Browse the registry

Every entry, alphabetically — 67,843 in total. Page 239 of 272.

• skill-writing-guideUse when creating, reviewing, or refining Agent Skills for this repository
• skill-writing-guideline自作 skill を書く・変更する・レビューするときに参照する記述規範。frontmatter・見出し構造・本文規約・チェックリストを定める。手動起動。
• skillaInstall, update, list, verify, and remove agent skills (agentskills.io) and Agent Plugins (agent-plugins.org)
• skillalchemy|
• skillberry-ai-diagnoseExtract the learning signal from execution traces — the textual analogue of a gradient. Use between evaluation
• skillcaddy-managerManage Skillcaddy source acquisition, source updates, migrations, project skill links, and the Web/TUI CLI. Us
• skillcheckValidates SKILL.md files for spec-facing structure, sizing, references, cross-agent compatibility, and agent-a
• skillci-guardrailsUse this skill whenever you create, edit, or review a Claude Skill — any SKILL.md file, or the eval cases/conf
• skillcraftESLint + Jest for agent-config files: lint, sync and scaffold SKILL.md / CLAUDE.md / AGENTS.md.
• skillctx-ify>
• skillctx-sync>
• skilldbSDK and CLI for SkillDB — discover, install, and manage AI agent skills
• skilldoctorDiagnose the Claude Code skills installed on this machine — why one never triggers, and whether Claude can see
• skilldoomRun DOOM in the Claude preview pane. Prebuilt WebAssembly — no compiling, no network calls. Ships Freedoom (fr
• skillers-compactCompact conversation transcripts into themed knowledge files.
• skillfed-mcpFind vetted agent skills for your task — privacy-preserving skill discovery over MCP.
• skillfileGenerate and refresh cross-agent context files (AGENTS.md, Claude SKILL.md) from a deterministic scan of a rep
• skillfold-cliUse skillfold to manage a project's Claude skills. Declare skills in skillfold.yaml, pin them in skillfold.loc
• skillforgeCreate or update a reusable agent skill. Use when you notice a repeated pattern, when a workflow should be per
• skillguardReview Claude/Cursor Skills for security issues (prompt injection, agentic/tool injection, data exfiltration,
• skillguard-cliSecurity scanner for third-party AI agent-skill files (SKILL.md, hooks, scripts) via MCP.
• skillhone>
• skillhone-evaluation>
• skillhone-optimization>
• skillhone-prd>-
• skillhone-synthesisUse this skill to synthesize closed-form, automatically verifiable benchmark Q/A by exploring a tool environme
• skillify>
• skillintAudit, lint, and secure AI agent skills across Codex, Cursor, Claude Code, Grok, Gemini, Copilot, and more. Us
• skillkit>
• skillkit-help>
• skillmatch-mcpJob search and ranking pipeline via MCP for Claude Desktop.
• skillmedev-deep-researchRuns a thorough multi-source research process - decompose the question, gather independent sources, cross-chec
• skillnoteSelf-hosted skill registry for OpenClaw. Stores procedures your team writes (name, description, body), syncs t
• skillnote-doctorA diagnostic tool for OpenClaw agents -- checks skill registry connectivity, AGENTS.md setup, config file vali
• skilloptRuns the SkillOpt single-lineage optimization loop over epochs x mini-batches with a textual learning rate (an
• skillopt-sleepReference-only OpenClaw adaptation of SkillOpt-Sleep. Use it to study or port the contributed DeepSeek wrapper
• skillpackGenerate and verify the agent-distribution layer for any OSS project
• skillpack-creatorCreate a reusable SkillPack from a successful completed task. Use when the user wants to convert a one-off res
• skillpmManage npm-distributed Agent Skill packages with skillpm.
• skillproof-mcpCheck whether a Claude Code skill was tested and whether it works before installing it.
