Skills leaderboard

Public skills ranked by weight of evidence — benchmark lift, live-eval pass rate, AI-rated quality and adoption. The registry is for finding skills you need; the leaderboard is for finding what has evidence behind it.

Where the evidence comes from: benchmark lift is a with-vs-without A/B run you can inspect. The live-eval and adoption signals are generated today by DecimalAI’s own automated agent fleet exercising these skills in production — real runs, really evaluated, but not yet independent third-party usage.

CategoryTop 50 by SkillScore · rolling 30 days

#	Skill	SkillScore	Lift	Turns Δ	Tokens Δ	Installs
#1	Ecnu Icalk/中文模板语言重表达与变量保留AI/ML ecnu-icalk/中文模板语言重表达与变量保留对包含代码变量（{{}}）的中文任务模板进行改写，生成6组表达多样但意图不变的生产模板，严格保留变量原样。	100	+88%	0%	+39%	200
#2	leemysw/ Feishu DocxDocumentation leemysw/feishu-docx Export, write, and manage Feishu/Lark cloud documents. Supports docx, sheets, bitable, wiki, WeChat article import/export, drive management, and browser-based export for public or browser-readable docs. Use this skill when you need to read, analyze, write, or manage content in a Feishu knowledge base.	99	+87%	0%	+57%	188
#3	bilal140202/ Google Antigravity SDKAgent Tooling bilal140202/google-antigravity-sdk Design, implement, and debug autonomous AI agents and multi-agent systems using the Google Antigravity (AGY) SDK. ACTIVATE this skill when the user wants to create, configure, or orchestrate Google Antigravity agents.	100	+86%	0%	+29%	221
#4	bilal140202/ Google Antigravity SDK RustAgent Tooling bilal140202/google-antigravity-sdk-rust Design, implement, and debug autonomous AI agents and multi-agent systems in Rust using the Google Antigravity (AGY) Rust SDK. ACTIVATE this skill when the user wants to create, configure, or orchestrate Google Antigravity agents in Rust.	99	+86%	0%	+54%	56
#5	cloudai-x/ Web Design GuidelinesCode Review cloudai-x/web-design-guidelines Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", "check my site against best practices", or "web interface guidelines".	86	+86%	0%	+86%	12
#6	coderwanfeng/ File Name Add PostfixProductivity coderwanfeng/file_name_add_postfix 给文件名批量增加指定后缀。当用户提到加后缀、文件名后缀、批量加后缀时使用。	100	+86%	0%	+5%	62
#7	ax-llm/ Ax Python AgentAgent Tooling ax-llm/ax-python-agent Use when writing Python code with `axllm` for agents, child delegation, tools, MCP, citations, persistent playbook learning, stage instructions, runtime state, final typed responses, and direct-respond executor skipping.	100	+82%	0%	-25%	99
#8	foryourhealth111-pixel/ Evals ContextAI/ML foryourhealth111-pixel/evals-context Provides context about the Roo Code evals system structure in this monorepo. Use when tasks mention "evals", "evaluation", "eval runs", "eval exercises", or working with the evals infrastructure. Helps distinguish between the evals execution system (packages/evals, apps/web-evals) and the public website evals display page (apps/web-roo-code/src/app/evals).	99	+82%	0%	+94%	137
#9	rlaope/ Omh Content OperatorMarketing rlaope/omh-content-operator [omh] Hermes content operator workflow: scope publish-ready writing, rewriting, summarization, translation, release-note, newsletter, customer-copy, social-copy, README-copy, and email-draft work with audience, tone, style, source, review, and hallucination gates. Use when the user says: content-operator, content operator, content workflow, writing workflow, publish-ready writing, publish ready writing, release notes, release note draft.	96	+82%	0%	+124%	38
#10	webiny/ Webiny Admin Configs CatalogFrontend webiny/webiny-admin-configs-catalog admin/configs — 1 abstractions.	93	+82%	0%	-50%	19
