、CET-6、2026六级、考研英语、英语阅读理解、英语写
• liucixin-perspective刘慈欣科幻创作思维——硬科幻的宏细节叙事、技术乐观主义、宇宙社会学构建。 触发词：「刘慈欣视角」「大刘会怎么写」「硬科幻构思」「宇宙尺度叙事」「黑暗森林式冲突」。 擅长：从科学概念推演社会冲突、构建跨越时空尺度的宇宙图景
• live-activity-generatorGenerate ActivityKit Live Activity infrastructure with Dynamic Island layouts, Lock Screen presentation, and p
• live-artifactCreate refreshable, auditable OpenDesign artifacts backed by connector or local data. Trigger when the user as
• live-canvasConduct design interviews, generate UI variations, and collect live click-to-annotate feedback that streams in
• live-co-dmReal-time co-DM for the Shattered Sea campaign while a session is actively being played. Invoke for: "co-DM th
• live-componentSymfony UX LiveComponent for reactive server-rendered UI -- components that re-render via AJAX on user interac
• live-dashboardNotion-style team dashboard rendered as a Live Artifact. A single-page, self-contained HTML dashboard with KPI
• live-database-ingestCapture semantic-layer and knowledge updates from a live database schema snapshot.
• live-session-management-for-agentic-engineeringMulti-agent engineering requires a live session layer in addition to durable Trackfiles, worktrees, checkpoint
• live-watchPolls the Agent Monitor /api/stats endpoint several times over a short window and reports the live deltas in a
• live.alpic.alpichack-3c740d01/alpichackAI-powered ticket triage and workflow automation
• live.alpic.apps-sdk-template-14df1dd6/apps-sdk-templateDescription of my MCP server
• live.alpic.clouddj-ce0f8cfd/clouddjcloud_dj
• live.alpic.doing-v2-d5286fe8/doingsimple task manager for your LLM
• live.alpic.email-mcp-400f7a0b/email-mcpDescription of my MCP server
• live.alpic.email-mcp-8d084a7a/email-mcpDescription of my MCP server
• live.alpic.email-mcp-dbb94dbf/email-mcpDescription of my MCP server
• live.alpic.email-mcp-ded4e7db/email-mcpDescription of my MCP server
• live.alpic.fast-mcp-f337845e/fast-mcpDescription of my MCP server
• live.alpic.gueguesser-chatgptap-68537aa2/gueguesser-chatgptappGeography Guesser game
• live.alpic.iaapp-a912a14e/IAAppChatgpt app for Morning brief
• live.alpic.lineup-bf157e35/lineupTurn one sentence into an event pack: event card, identity badges, QR codes, and .ics.
• live.alpic.linkup-company-resea-2df3e8e8/Linkup-Company-ResearchDescription of my MCP server
• live.alpic.mcp-server-template-7860f7d3/mcp-server-template-pythonDescription of my MCP server
• live.alpic.mcp-server-template-d2d1b3b5/mcp-server-template-xmcpDescription of my MCP server
• live.alpic.mcpimmo-10e693d9/mcpimmoDescription of my MCP server
• live.alpic.new-test-cli-239fbe01/new-test-cliAsk a question and get a deterministic Magic 8 Ball answer.
• live.alpic.node-email-mcp-b25f10ec/node-email-mcpDescription of my MCP server
• live.alpic.node-mcp-3a40efc5/node-mcpDescription of my MCP server
• live.alpic.openjobs-3168f222/openjobsFind jobs in your own words and apply on the company website — no detours.
• live.alpic.qa-test-cli-b955e6a8/qa-test-cliTesting publish command
• live.alpic.send-email-49a8d7ee/send-emailDescription of my MCP server
• live.alpic.staging.alpic-poc-frontend-c68d130f/alpic-poc-frontendDescription of my MCP server
• live.alpic.staging.demo-81c8a122/demoDescription of my MCP server
• live.alpic.staging.email-mcp-17ee097a/email-mcpStill WiP
• live.alpic.staging.email-mcp-3b5a375e/email-mcpStill WiP!
• live.alpic.staging.email-mcp-c880a7f7/email-mcpStill work in progress
• live.alpic.staging.everything-app-7f22928f/everything-appStill WiP
• live.alpic.staging.everything-app-ce82911c/everything-appStill WiP
• live.alpic.staging.mcp-server-6283dc54/mcp-serverA non functional MCP server (yet)
• live.alpic.staging.mcp-server-a2d17427/mcp-serverA non functional MCP server (yet)
• live.alpic.staging.mcp-server-template--1488dac2/mcp-server-template-nodejsNon functional server (yet)
• live.alpic.staging.mcp-server-template-5eacc5c3/mcp-server-templateA non functional MCP server (yet)
• live.alpic.staging.mcp-server-template-7b99436a/mcp-server-templateServer not ready (yet!)
• live.alpic.staging.mcp-server-template-8068f74b/mcp-server-templateA non functional MCP server (yet)
• live.alpic.staging.mcp-server-template-90a89880/mcp-server-templateWork in progress
• live.alpic.staging.mcp-server-template-99cbcf02/mcp-server-templateNot ready (yet!)
