Registry durchsuchen

Alle Einträge, alphabetisch — insgesamt 56.437. Seite 195 von 226.

• singleton-sd-refactoringIdentify and apply targeted refactoring improvements to existing code without changing behavior
• sinhoneyy-advanced-evaluationThis skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create eva
• sinhoneyy-agentfolioSkill for discovering and researching autonomous AI agents, tools, and ecosystems using the AgentFolio directo
• sinhoneyy-app-builderMain application building orchestrator. Creates full-stack applications from natural language requests. Determ
• sinhoneyy-bill-gatesAgente que simula Bill Gates — cofundador da Microsoft, arquiteto da industria de software comercial, estrateg
• sir-agentGenerates decision-grade Security and Impact Reports for applications, vendor SaaS, infrastructure changes, an
• sisyphus-designProduce high-quality design documents through research, divergent thinking, and iterative refinement
• site-architectureWhen the user wants to plan, map, or restructure their website's page hierarchy, navigation, URL structure, or
• site-audit-to-social-distributionFind weak pages, technical issues, and content gaps in SE Ranking, then coordinate the fix end-to-end in Plana
• site-generationEnd-to-end AI website generation pipeline. Claude Opus 4.8 emits Bolt-style <boltArtifact> envelopes (multi-fi
• site-launch-checklistPre-launch checklist for shipping a new website. Orchestrates analytics setup (GA4, PostHog, Google Search Con
• site-onboardingUse when the user says 'get started with my site', 'connect to my wordpress site', 'what can you do on my site
• site-reliabilityUse when establishing reliability practice. Covers SLOs and error budgets, capacity planning, graceful degrada
• site-server-auditAudit a public-facing site or server for common misconfigurations without sending exploit traffic. Covers DNS
• site-to-ios-appTurn a website, PWA, dashboard, or marketplace into an iOS app with App Store strategy, screenshots, metadata,
• site-worldBuild a complete, agency-grade website — not just a hero. Runs a structured pipeline: creative-brief interview
• site.jiebang.www/tools20 free dev tools: JSON/YAML, XML/SQL, Cron, SEO, QR code, URL shortener, cron tasks, files
• site.lanlan/website-builderBuild a hosted website by chatting. Snapshots, forms, analytics. Hand off the dashboard. Walk away.
• site.pdfzen/renderRender PDFs from 45 starter templates or raw HTML. Pay-per-render with USDC via x402.
• site.skew/skewAuthored design service: one-of-one landing pages, pitch decks, and research-grounded briefs.
• sitemap-auditXML sitemap audit — find and fix the sitemap problems that quietly waste crawl budget and slow indexing. Disco
• sitemap-task-biasUse when creating or auditing an agent-team sitemap, Task Bias ledger, concept coverage, product surface map,
• sitemapkitDiscover and extract sitemaps from any website using SitemapKit. Use this skill whenever the user wants to fin
• situk-yangtao-perspective用杨涛(涛哥/涛神)的认知操作系统分析问题。蒸馏自杨涛 ~970 万字一手输出(《确定性成长》+ 公众号「屋里涛说」+ 知识星球「平民创业手册」+ 播客 200 集 + 直播 300 小时 + 生财有术帖子)。触发场景:
• siva01c-feature-workflowPhased workflow for delivering a Drupal feature or non-trivial change: plan, implement, review, test, finalize
• six-hatsParallel thinking with six enforced perspectives, based on Edward de Bono's Six Thinking Hats® method - examin
• six-layer-product-researchExecute Teresa Torres' 6-Layer Problem Definition Framework for rigorous product research — from customer voic
• six-sigma-dmaicUse when the user wants to improve an existing process by reducing defects or variation using Six Sigma DMAIC
• six-sigma-rGenerates R implementations for Six Sigma / statistical-process-control tasks — control charts (X-bar R, I-MR,
• six-sigma-verification-stageSix Sigma Black Belt verification and body-of-knowledge skill for auditing project plans, phase plans, impleme
• six-thinking-hatsUse when the user wants to examine an idea, plan, or decision from every angle, run a structured deliberation,
• sixtyfourPeople and company intelligence via the Sixtyfour AI API. AI research agents that read the live web — not stat
• size-and-justify-samplesThe canonical sample-size-and-sufficiency reference for all research — the single authority on 'how many parti