• skills
• skills-analytics-dashboardLaunch the skills analytics dashboard to view usage metrics, scores, and trends
• skills-and-mcp-architecture-playbookGuidance for designing workflows where MCP servers provide tool access and skills encode procedural expertise,
• skills-approveUse when you need the Codex Copilot equivalent of Claude Copilot /skills-approve: review available skills and
• skills-auditAudit .agents/skills SKILL.md files. Use for recurring checks of duplicate, overlapping, stale, inconsistent,
• skills-backup-keeperKeeps dated backups of the Cowork skills folder and an append-only session journal so work survives crashes, c
• skills-best-practicesBuild high-quality Agent Skills for any agent - opinionated best practices distilled from the Agent Skills spe
• skills-cliUse when users ask to discover, install, list, check, update, remove, back up, restore, sync, or initialize Ag
• skills-creatorCreate or update LiveAgent runtime skills. Use when you need to summarize a workflow into a skill, write it in
• skills-evalEvaluate Claude skill quality through auditing. Use when reviewing or auditing skills.
• skills-finderFind Agent Skills on skills.sh and adopt only the ones that pass a security audit. Use when the user wants to
• skills-flaky-test-analyzerSkill phân tích và khắc phục các automation test không ổn định (flaky tests), xác định root cause và đề xuất f
• skills-framework-architectSkill thiết kế và scaffold automation framework hoàn chỉnh cho Playwright, Selenium, và Appium — bao gồm proje
• skills-from-the-artificerDispatcher for the Artificer laws-of-software collection. Given a proposed change, fix, diff, design, or decis
• skills-gatewayIntelligent skill selection system that reduces token consumption
• skills-hubBrowse and install community skills from the BioClaw Skills Hub. Use when a user's task is not covered by buil
• skills-index>
• skills-index-snippetsCreate and maintain AGENTS.md / CLAUDE.md snippet indexes that route tasks to the correct dotnet-skills skills
• skills-installerInstall, list enabled, validate, or package LiveAgent skills. Use when you need to inspect the skills enabled
• skills-jira-integrationSkill tích hợp Jira/Xray — lấy requirements từ Jira, xác thực Xray, và đẩy kết quả test lên Xray Cloud/Server.
• skills-keysManage API keys for the runner's --execute layer. CRUD on ~/.skills.env (chmod 600): list / add / update / rem
• skills-load>
• skills-locator-healer-agentSkill tự động phát hiện và sửa chữa locators bị hỏng khi automation tests fail do thay đổi DOM.
• skills-lock>-
• skills-managementSearch, find, discover, install, remove, update, review, deduplicate, list, move, optimise, and iterate on ski
• skills-manager搜索、安装和协调创建 Claude Code Agent Skills。当用户想要搜索技能、安装工具、创建自定义 Skill，或者说"find a skill"、"搜索技能"、"帮我做个 skill"、"create a
• skills-managingCreate and manage ASE skills following best practices. Use when creating new skills, importing skills, underst
• skills-packaging-principlesPackage domain expertise into scalable Agent Skills using progressive disclosure (metadata, SKILL.md, and on-d
• skills-qa>
• skills-qa-automation-engineerSkill hỗ trợ agent thực hiện các tác vụ QA automation testing bao gồm generate test cases, automation scripts,
• skills-rbt-manual-testingSkill sinh manual test cases với 2 modes — QUICK (sinh nhanh từ requirements) và FULL RBT (quy trình AI-RBT 6
• skills-requirements-analyzerKỹ năng phân tích trang web/module/tài liệu và sinh ra tài liệu Yêu cầu (Requirements Document/User Stories) c
• skills-save>
• skills-security-check腾讯云鼎实验室出品，Skill安全审查工具。对用户指定的skill.md文件及其配套的文档、程序、脚本等进行全面安全审计，确保引用安全
• skills-share>
• skills-smart-locator-agentSkill sinh locator ổn định và dễ bảo trì cho UI automation, hỗ trợ Playwright, Selenium và Appium.
• skills-stack-explainerDecide when to use Skills vs prompts, Projects, MCP, and subagents, and combine them into a coherent workflow.