• live.alpic.staging.mcp-template-e37c5898/mcp-templateA non functional MCP server (yet)
• live.alpic.staging.node-email-mcp-25ea0992/node-email-mcpStill work in progress
• live.alpic.staging.node-email-mcp-731b03b7/node-email-mcpNon functional server (yet)
• live.alpic.staging.node-email-mcp-a629b9bc/node-email-mcpNon functional server (yet)
• live.alpic.staging.personal-chef-chatgp-c951fcb6/personal-chef-chatgpt-appOk
• live.alpic.staging.property-search-mcp-ce598409/property-search-mcpWork in progress (for now)
• live.alpic.staging.python-email-mcp-f5c8e0a7/python-email-mcpStill WiP
• live.alpic.staging.send-email-mcp-04d3fdca/send-email-mcpNon functional server (yet)
• live.alpic.staging.server-template-3b6131fe/server-templateA non functional MCP server (yet)
• live.alpic.staging.skybridge-712c1350/skybridgeA great map with info on Capitals all around the world
• live.alpic.staging.system-prompts-of-ai-987eba72/my-mcp-serverDescription of my MCP server
• live.alpic.staging.template-0f352e26/templateA non functional MCP server (yet)
• live.alpic.staging.template-nodejs-d3cd3099/template-nodejsA non functional MCP server (yet)
• live.alpic.staging/alpic-poc-frontend-9eb5bfc8Description of my MCP server mega cool capabilities, lesgo
• live.alpic.staging/email-serverAn MCP server that provides email capabilities, hosted on Alpic platform
• live.alpic.staging/mcp-server-template--43874b8fDescription of my MCP server
• live.alpic.staging/mcp-server-template--de51cc9aDescription of my MCP server
• live.alpic.staging/node-email-mcp-59eeb419An MCP server that provides email capabilities, hosted on Alpic platform
• live.alpic.staging/node-email-mcp-ea33e576Description of my MCP server
• live.alpic.staging/send-email-mcp-01f22b8fSuper description
• live.alpic.staging/test-serverAn MCP server that provides email capabilities, hosted on Alpic platform
• live.alpic.tasks-example-ca49f0f6/tasks-exampleA test MCP server for task management
• live.alpic.template-server-8e74ee32/template-serverDescription of my MCP server
• live.alpic.template-server-ed7df515/template-serverDescription of my MCP server
• live.alpic.test5-ca2cc17f/test5Skybridge demo for QA and playground validation
• live.bitcoinintel/signal-apiBitcoin 15-min prediction signals with on-chain commitment proofs. L402-gated.
• live.grabbit/screenshotsScreenshot any URL as a hosted image. No local browser; handles bot walls and full-page captures.
• live.hypertext/hypertextPublish complete HTML artifacts and return a public share URL.
• liveagent-code-reviewReview an open GitHub pull request or the current local branch and working tree with parallel, independent rev
• liveblocks-ui-skillsLiveblocks's UI design system. Use when building interfaces inspired by Liveblocks's aesthetic - dark mode, In
• livekit-skillsBuild voice AI agents with LiveKit Agents SDK. Use when the user asks to "build a voice agent", "create a Live
• liveryThe visual-craft lens for a frontend build — where the surface gets its color, type, depth, and motion. Use af
• livestream-and-realtimeThe live + realtime-format skill -- plan, promote, run, and repurpose livestreams and realtime moments (IG Liv
• liveview-code-reviewReviews Phoenix LiveView code for lifecycle patterns, assigns/streams usage, components, and security. Use whe
• liveview-patternsBuild LiveView: async data (assign_async), PubSub (check connected?),
• living-docsRun a project's documentation as a living system — docs-first issues/PRDs, MADR-lite ADRs (supersede, never de
• livreCommit les changements, se synchronise avec main distant, push la branche courante et crée une Pull Request. R
• LiXiaoYaoCareFree/MultiGenMulti-agent end-to-end application - General-purpose artificial intelligence agent for multimodal agent collab
• liyupi-seo-auditWhen the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "S
• lkangd-improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whicheve
• llamaMeta Llama open-source LLM family. Use for local AI.