• skalesapp/skalesYour personal AI desktop agent for Windows, macOS, Linux & Android. Set a goal, it works on its own. Teams (pa
• skd-editНабор навыков для AI(ИИ)-агентов (Claude Code, Cursor, Codex и др.), помогающий охватить полный цикл разработк
• skeleton-loadersFor building skeleton loading states that are pixel-perfect matches of real content. Use this skill whenever a
• skepticPressure-test a plan, finding, or design — steelman it, attack correctness/necessity/cost, and deliver a REFUT
• sketchIterate a UI/UX surface with a human — at the highest fidelity the target can honestly afford — and climb from
• skeumorphismReal-world mimicry with textured surfaces, 3D effects, and familiar physical metaphors for intuitive digital i
• skf-analyze-sourceDiscover what to skill in a large repo and produce recommended skill briefs. Use when the user requests to "an
• skf-audit-skillDrift detection between skill and current source code. Use when the user requests to "audit a skill" or "audit
• skf-brief-skillDesign a skill scope through guided discovery. Use when the user requests to "create a skill brief" or "brief
• skf-campaignCampaign orchestration — multi-library skill production with dependency tracking, file-based state, and resume
• skf-create-skillCompile a skill from a brief. Supports --batch for multiple briefs. Use when the user requests to "create a sk
• skf-create-stack-skillConsolidated project stack skill with integration patterns — code-mode (analyzes manifests) or compose-mode (s
• skf-drop-skillDrop a specific skill version or an entire skill — soft (deprecate) or hard (purge) with platform context rebu
• skf-export-skillPackage for distribution and inject context into CLAUDE.md/AGENTS.md/.cursorrules. Use when the user requests
• skf-forgerSkill compilation specialist — the forge master. Use when the user asks to "talk to Ferris" or requests the "S
• skf-quick-skillFast skill from a package name or GitHub URL — no brief needed. Use when the user requests a "quick skill" or
• skf-refine-architectureImprove architecture doc using verified skill data and VS feasibility findings. Use when the user requests to
• skf-rename-skillRename a skill across all its versions — transactional copy-verify-delete with platform context rebuild. Use w
• skf-setupInitialize forge environment, detect tools, and set capability tier (Quick/Forge/Forge+/Deep). Use when the us
• skf-test-skillCognitive completeness verification — quality gate before export. Use when the user requests to "test a skill"
• skf-update-skillSmart regeneration preserving [MANUAL] sections after source changes. Use when the user requests to "update a
• skf-verify-stackPre-code stack feasibility verification against architecture and PRD documents. Use when the user requests to
• skillA general skill for following instructions precisely and making no mistakes.
• skill-0058Specialized skill #0058 for design development
• skill-0119Specialized skill #0119 for data development
• skill-1Declarative management of Agent Skills on Nix
• skill-2Declarative management of Agent Skills on Nix
• skill-aSkill A from skills directory
• skill-abacatepay-integrationIntegrate AbacatePay PIX/card billing, customers, QRCode PIX, billing webhooks, CPF/CNPJ validation, BRL SaaS
• skill-adrRegistra decisões arquiteturais com contexto, alternativas, drivers, consequências, evidência e plano de revis
• skill-agent-observabilityDefine observabilidade para agentes e aplicações de IA com eventos, tracing, custos, latência, qualidade, regr
• skill-ai-orchestrationUse for server-side AI orchestration in SaaS products, including OpenAI, Gemini, Claude, ElevenLabs, streaming
• skill-aionui-cowork-orchestrationUse when integrating AionUi into the {{USER_NAME}} orchestrator workflow, coordinating Codex, Claude, Gemini,
• skill-alignAudit and fix all Lattice documentation, README, docs/, PROJECT.md, GitHub issue templates, and CLAUDE.md to e
• skill-antivirusReview agent skills (SKILL.md, skill folders, or ZIP packages) with deterministic static analysis plus LLM heu
• skill-architectExpert guide for designing and building high-quality skills from scratch through structured conversation. Use
• skill-atlasGraph, categorize and visualize the installed Claude Code skill collection. Use when the user wants to map, au