• skills-stylesManage the local style library — bundled (24 carousel + 12 video director + 12 music genre) plus user override
• skills-summarizerSummarize skill usage logs into JSON and HTML upkeep reports, and propose conservative skill improvements with
• skills-test-data-generatorSkill sinh test data có cấu trúc, unique, traceable cho automation tests, bao gồm positive, negative, boundary
• skills-ui-debug-agentSkill inspect web/mobile applications bằng browser tools, phân tích DOM elements, xác định locators ổn định, d
• skills-update>
• skills-updaterImprove existing skills in this repo by proposing and applying minimal, reviewable edits based on observed gap
• skills-visibilityPublish a catalog of agent skills and make it discoverable to AI coding agents and their installers — the way
• skills-voteFind the most relevant external agent skills for the current task, then submit grounded feedback about which s
• skills-vote-localUse when retrieving the most relevant skills from a local or private skill library instead of relying on netwo
• skills-web-devTop-level router for the Chwezi Core Systems web-development and software-engineering skills engine. Use for A
• skillscopeInspect and manage SKILL.md files across every agentic-CLI harness on this machine — Claude Code, Codex, Curso
• skillselion-mcpOn-demand access to thousands of install-ranked Claude Code skills - search and load mid-task.
• skillsguardAudit AI agent skill packages for security threats before installing or using them. Use this skill to scan a S
• skillshare|
• skillshare-changelog>-
• skillshare-cli-e2e-test>-
• skillshare-codebase-audit>-
• skillshare-devcontainer>-
• skillshare-implement-feature>-
• skillshare-release>-
• skillshare-ui-website-style>-
• skillshare-update-docs>-
• skillsindex-mcpSearch and score 11,000+ AI agent tools: MCP servers, Claude skills, GPT actions, IDE plugins.
• skillsmithSkillsmith is the canonical lifecycle manager for agent skills (SKILL.md format) across any MCP-capable agent
• skillsmith-agentDelegate your agent-skill lifecycle: keep skills current, audit and clean up your inventory, and vet skills be
• skillspec-backportReconcile changes from a modified SKILL.md back into the .agent source file.
• skillspec-migrateComplete a .agent.partial file by resolving TODO markers.
• skillspec-testExecute test blocks from a SkillSpec .agent file.
• skilluiExtract a complete design system from any website, local directory, or public GitHub repo using the skillui CL
• skillview-cliInventory and explore agent skills installed on the local machine via the `skillview` CLI. Use when asked to d
• skiloUse this skill when the user wants to share, install, inspect, publish, claim, or troubleshoot agent skills wi
• skim-mcpClean web reader for AI agents. Free remote read tier, optional x402 pay-per-call. No API keys.
• skip-level-plannerDesign your skip-level meeting strategy — who to meet, how often, what to ask, and what signals to watch for.
• skitsanos-checkRun focused or complete validation for IronCrew. Use when the user asks to check, validate, lint, test, audit,
• skrift-formsSkrift form system — Pydantic-backed forms with CSRF protection, template rendering, and hook integration.
• skrun-dev-code-reviewReview code for quality, bugs, security issues, and suggest improvements. Use when asked to review, audit, or
• skrun-dev-seo-auditAudit a website for SEO issues and track improvements over time. Use when analyzing website SEO performance.
• skulto-release-certCertify a skulto build for Homebrew prod release. Runs three passes — unit/lint/cross-compile, clean-slate CLI
• skybridge|
• skydoves-configuring-r8-for-composeUse this skill to configure R8 correctly for a Jetpack Compose application — full mode by default, `proguard-a
• skyglanceWhat's flying above you: live aircraft, identity, routes, and your own sighting history.
• skykickFleet-wide M365 backup assurance for SkyKick Cloud Backup - posture, stale snapshots, and coverage gaps no por
• skylight-mcpSkylight Calendar for Claude — family events, chores, and rewards.