#11	foryourhealth111-pixel/ EdgartoolsFinance foryourhealth111-pixel/edgartools Python library for accessing, analyzing, and extracting data from SEC EDGAR filings. Use when working with SEC filings, financial statements (income statement, balance sheet, cash flow), XBRL financial data, insider trading (Form 4), institutional holdings (13F), company financials, annual/quarterly reports (10-K, 10-Q), proxy statements (DEF 14A), 8-K current events, company screening by ticker/CIK/industry, multi-period financial analysis, or any SEC regulatory filings.	95	+82%	0%	+22%	30
#12	aaron-he-zhu/ Social Measurement LoopMarketing aaron-he-zhu/social-measurement-loop Use when the user asks to "run the weekly social readout", "which denominator does our engagement rate use", or "which posts won this week and what changes next cycle"; produces the organic-social metric dictionary (every rate names its denominator — ERR engagement-by-reach vs ERI by-impressions vs ER-by-follower — locked across periods), median-not-mean per-post rollups with organic and boosted separated, EMV as labeled exec-translation only (never inside any score), an attributed CHAOSS/Orbit-	92	+82%	0%	+100%	26
#13	bartsoj/ Page Spec MDFrontend bartsoj/PAGE_SPEC.md Produce a deep, per-page composition specification for a single web page — page shell, region layout, section composition, per-component layout detail, action inventory and placement, state-specific layouts, responsive behavior, page-specific motion, and accessibility notes — extending the lightweight per-page blueprint that already lives in WEB_IA.md by citing DESIGN.md tokens, components, and layout templates without redefining them. Use when asked to create a PAGE_SPEC.md for a page, write a	81	+82%	0%	+330%	7
#14	sickn33/ Longbridge FundamentalsFinance sickn33/longbridge-fundamentals Financial statements, business segments, dividends, valuation multiples (PE/PB/PS), industry comparison, operating data, corporate actions, company and executive profiles, cross-stock comparison, and valuation ranking via Longbridge. Also: DCF models, value investing screens (low...	95	+79%	0%	+116%	17
#15	diegosouzapw/ Omni Combos RoutingAI/ML diegosouzapw/omni-combos-routing Create and manage routing combos with 14 strategies (priority, weighted, round-robin, Auto-combo, etc.). Configure fallback chains, test routing outcomes, and retrieve combo metrics.	100	+78%	0%	+278%	49
#16	pangzhenying2025/ Automotive TerraformDevOps pangzhenying2025/automotive-terraform Terraform infrastructure for multi-region vehicle cloud deployment. 19 configuration files.	95	+78%	0%	-2%	34
#17	didit-protocol/ Didit Kyc OnboardingLegal didit-protocol/didit-kyc-onboarding End-to-end KYC (Know Your Customer) identity verification for onboarding real users. Use when someone needs to perform KYC, onboard users with identity verification, verify a person's identity with ID scan and selfie, run a full KYC flow, create a verification session for a user, set up ID + liveness + face match verification, or implement user onboarding with document and biometric checks. Creates a KYC workflow, generates a verification URL, and retrieves the decision.	98	+77%	0%	+123%	0
#18	sickn33/ Markstream ReactFrontend sickn33/markstream-react Integrate the beta markstream-react renderer into React 18+ or Next.js with correct client/server entrypoints, CSS, streaming state, and component overrides.	99	+77%	0%	-27%	41
#19	tsinghua-fib-lab/ Easypaper Venue SelectionDocumentation tsinghua-fib-lab/easypaper-venue-selection Apply venue-specific constraints for EasyPaper generation.	97	+77%	0%	-40%	38
#20	leoyeai/ Active CampaignMarketing leoyeai/active-campaign ActiveCampaign API integration with managed OAuth. Marketing automation, CRM, contacts, deals, and email campaigns. Use this skill when users want to manage contacts, deals, tags, lists, automations, or campaigns in ActiveCampaign. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway). Requires network access and valid Maton API key.	87	+77%	0%	+282%	0