• skill-atlas-builder制作只保存在本机的 Skill Atlas / 技能速查网页：扫描使用者自己电脑上多个 AI Agent 环境中的 SKILL.md，合并成可搜索、按任务筛选、按主题和运行环境过滤的索引，提供收藏、详情、Prompt 复
• skill-auditAudit, design, categorize, distribute, and measure agent skills using lessons from Anthropic's Lessons from bu
• skill-audit-auditRun a full skill activation audit experiment. ALWAYS invoke this skill when the user says "skill audit", "audi
• skill-audit-setupSet up the skill-audit plugin environment. ALWAYS invoke this skill when the user says "skill-audit setup", "s
• skill-auditingActivates when the user wants to see their installed skills, mentions "skill manager", "check my skills", "ski
• skill-auditorAnalyze agent skills for security risks, malicious patterns, and potential dangers before installation. Use wh
• skill-authorTeach an author how to integrate the CAFleet-orchestrated team pattern into a new skill they are writing. Auto
• skill-authoringUse when creating, editing, or reviewing HOTL skills, agents, command prompts, or other behavior-shaping instr
• skill-authoring-guideOfficial catalog registry for skill-hub
• skill-authoring-standardThe bar a SKILL.md must clear before it ships in this lacquer — tight trigger-oriented frontmatter, single res
• skill-authoring-workflowTurn raw PM content into a compliant, publish-ready skill. Use when creating or updating a repo skill without
• skill-bSkill B from experimental directory
• skill-base-cliThe official Skill Base CLI client. Use the `skb` (Skill Base CLI) command to search, install (single skill or
• skill-base-web-deploySkill Base server deployment guide. Covers starting the Skill Base server (npx skill-base), Docker configurati
• skill-blueprint为任意 Claude Code SKILL.md 自动生成 ASCII 架构图 + Mermaid 流程图的元技能。 当用户说 "画架构图"、"visualize this skill"、"生成蓝图"、"添加架构图"、
• skill-boilerplateDefine a standard per-skill local data layout at <project_root>/.skills-data/<skill-name> and required SKILL.m
• skill-browser-agentUse for reliable web-browser agents, semantic page inspection, Playwright automation, accessibility-tree navig
• skill-builderBuild correct, consistent Agent Skills for any compatible agent product. Use when creating, updating, renaming
• skill-building-guideHelps plan, structure, test, and distribute Claude Agent Skills. Use when drafting SKILL.md frontmatter, organ
• skill-cUse when doing task C.
• skill-captureExtracts valuable workflows, patterns, and domain knowledge from conversations and persists them as reusable S
• skill-chain-generatorUse when you need to create, design, or generate a multi-skill workflow (skill chain) for complex multi-phase
• skill-checkValidate Claude Code skills against Anthropic guidelines. Use when user says "check skill", "skillcheck", "val
• skill-checkerReviews a SKILL.md file and evaluates whether it is well-constructed, using best practices distilled from real
• skill-checkupSkill quality + package structure expert. ALWAYS invoke when creating, editing, reviewing, or restructuring an
• skill-ci-checklistA curated collection of Claude Code skills for SpoonOS development and Web3 integrations. 57 Python scripts ac
• skill-cleanerAudits ~/.claude/skills/ for hygiene issues. Use when trimming the skill set, asking which skills are unused o
• skill-cli-generatorGenerates a SKILL.md and Python CLI script for any API or service, following the Agent Skill + CLI Architectur
• skill-cobranca-automatizada-saas-abacatepayAutomatic SaaS billing engine with AbacatePay (PIX + credit card), configurable dunning (regua de cobranca), t
• skill-compassInstall, configure, and operate the skill-compass hooks for Claude Code — UserPromptSubmit + PostToolUse hooks
• skill-complyMeasure whether agents actually follow a skill, rule, command, or agent definition by deriving expected behavi
• skill-composerDAG-based multi-skill orchestration with dependency resolution.
• skill-compositionCRITICAL: Skill composition engine for automatic workflow generation from skill metadata. Triggers: compose sk
• skill-conductorCreate, edit, evaluate, and package agent skills. Use when building a new skill from scratch, improving an exi
• skill-console-dashboard-builderGenerate a single-file HTML console for local Codex/Claude-style SKILL.md libraries. Use when the user wants t
• skill-consumerUse when consuming optimization artifacts.