• llama-cppOperate, configure, benchmark, and troubleshoot llama.cpp across CPU, Metal, CUDA, HIP/ROCm, Vulkan, SYCL, and
• llama-factoryExpert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, m
• llama-parseUse this skill to parse complex documents (PDFs, Word documents, PowerPoint presentations, Excel spreadsheets,
• llamaguardMeta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate,
• llamaindexProduction-ready AI coding skills for APIs. Installable skills for Claude Code, Cursor, Codex CLI, Gemini CLI,
• llavaLarge Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines
• lld-flow-explorerTurn a Low-Level Design doc (Mermaid sequence diagrams, state machines, pipeline charts) into ONE interactive,
• llm-api-call-error-wrapper-checksGuidelines and instructions for LLM API call error wrapper checks
• llm-api-rate-limit-retry-policiesGuidelines and instructions for LLM API rate limit retry policies
• llm-api-usage-tracking-database-layoutsGuidelines and instructions for LLM API usage tracking database layouts
• llm-app-developmentLLM app development with RAG, prompt engineering, vector databases, and AI agents
• llm-app-patternsProvides architectural patterns for LLM-powered applications and AI assistants, including prompt engineering,
• llm-app-securityApply operational controls to applications built on the Anthropic API or similar LLM SDKs. Maps the OWASP LLM
• llm-application-devBuilding applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use
• llm-artifacts-detectionDetects common LLM coding agent artifacts in codebases. Identifies test quality issues, dead code, over-abstra
• llm-as-computerExecute programs on a compiled transformer stack machine where every instruction fetch and memory read is a pa
• llm-benchmarkLLM benchmarking: design benchmark suites, establish baselines, run A/B model comparisons, detect regressions,
• llm-busterUse this skill when the user asks to audit a codebase for LLM API calls (OpenAI, Anthropic — Python and TS/JS
• llm-cachingImplement multi-layer LLM caching with exact match, semantic similarity, and provider-side prompt caching. Red
• llm-campaign-drift-gateGate resumption of any multi-day LLM batch-scoring campaign that calls an unpinned model alias (deepseek-chat,
• llm-coding-failure-modesRecognize the recurring security failure modes of LLM coding agents — Claude Code, Copilot, Cursor, Windsurf,
• llm-coding-guardrailsBehavioral guardrails to reduce common LLM coding mistakes with a caution-first approach.
• llm-comparisonAnalyze and produce a llm comparison with structured process, quality checks, and system integration
• llm-costToken accounting across a pipeline: where the spend actually accrues, caching that works, and the retry loop n
• llm-cost-advisorWHAT — Recommend the most cost-effective LLM provider for a given task type. Shows estimated
• llm-cost-optimizationFunnel-with-gate workflow for reducing LLM costs without degrading quality. Starts with diagnosing the cost su
• llm-cost-optimizerAudits an AI application for unnecessary token spend and recommends prompt caching, model routing, and token r
• llm-councilOrchestrate a configurable, multi-member CLI planning council (Codex, Claude Code, Gemini, OpenCode, or custom
• llm-debuggerDiagnoses LLM output failures including hallucinations, constraint violations, format errors, and reasoning is
• llm-deploy-training当需要部署或训练 LLM/VLM 时使用；覆盖 vLLM OpenAI-compatible 服务、多模态输入限制、Qwen3.5 工具调用、thinking/reasoning 控制、CUDA Graph 策略，以及
• llm-evalLLM evaluation: build evaluation datasets, choose metrics (RAGAS, G-Eval, LLM-as-judge), run automated evals,
• llm-evals-and-retrieval-qualityReference-grade guide to evaluating LLM and RAG systems — golden/regression/adversarial eval sets, LLM-as-judg
• llm-evaluationImplement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, an
• llm-fine-tuningSet up infrastructure for fine-tuning LLMs with QLoRA, LoRA, and full fine-tuning using Hugging Face TRL, Axol
• llm-friendly-context入力・出力・成功基準・決定事項・未解決条件を明確化し、下流エージェントが推測せず実行できるようにする。LLM向けのプロンプト・ハンドオフ・計画成果物・レビュー・レポート・生成指示を記述または改訂する時に使用。
• llm-gateLLM-powered quality verification using prompt hooks. Validates commit messages, code patterns, and conventions
• llm-gold-bound-failure-checkDiagnose whether an LLM classifier's validation-gate failure is GOLD-BOUND before spending on prompt revision
• llm-image-generation当需要通过 OpenAI-compatible LLM 网关生成图片时使用，尤其是使用 LLM_API_KEY 和 LLM_BASE_URL 调用 gpt-image-2、gpt-image-1、dall-e-3 等图像
• llm-inference-scalingAuto-scale LLM inference clusters on Kubernetes using KEDA, custom GPU metrics, and horizontal pod autoscaling
• llm-integrationLLM integration patterns including API usage, streaming, function calling, RAG pipelines, and cost optimizatio
• llm-judgeUse when comparing two or more code implementations against a spec or requirements doc. Triggers on \"which re
• llm-model-selectionSelect the right LLM for a task by consulting benchmarks and real performance data. Use when choosing between
• llm-observability-and-costReference-grade guide to production LLM observability and cost attribution — distributed traces and spans for
• llm-opsLLM Operations -- RAG, embeddings, vector databases, fine-tuning, prompt engineering avancado, custos de LLM,
• llm-privacyReversible PII tokenization for working with sensitive data. Masks personal data (emails, phones, IBANs, cards
• llm-prompt-engineeringDesign effective prompts for large language models - chain-of-thought reasoning, few-shot examples, role assig
• llm-providerAdds a new LLM provider implementing LLMProvider interface with call() and stream() methods. Integrates with p