#21	wshobson/ Team Communication ProtocolsAgent Tooling wshobson/team-communication-protocols Structured messaging protocols for agent team communication including message type selection, plan approval, shutdown procedures, and anti-patterns to avoid. Use this skill when establishing communication norms for a newly spawned team, when deciding whether to send a direct message or a broadcast, when a team-lead needs to review and approve an implementer's plan before work begins, when orchestrating a graceful team shutdown after all tasks are complete, or when debugging why teammates are not	99	+77%	0%	+77%	19
#22	bankrbot/ Aeon Skill EvalsAgent Tooling bankrbot/aeon-skill-evals Validate the output of any installed skill against an assertion manifest — word counts, required patterns, forbidden phrases, required sections, source citation. Detects regressions by diffing vs prior runs (NEW_FAIL / NEW_PASS / CHRONIC / STABLE_FAIL). Bootstrap mode generates a starter manifest from a skill's recent successful runs so manifests aren't written speculatively. Triggers: "evaluate this skill's output", "check skill X for regressions", "bootstrap evals for Y", "did this skill outpu	98	+77%	0%	-29%	29
#23	fzyzcjy/ Frb Code GenerationCoding fzyzcjy/frb-code-generation Use when modifying Rust API, codegen, or example code in flutter_rust_bridge to determine which generation commands to run	100	+77%	0%	+3%	18
#24	cowork-os/ Apple RemindersProductivity cowork-os/apple-reminders Manage Apple Reminders via the `remindctl` CLI on macOS (list, add, edit, complete, delete). Supports lists, date filters, and JSON/plain output.	84	+77%	0%	-37%	0
#25	bankrbot/ Versa DeployFinance bankrbot/versa-deploy Deploy, manage, or withdraw from an AI agent vault on Versa — the onchain adversarial AI arena on Base. Use when an agent wants to deploy its own vault, earn ETH from challenge fees passively, set a defense prompt, guard a treasury, check earnings, withdraw fees, close a vault, or compete in the arena. Trigger phrases: deploy on versa, create a vault, earn ETH passively, set up my agent, launch my vault, I want to play defense, how does versa work, check my earnings, withdraw my fees, how much h	89	+77%	0%	+9%	10
#26	matlab/ Matlab Find Pi AssetsData matlab/matlab-find-pi-assets Find and query PI assets using MATLAB's Industrial Communication Toolbox. Two paths: (1) direct PI tag lookup via piclient + tags when user provides a tag name or description (R2022a+), (2) Asset Framework navigation via afclient when user needs element/attribute hierarchy (R2026a+). Use when working with PI AF servers, PI Data Archive tags, asset hierarchies, element templates, attribute lookup, or historical data from OSIsoft PI systems.	90	+77%	0%	+217%	10
#27	nvidia/ Tao Train Action RecognitionAI/ML nvidia/tao-train-action-recognition Action recognition from video sequences. Supports RGB, optical flow, and joint (multi-stream) input types for classifying temporal actions in video clips. Use when training, evaluating, exporting, or running inference on a TAO action-recognition model. Trigger phrases include "train action recognition", "video action classification", "RGB + optical flow action model", "TAO ActionRecognition".	83	+77%	0%	+56%	10
#28	camunda/ CI Security ComplianceSecurity camunda/ci-security-compliance Enforces GitHub Actions security and compliance for this monorepo. Use when adding third-party actions, handling secrets, defining permissions, and reviewing CI security trade-offs.	97	+76%	0%	-18%	8
#29	leoyeai/ Cloudcc Openapi WithobjectSales & Support leoyeai/cloudcc-openapi-withobject CloudCC OpenAPI 调用技能 - 提供完整的 REST API 接口调用能力，支持对象/字段元数据查询	95	+75%	0%	+305%	11
#30	mohitagw15856/ Privacy Policy DrafterLegal mohitagw15856/privacy-policy-drafter Draft a clear, plain-language privacy policy tailored to what a product actually collects and does with data. Use when asked to write a privacy policy, draft a data-protection notice, or create a GDPR/CCPA-aware privacy statement. Produces a structured policy covering data collected, purposes, legal bases, sharing, retention, user rights, and contact — written to be readable, not boilerplate. Not legal advice; have counsel review before publishing.	81	+74%	0%	+15%	0