• skill-converterConvert an upstream agent spec, prompt file, markdown role definition, or similar source document into a local
• skill-coverage-mapA curated collection of Claude Code skills for SpoonOS development and Web3 integrations. 57 Python scripts ac
• skill-craftingCreate, fix, and validate skills for AI agents. Use when user says 'create a skill', 'build a skill', 'fix my
• skill-creation-walkthroughStep-by-step guide for creating your own Claude Skills, from deciding whether a skill is the right tool to wri
• skill-creatorCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to c
• skill-creator-enhancedGuide for creating effective skills. This skill should be used when users want to create a new skill (or updat
• skill-creator-githubGenerate SKILL.md files conforming to the arxiv-claude-skills repository format. Extracts methodologies from a
• skill-creator-guideInterviews you about a task you repeat often, then walks you through building a custom skill for it using Cowo
• skill-creator-proCreate and evolve production-ready skills with reusable scripts, references, and validation. Use for new skill
• skill-cronUse when the user wants to register, inspect, manually run, or remove scheduled Claude skills with Telegram pu
• skill-curatorSelf-evolving memory layer for AI coding agents. Captures failure DNA, prevents bug repetition, enables collec
• skill-customizerCustomize any Cowork skill or workflow to match your specific industry, company, and style. For tuning default
• skill-database-migrationsPlaneja e verifica migrações de banco com compatibilidade, idempotência, RLS, seeds, índices, backfill e rollb
• skill-debriefDebrief an AI agent skill (SKILL.md) after using it — capture session feedback or a retrospective and fold it
• skill-deep-wikiGera documentação técnica navegável de um repositório, com arquitetura, Mermaid, onboarding, AGENTS.md, llms.t
• skill-dependency-upgradeAtualiza dependências com changelog, compatibilidade, vulnerabilidades, lockfile, testes e plano de rollback.
• skill-description-optimizerMeta-skill for optimizing skill descriptions using SDS standard and seven core techniques. Use when refining s
• skill-design-benchmark评估一个或一批 Agent Skills 的设计质量，按 8 个有来源、有证据的维度输出 0–100 分、S/A/B/C/D 等级和优先改进项。重点检查触发边界、完成闭环、决策适应、安全恢复、上下文效率、复杂度适配、一致
• skill-design-guideComprehensive guide for designing, building, testing, and distributing Claude skills. Use when user wants to "
• skill-designerDesign new Claude skills from structured idea specifications. Use when the skill auto-generation pipeline need
• skill-developerCreate and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifyi
• skill-developmentThis skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill
• skill-dietAudit the always-on context cost of an agent setup: installed skills, memory files (CLAUDE.md, AGENTS.md), and
• skill-discoveryFind agent skills and skill repositories on GitHub.
• skill-dispatchSingle front door for authoring and maintaining agent skills. Parses a subcommand — create, capture, comply, o
• skill-distillerFetches top-rated skills from skills.sh, analyzes them, and synthesizes one token-efficient skill combining th
• skill-distributionUse when packaging, installing, publishing or sharing an Agent Skill, or when deciding how to get a SKILL.md o
• skill-doc-indexA curated collection of Claude Code skills for SpoonOS development and Web3 integrations. 57 Python scripts ac
• skill-doctorUse the `skill-doctor` CLI to analyze, audit, and diagnose AI-agent skills (duplicates, conflicts, security ri
• skill-downloaderDownload and install Claude Code skills from various sources. Supports GitHub repositories, compressed archive
• skill-draftingUse when creating, updating, reviewing, or validating Codex or Claude skills: drafting SKILL.md files, trigger
• skill-ecosystem-doctorAudit and safely repair cross-runtime Skill ownership, loading, duplication, scopes, budgets, lifecycle, quara
• skill-elevenlabs-voice-cloningUse for ElevenLabs voice generation and voice cloning integrations, including Brazilian Portuguese TTS, explic
• skill-enhanceImprove a SKILL.md file by applying missing or weak skill-authoring patterns (17 patterns across 7 categories)
• skill-evalBehavioral evaluator for zuvo skills. Runs a skill against its eval corpus (evals/<skill>.evals.json) in fresh
• skill-eval-loopRun the observe-analyze-iterate loop on promptfoo evals for a skill collection. Promptfoo-specific — assumes p
• skill-eval-runnerUse when the user types "/eval skill X", "test skill X", "run evals on", "regression test skill", "eval skill"
• skill-evals-maintenance-playbookMaintain Agent Skills over time by defining evals, running benchmarks, comparing variants, and tightening skil
• skill-evaluation-workbenchUse when designing, running, debugging, or hardening deterministic eval suites for agent skills, prompts, tool
• skill-evaluatorRigorously evaluate an Agent Skill end-to-end across ANY coding-agent CLI — verify its scripts emit the docume
• skill-everythingGit-versioned agent memory — agents that never make the same mistake twice.