• skyllSearch and retrieve agent skills at runtime. This skill should be used when the agent needs to find specialize
• skypilot-multi-cloud-orchestrationMulti-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training
• skyscraper-techniqueBuild high-quality backlinks systematically using Brian Dean's proven 3-step content marketing framework—find
• skywork-designGenerate or edit images via backend Skywork Image API. Use for any image creation, poster design, logo design,
• skywork-documentSTRONGLY RECOMMENDED for ANY task that could result in a document output. The Skywork Office Doc API is a powe
• skywork-excelSTRONGLY RECOMMENDED for ANY task involving Excel, spreadsheets, tables, data analysis, structured reports, or
• skywork-music-makerCreate professional music with Mureka AI API — songs, instrumentals, and lyrics from natural language descript
• skywork-ppt|
• skywork-searchSearch the web for real-time information using the Skywork web search API. Use this skill whenever the user ne
• slktx's semantic layer - a structured catalog of sources (tables/views), measures, joins, and segments expressed
• sl-captureHow to capture new reusable patterns into ktx's semantic layer - when a measure, segment, or join belongs in t
• sla-management>-
• sla-monitorCheck SLA compliance across open tickets and flag breaches or at-risk tickets
• slac-mcpMCP server exposing SLAC (Simple Logic & Arithmetic Compiler) as tools for LLM agents
• slackSend messages, read channels, search Slack via its Web API. Use when the user wants to post to a channel, read
• slack-apiDiscover, navigate, and call Slack Web API methods (the family.method endpoints at slack.com/api like chat.pos
• slack-assistantInteract with Slack workspaces for reading channels/messages, sending messages, adding reactions,
• slack-block-kitProactively apply when generating Slack API payloads with blocks, chat.postMessage calls with structured conte
• slack-botsSlash commands, interactivity payloads, and the three-second acknowledgement deadline that shapes the whole de
• slack-cliInteract with the official Slack CLI to create, run, deploy, and manage Slack apps, environments,
• slack-digestUse when generating a weekly Slack digest, summarizing channel activity, finding key discussions, or checking
• slack-docsSearch and read the official Slack platform documentation at docs.slack.dev. Use this skill to answer conceptu
• slack-draftDrafts a copy-paste Slack message in mrkdwn, conclusion first, AI tells stripped. Pass --tech for a peer who r
• slack-gif-creatorKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools
• slack-message-checkCheck Slack for important messages and activity. Use during daily planning or when user asks about Slack updat
• slack-messagingSlack channel and thread messaging skill with context-aware session management. Reads messages, sends replies,
• slack-mrkdwnProactively apply when generating any Slack text content, message text fields, Block Kit text objects, standar
• slack-searchFind messages, files, channels, and people across Slack with the search MCP tools. Use whenever locating conve
• slack-slack-integrationA reusable workflow for using Claude in Slack (and Slack as a connector) to draft replies, summarize threads,
• slack-to-code-session-routingGuidance for delegating coding tasks from Slack to Claude Code sessions, including setup, when it works best,
• slack-ui-skillsSlack's UI design system. Use when building interfaces inspired by Slack's aesthetic - light mode, Inter font,
• slack-workspace-mcp-serverMCP server for Slack workspace integration
• slamUse when building, tuning, or debugging SLAM and localization on mobile robots — occupancy grid mapping, AMCL
• slammedSustainable workload signaling. Use when colleagues need visibility into your capacity, to set expectations an
• slanchaai-pdfMerge several PDF files and add page numbers.
• slanchaai-xlsxAnalyze this workbook and build a pivot table.
• slang-workflowsProvable, declarative multi-agent workflows for Claude Code (typed .slang, non-LLM executor).
• slash-command-factoryGenerate custom Claude Code slash commands through intelligent 5-7 question flow. Creates powerful commands fo
• slash-commandsUse when creating reusable slash commands for an agent. Covers when a command beats a skill, argument handling
• slashesShow all available slash commands with usage examples. Use when user asks about available commands.