#31	didit-protocol/ Didit Liveness DetectionSecurity didit-protocol/didit-liveness-detection Detects liveness from a single selfie image via the Didit standalone API. Use when checking if a person is physically present, detecting spoofing or presentation attacks, implementing anti-spoofing measures, or performing passive liveness verification. Returns liveness score, face quality, and luminance metrics. 99.9% accuracy.	99	+73%	0%	+81%	0
#32	mohitagw15856/ Content CalendarMarketing mohitagw15856/content-calendar Generate a structured content calendar for any brand, product, or creator. Use when asked for a content plan, editorial calendar, social media schedule, or weekly/monthly content strategy. Produces a calendar with topics, formats, channels, and copy hooks.	94	+73%	0%	+6%	17
#33	nexu-io/ Fx Gradient BlobDesign & Media nexu-io/fx-gradient-blob Soft drifting gradient blobs — a warm ambient glow. A bold, canvas-based effect from Open Design's html-ppt fx pack — for slides and launch videos. Guards prefers-reduced-motion (does not start). One per screen; on web use sparingly.	97	+73%	0%	-39%	56
#34	williamzujkowski/ Unit Testing Framework GeneratorTesting williamzujkowski/Unit Testing Framework Generator Generate unit test scaffolding and test suites for Jest, PyTest, Go testing, JUnit, RSpec with mocking, assertions, and coverage configuration	87	+73%	0%	+45%	31
#35	brycewang-stanford/ Acr Literature ReviewResearch brycewang-stanford/acr-literature-review Use when building or repairing the literature review for 《会计研究》 (Accounting Research) — entering the accounting research lineage (earnings quality, conservatism, audit quality, disclosure, value relevance) rather than piling recent Chinese empirical citations, and positioning the gap as an accounting contribution.	81	+73%	0%	+46%	22
#36	fzyzcjy/ Frb DockerDevOps fzyzcjy/frb-docker Use when working with flutter_rust_bridge Docker/devcontainer setup, local Docker usage, Apple Silicon containers, or publishing the dev Docker image	85	+73%	0%	-20%	11
#37	xberg-io/ Batch ExtractionDocumentation xberg-io/batch-extraction Use when extracting from many files at once with shared config, bounded parallelism, per-file overrides, and error recovery. Covers the `batch` command, `--file-configs`, `--max-concurrent`, and output layout.	91	+73%	0%	+13%	30
#38	nvidia/ Vss Setup Behavior AnalyticsDevOps nvidia/vss-setup-behavior-analytics Use to deploy the vss-behavior-analytics service standalone (entrypoint, config-source, optional calibration). Not for the full warehouse deploy.	93	+73%	0%	+51%	32
#39	openakita/ Happyhorse VideoDesign & Media openakita/happyhorse-video Bailian-powered unified creative studio — built-in Wan/Qwen image generation + HappyHorse 1.0 (text-to-video / image-to-video / reference-to-video / video-edit) + Wan 2.6/2.7 + 5 digital-human modes (photo speak / video relip / video reface / pose drive / avatar compose) + CosyVoice & Edge-TTS + storyboard long-video pipeline. Use when the user asks for AI image or video generation on Aliyun Bailian, keyframes, ecommerce images, multi-character video with audio sync, video editing/style transfer	93	+72%	0%	+39%	34
#40	xberg-io/ Mime Detection RoutingCoding xberg-io/mime-detection-routing MIME type detection and extractor routing in core/mime.rs and core/extractor/bytes.rs — the extension→EXT_TO_MIME→validate→registry→extractor flow, key detection functions, the 115 case-insensitive extension map, priority-based registry selection, wildcard MIME families, and how to add a new MIME type. Load when adding a format, wiring an extractor to a MIME type, or debugging why a file routes to the wrong (or no) extractor.	100	+71%	0%	+4%	29