• skill-evo交互式锻造项目专属 Claude Code skills，内置自我进化能力。 扫描项目 → 规划 → 问答 → 生成。可反复执行，越用越好。 触发词：初始化 skills、init skills、skill-evo、锻造
• skill-evolution-apiUse for WhatsApp automation with Evolution API, including instance lifecycle, QR pairing, inbound and outbound
• skill-evolve피드백 기반으로 SKILL.md를 자동 개선하는 메타 스킬
• skill-example-runnerA curated collection of Claude Code skills for SpoonOS development and Web3 integrations. 57 Python scripts ac
• skill-explorerVisualize SKILL.md structure.
• skill-extractorA Claude Code Marketplace
• skill-factoryAnalyze session work and automatically convert reusable patterns into Claude Code skills. Use when: "세션을 스킬로",
• skill-federationConsult the current state of practice before doing expert work — search a federated catalog of vetted agent sk
• skill-feedback-writerUse to identify missing instructions in another skill based on its output.
• skill-fetchThis skill should be used when the user asks to "fetch skill", "install skill", "search for a skill", or when
• skill-finderUse WHENEVER the user wants to find, install, manage, or CREATE an AI agent skill / Claude Code skill / Codex
• skill-fixSkill诊断修复|description字段扫描压缩。触发:"fix skill"|"skill not working"|"agent output unstable"|"context pollution"|"fi
• skill-flowUse when the user asks Codex to inspect, import, enable, disable, deploy, update, repair, migrate, or uninstal
• skill-forgeUse when creating new Rune skills, editing existing skills, or verifying skill quality before deployment. Appl
• skill-forge-auditBatch-evaluate all skills in the repo with skill-forge-judge and render a single consolidated grade report sor
• skill-forge-createCreate a new SKILL.md via discovery recap, pattern selection, WebFetch spec fetch, knowledge delta discipline,
• skill-forge-feedbackCollect user feedback (bugs, friction, feature requests) about skill-forge skills via a short interview, then
• skill-forge-hitlApply a numbered list one item at a time — status board upfront, per-item approve/skip, approve-all mode, comm
• skill-forge-judgeEvaluate any LLM prompt (SKILL.md, CLAUDE.md, system prompts, bash guidance) for quality: grouped dimensional
• skill-forge-recapRead a skill's body and report what it actually does vs. what the description claims: drift, undeclared behavi
• skill-forge-updateGuided update for an existing SKILL.md: structured recap, drift detection, change elicitation with conflict ch
• skill-foundryAuthor high-quality Claude Code SKILL.md files using philosophy-first design, evidence-based prompting, progre
• skill-frontend-ux-guardrailsApply frontend UX quality gates for SaaS dashboards, product screens, modals, tables, forms, responsive layout
• skill-gap-detectorUse when the user wants to "find missing skills", "what skills should I have", "what am I explaining over and
• skill-gateBefore starting any significant task, force explicit evaluation of available skills. For each potentially rele
• skill-generalizerUse when turning local, private, or personal Agent Skills into publishable skills for GitHub, marketplaces, te
• skill-generationLLM-powered generation pipeline for Claude Code skills and CLAUDE.md — doc-init command, prompt system, contex
• skill-generatorCreate new Claude Code skills with proper structure and best practices. Use when the user wants to create a ne
• skill-google-workspace-syncUse for Google Workspace integrations with OAuth, Calendar, Meet, FreeBusy, Drive, Sheets, webhooks, least-pri
• skill-graph-auditAudit Skill() refs; detect hubs, isolates, and dangling targets. Use when auditing skills.