• slbSimultaneous Launch Button - Two-person rule for destructive commands in multi-agent workflows. Risk-tiered cl
• sleekModern minimalist aesthetic with clean lines, intentional color palette, subtle interactions, and consistent s
• sleek-design-mobile-appsUse when the user wants to design a mobile app, create screens, build UI, or interact with their Sleek project
• sleep-analyzerComprehensive sleep tracking and optimization skill. Analyzes sleep duration, quality, efficiency, and pattern
• sleuthUse when conducting structured investigative research, OSINT analysis, due diligence, or intelligence-grade in
• slice>
• slice-buildThree composable Claude Code skills that turn a one-line feature description into a production-quality vertica
• slice-exitUse when the builder believes the slice is green, to produce the slice-exit report that is the definition of g
• slice-resume>
• slice-video-framesExtract ordered still-image frames from local video files with FFmpeg, using a fixed FPS, an exact frame count
• slicing-code-contextSelects bounded, graph-informed source slices with Trailmark and delegates focused code analysis or patch-prop
• slicing-into-tracer-bullets>-
• slide-architectBuild professional PowerPoint presentations and slide decks from scratch. Use when creating, structuring, or i
• slide-deckWhen you want to draft, update, convert, or export a slide deck for a React/Next.js slide system (${SLIDE_DECK
• slide-deck-generatorGenerate a real PowerPoint .pptx deck from a Markdown outline. Picks slide layouts (title / content / closing)
• slide-designVisual design system for creating high-quality presentation slides (HTML, PPTX, or PDF). Use when designing pi
• slide-generation>
• slide-systemSistema de diapositivas brand-agnostic — 10 plantillas + 19 smart diagrams en HTML/CSS. Cuando el usuario pida
• slide-tighteningRubric for sharpening the active slide — parallelism, bullet count, length, title strength, notes-vs-bullets s
• slide-wrightCreate beautiful, animated web presentations from a topic, rough notes, or an outline, and edit decks afterwar
• slide-writer把想法、大纲、文档或草稿变成结构清晰、设计精良的企业级 HTML 演示文稿。
• slidedownConvert Markdown files into beautiful, professionally-designed PowerPoint presentations (.pptx) that open nati
• slideforge-mcpDeterministic, fully editable PowerPoint from typed slide intents. 200+ layouts, brand templates.
• slidesGenerate Marp-compatible slide decks from structured JSON schema. Converts context into presentations for tech
• slides-to-videoUse when the user wants to turn prepared slides (PNG, PDF, or PPTX) into a narrated, captioned video in a chos
• slidesage>-
• slidevCreate and present web-based slidedecks for developers using Slidev with Markdown, Vue components, code highli
• slidewrightCreate stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when th
• slim-claude-mdSlim or restructure an oversized CLAUDE.md into path-scoped .claude/rules/ files, verifying nothing was lost.
• slimctxReversible context compression for AI agents: cut token usage up to 94%, originals retrievable
• slimdex-mcpNarrow code retrieval for agents: outlines, symbol context, dep graph, persistent memory.
• slime-rl-trainingProvides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GL
• slo[UDS] 引導 SLI 選取、SLO 設定和 Error Budget 管理
• slo-check>
• slo-definitionCovers turning "the service should be reliable" into a falsifiable number — SLIs that reflect real user experi
• slopRemove AI-generated code slop from git diffs to maintain code quality
• slop-checkAudit drafts for AI-slop patterns before publishing. Use when checking, scoring, rewriting, or humanizing cont
• slop-eval-cliWraps the slop-eval CLI as a single generic MCP tool for genericness scoring of AI UI output.
• slop-mop>-
• slop-pattern-auditorFlag formulaic AI-writing patterns in any text artifact without any engine or launcher installed — negative pa
• slope-mcpProprietary B2B creator-velocity data: ranked board, live breakouts, and audience-growth curves.
• slopmop>-
• slopsec>-
• slopus/happyMobile and Web client for Codex and Claude Code, with realtime voice, encryption and fully featured
• slot-machineUse when a well-specified task has meaningful design choices and you want to maximize quality by comparing mul
• slugTODO — one-paragraph description of what this skill does, when to use it, and what it produces. Shown in the d
• slugifyConvert a title into a URL slug. Use when asked to slugify a title or make a URL slug.
• slurm-job-array-starterA framework for discovering, compiling, and validating reusable skills for scientific agents.
• slurm-job-debug-templateUse this skill to render, submit, and inspect a minimal Slurm smoke job before submitting heavier workloads on
• slurm-job-script-generator>
• slurm-monitoring-accounting-starterA framework for discovering, compiling, and validating reusable skills for scientific agents.
• small-batch-commits-merged-oftenFavour small, short-lived feature branches that land on main quickly — easier to review, less conflict-prone,
• small-rna-seqWorkflow for small RNA and miRNA preprocessing, quantification, differential analysis, and target-oriented int
• smallnest-prdGenerate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new
• smallnest-refactorExpert code refactoring based on Martin Fowler's catalog — improve maintainability without changing behavior.