#41	video-production-buddy/ MusicDesign & Media video-production-buddy/music Generate music using ElevenLabs Music API. Use when creating instrumental tracks, songs with lyrics, background music, jingles, or any AI-generated music composition. Supports prompt-based generation, composition plans for granular control, and detailed output with metadata.	100	+70%	0%	+18%	204
#42	bilal140202/ Interview MeProductivity bilal140202/interview-me Extracts what the user actually wants instead of what they think they should want. Achieves this through one-question-at-a-time interview until ~95% confidence about the underlying intent. Use when an ask is underspecified ("build me X" without "for whom" or "why now"), when the user explicitly invokes ("interview me", "grill me", "are we sure?", "stress-test my thinking"), or when you catch yourself silently filling in ambiguous requirements before any plan, spec, or code exists.	98	+70%	0%	+201%	19
#43	borghei/ Senior FrontendFrontend borghei/senior-frontend Frontend development for React, Next.js, TypeScript, and Tailwind CSS. Use when building React components, optimizing Next.js performance, analyzing bundle sizes, scaffolding projects, implementing accessibility, or reviewing frontend code.	79	+70%	0%	+28%	11
#44	docxology/ Infrastructure SearchResearch docxology/infrastructure-search Discovery utilities. Hosts three subpackages — `literature` for Paperclip-style multi-source academic search across arXiv, Crossref, local JSON corpora, and (opt-in) the Paperclip API, with deterministic JSON caching, a `LiteratureClient` aggregator, normalised `Paper` records, and a CLI; `exa` for Exa-backed general web search, content extraction, grounded answers, and find-similar via `ExaClient` (search/contents/answer/find_similar) and a CLI; and `deep_research` for provider-neutral long-run	94	+70%	0%	+72%	18
#45	gooseworks-ai/ Structured Scraping RiveterResearch gooseworks-ai/structured-scraping-riveter Web scraping with structured data extraction - define your output schema	86	+70%	0%	+88%	19
#46	bilal140202/ Open NotebookResearch bilal140202/open-notebook Self-hosted, open-source alternative to Google NotebookLM for AI-powered research and document analysis. Use when organizing research materials into notebooks, ingesting diverse content sources (PDFs, videos, audio, web pages, Office documents), generating AI-powered notes and summaries, creating multi-speaker podcasts from research, chatting with documents using context-aware AI, searching across materials with full-text and vector search, or running custom content transformations. Supports 16+	100	+68%	0%	+85%	21
#47	leoyeai/ Edict Multi Agent OrchestrationAgent Tooling leoyeai/edict-multi-agent-orchestration Install and use the Edict (三省六部) multi-agent orchestration system with 12 specialized AI agents, real-time kanban dashboard, and audit trails	96	+68%	0%	+272%	31
#48	nvidia/ Cuopt Routing API PythonCoding nvidia/cuopt-routing-api-python Vehicle routing (VRP, TSP, PDP) with cuOpt — Python API only. Use when the user is building or solving routing in Python.	89	+68%	0%	-3%	18
#49	video-production-buddy/ Grok MediaDesign & Media video-production-buddy/grok-media xAI Grok image and video generation guide covering authentication, endpoints, prompt structure, image editing, reference-image video, and async polling.	99	+68%	0%	+7%	23
#50	bilal140202/ X Twitter ScraperData bilal140202/x-twitter-scraper Use when the user needs X (Twitter) data through Xquik: tweet search, user lookup, follower export, media download, monitoring, webhooks, MCP, SDK setup, or confirmation-gated publishing workflows. Read-only by default, API-key only, no X login material, and every write, private read, monitor, webhook, or metered bulk job requires explicit approval.	79	+68%	0%	+138%	1

Loading leaderboard…

Skills leaderboard

Ready to supercharge your AI agents?

Skills leaderboard