• skill-graph-creatorGuide for creating skill graphs — interlinked, modular skill architectures that decompose knowledge into navig
• skill-graveyardAudit which Claude Code skills you actually invoke. Use when the user wants to find dead/unused skills, halluc
• skill-grepUse when a user is trying to discover an installable or reusable skill or workflow, especially when they ask f
• skill-guideSkill navigator and guide -- automatically scans all installed skills and slash commands, then explains them i
• skill-harmonizationHarmonize a repository's skill portfolio across catalog and user-installed skills.
• skill-health-checkValidate skill quality against routing, progressive loading, and verification criteria. Use when: auditing ski
• skill-hunterUse when the user wants to find NEW external skills for a project, build a skill stack from external registrie
• skill-i18nTranslate SKILL.md and README.md files into multiple languages for sharing skills internationally
• skill-id-here1行で何をするスキルか。いつ使うかを書く。
• skill-id-kebab-case-skills-catalog-yamlOne line — used in CLAUDE.md system-reminder and the skill catalog.
• skill-idea-minerMine Claude Code session logs for skill idea candidates. Use when running the weekly skill generation pipeline
• skill-importDiscover and import skills from external git repos into the current project's .claude/skills/, matched to the
• skill-improveImprove a skill using a test-fix-retest loop. Runs static checks, proposes targeted fixes, rewrites the skill,
• skill-improvement-guideRevise an existing Skill's SKILL.md based on real execution experience or user feedback, and hand back an upda
• skill-improverReview feedback from skill retrospectives and update skill files to improve with use. Creates a continuous imp
• skill-incident-responseOrganiza resposta a incidentes técnicos com contenção, evidência, comunicação, recuperação, timeline e postmor
• skill-initcheat-on-skill 的首次 onboarding。盘点用户能力（现有技能/可迁移底子/学历经验/每周可学时间/能坚持几个月/学习能力自评/地区/目标薪资/转型紧迫度），判定起点档位，创建 .skill-stat
• skill-inspectorReview AI agent skills before installation using NVIDIA SkillSpector and source-aware semantic review. Use whe
• skill-installation审查、安装、配置、激活、验证、更新和回滚 AgentDock Skill 时使用；负责来源校验、安全评估、环境配置和已安装版本验收。
• skill-installerInstall Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks t
• skill-integration-testerValidate multi-skill workflows defined in CLAUDE.md by checking skill existence, inter-skill data contracts (J
• skill-interview-builder通过分步访谈引导用户理清需求，最终产出完整的Skill文件包（含SKILL.md、参考文档、示例文件等）， 并打包为可直接使用的压缩包。 当用户说"我想通过访谈新建Skill"、"用访谈方式做一个Skill"、"访谈建S
• skill-inventoryInventory the installed skills and which plugins contribute them, then flag overlap with the user's own skills
• skill-judgeEvaluate Agent Skill design quality against official specifications and best practices. Use when reviewing, au
• skill-landingpage-claude-opusBuild high-converting landing pages with persuasive copywriting, CRO best practices, and production-ready HTML
• skill-learningExtracts actionable knowledge from external sources and enhances existing skills using a 4-tier novelty framew
• skill-lgpd-brasilLGPD-focused privacy and data-governance skill for Brazilian software products. Use for data mapping, legal ba
• skill-libraryAgent-native catalog and installer for armory packages across all 7 types. Browse, search, install, update, an
• skill-library-missionBuild a project skill library in .claude/skills/ via discovery, parallel authoring, and review. Use when packa
• skill-lifecycle-managerManage Agent Skills across Codex, Claude Code, local/global/project roots, Skill Hubs, GitHub, skills.sh, and
• skill-lifecycle-promotionUse when adding or auditing Agentlas skill lifecycle metadata, skill-registry.json, trial evidence, Curator pr
• skill-lifeguardUse when a skill is brittle, drifting, repeatedly failing, or needs a Reliable Skill Contract. Trigger for phr
• skill-lintLint and auto-fix skill folders for metadata, naming consistency, path placeholder consistency, and optional a
• skill-linterAudit SKILL.md files against published skill-authoring guidance — frontmatter validity, whether the descriptio
• skill-live-processingUse for live stream and VOD ingestion pipelines, including YouTube, Twitch, uploads, capture jobs, queues, tra
• skill-maintenance-skillMonthly skill library maintenance with audit scripts and gap detection. Use when auditing skills for 'Use when