• smallnest-to-issuesDecompose a PRD and/or SPEC into implementable Issues and create them in your chosen platform (GitHub or Local
• smalltalk-commenterGenerates CRC-style class comments for Smalltalk classes. Use after creating or modifying Tonel files to add o
• smalltalk-debuggerSystematic debugging guide for Smalltalk (Pharo/Squeak) development. Provides expertise in error diagnosis (Me
• smalltalk-developerComprehensive Smalltalk (Pharo/Squeak) development workflow guide with AI-driven Tonel editing. Provides exper
• smalltalk-implementation-finderMethod implementation finder and analyzer for Smalltalk (Pharo/Squeak). Provides expertise in discovering impl
• smalltalk-usage-finderClass and method usage analyzer for Smalltalk (Pharo/Squeak). Provides expertise in understanding class respon
• smart-categorize>
• smart-commitSmart batch commit. Analyzes uncommitted changes, groups by cohesion, generates commit messages matching proje
• smart-connections-mcpLocal semantic search over Obsidian vaults via Smart Connections embeddings. Multi-vault, private.
• smart-contract-auditorAutomated smart contract security auditor using source code analysis, function signature intelligence, and mul
• smart-contract-fuzz-testerDynamic testing framework that generates random inputs to discover vulnerabilities and invariant violations in
• smart-contract-testingSmart contract testing with Hardhat, Foundry, and Brownie including unit tests, gas optimization, reentrancy c
• smart-contracts-move
• smart-exploreToken-efficient code exploration — view file structure, search symbols, and read specific implementations with
• smart-git-commit>
• smart-illustrator智能配图与 PPT 信息图生成器。支持三种模式：(1) 文章配图模式 - 分析文章内容，生成插图；(2) PPT/Slides 模式 - 生成批量信息图；(3) Cover 模式 - 生成封面图。所有模式默认生成图片，`
• smart-learn独立学习技能，基于费曼学习法的五步闭环。触发方式：输入 /smart-learn 主题，或说"教我XX"、"帮我系统学习XX"。每学完一步自动同步更新 Word 文档 + Mermaid 思维导图。
• smart-orchestrator>
• smart-ralphThis skill should be used when the user asks about "ralph arguments", "quick mode", "commit spec", "max iterat
• smart-readingBehavioral protocol for reading files or command output of unknown size. Loaded automatically for all file rea
• smart-rebaseSmart partial rebase for squash-merge repositories. Auto-detect which commits to keep/drop when base branch wa
• smart-reviewContext-aware code review that adapts its strategy based on what changed
• smart-search基于 opencli 命令的智能搜索路由器。当用户想要使用 OpenCLI、CLI 或 API 搜索、查询、查找或研究信息时，尤其是涉及指定网站、社交媒体、技术资料、新闻、购物、旅游、求职、金融或中文内容时，务必使用此
• smart-sourcingSelects optimal sources for tool calls, balancing accuracy with token cost. Use before research tasks or when
• smart-split>
• smart-summarizeChoose the best summarization method based on content type and automatically produce a high-quality summary. U
• smart-triggerDecides when the CI/CD pipeline should run. Detects push, PR, tag, ignores commits without impact, and priorit
• smart-video-editor把多段原始素材剪成一条成片——先用视觉模型看懂每段画面拍了什么、哪几秒可用，再决定取舍、顺序、时长、调色和 BGM，最后用 ffmpeg 渲染。适用于"我给你几段视频，帮我剪一条小红书/朋友圈/vlog"这类需求。当用户
• smart-web-fetchFetch web content efficiently by checking llms.txt first, then Cloudflare markdown endpoints, then falling bac
• smart-web-mcpsmartfetch direct-URL fetch, smartsearch web discovery, smartcrawl sites, and docs export MCP.
• smartcli-toolkitLet agents drive vim, htop, lazygit: send keys, wait on screen state, read the rendered cell grid.
• smartflow-verify-mcpIndependent x402 observatory on Base. Sealed decomposition + endpoint audits paid over x402 itself.
• smartrent-mcpControl SmartRent smart home devices (locks, thermostat, switches, sensors) via Claude
• smartstore-listing-optimization스마트스토어 등 온라인 쇼핑몰 상품등록(상품정보·이미지·상세페이지·가격)을 검색노출과 구매전환 관점에서 점검하고, 카테고리별 표시·광고 규제 리스크를 별도로 짚는다. "이 상품 등록 봐줘", "상세
• smb-onboard>