• skill-managementManage a skill repository: create, classify, improve, deprecate, or reorganize agent skills with clean buckets
• skill-managerReference: detailed uninstall, disable, and re-enable workflows for community skills installed via the strateg
• skill-manual-video-processingUse for manual video or audio uploads in SaaS apps, including upload UX, direct storage, validation, malware c
• skill-mapPRB's collection of agent skills
• skill-masterIntelligent skill orchestrator that automatically finds, creates, executes, and improves skills. When you need
• skill-matcherIntelligent skill recommendation and activation system. Use when: (1) user asks what skills are available, (2)
• skill-mcp-builderProjeta e implementa MCP servers seguros, com schemas claros, autenticação mínima, tratamento de erros, testes
• skill-mcp-masterMaster reference for the Skill MCP server - a self-hosted agent skills registry that delivers curated, expert
• skill-md-basicUse this skill when the user wants a Hello World demonstration in Python. Provides a minimal verified example
• skill-md-permissionedUse this skill when the user wants to commit staged changes with a conventional-commits style message. The ski
• skill-md-with-examplesUse this skill when the user wants to format JSON files in place. The skill demonstrates a typical read → tran
• skill-measureRun a baseline-enhance-reeval loop on a SKILL.md to measure improvement. Generates targeted test cases for enh
• skill-memoryUse skill-memory to download, view and edit agent skills in memory. TRIGGER by 'skill', 'memory', 'learn'.
• skill-metadata-maintainerInitialize or update the metadata field in one specific skill's SKILL.md according to this repository's CONTRI
• skill-metadata-qualityOfficial catalog registry for skill-hub
• skill-metrics-collectorA curated collection of Claude Code skills for SpoonOS development and Web3 integrations. 57 Python scripts ac
• skill-minerUse when mining coding-agent session history, archived transcripts, memories, or repeated local work to discov
• skill-modern-ui-patternsUse for professional SaaS UI implementation and refinement in React, TypeScript, Tailwind, dashboards, admin p
• skill-monitorAnalyze skill effectiveness across sessions. Computes per-skill metrics (action rate, friction, outcomes), ide
• skill-multi-publisherOne-command publish a Claude Code skill to ALL major marketplaces: GitHub (npx skills), ClawHub, and community
• skill-multiagent-orchestrationUse when a task mentions subagents, multiagents, parallel agents, team execution, swarm, delegation, or requir
• skill-name<one-line description>
• skill-name-must-equal-the-parent-folder-name-of-skill-md-lowercase-hyphenatedGENERIC form: To <verb> <what it does + when/why; dense keywords>. CRITICAL/guardrail form: 'Rosetta CRITICAL
• skill-navigatorUse when users ask which already-installed local Agent Skill should handle a task. It calls local skm recommen
• skill-open-design-uiApply open-design product UI workflow for premium visual redesigns, dashboards, landing pages, design tokens,
• skill-opsSkill ops hub: snapshot/rollback + usage health + invocations.
• skill-optimisercompress SKILL.md tokens, indexify large skills, parallel sweep all skills
• skill-optimizationスキルファイルの品質を8つのコンテンツパターンと9つの編集原則で評価・最適化。スキル作成、内容改善、品質監査時に使用。
• skill-optimize-imagesOptimizes images for blogs and websites, including format conversion, resizing, compression, responsive delive
• skill-optimizer诊断并优化 Skills 的持续改进工具，支持调用 efficiency-audit 进行效率审计。触发词：优化 skill、skill 没触发、为什么没有、skill 诊断、skill-optimizer
• skill-orphanUse when doing an orphan task.
• skill-os-builderStand up a self-contained second-brain "OS" that lives entirely inside a Claude skill — a short SKILL.md route
• skill-packageOptimize an Agent Skill package itself — its SKILL.md (frontmatter + body), references, and bundled scripts. U
• skill-package-builderSelf-evolving memory layer for AI coding agents. Captures failure DNA, prevents bug repetition, enables collec
• skill-packagerOpen-source desktop AI agent that gets work done — plans & self-corrects, agentic visual workflows, generative
• skill-pdf-content-extractorBattle-tested reusable skills for OpenClaw, Claude, and agent runtimes · 真实任务验证过的可复用 Agent Skills
• skill-perfectionUse this skill when you need to QA audit and fix a plugin skill file. Provides a methodology for verifying ski