Skill rankings
Recently updated AI agent skills
High-signal skills that have recent GitHub activity and are worth checking for actively maintained workflows.
Shown: 30 · Candidates: 480
Compare top 4- 01
openagentskill-registry
Discover, compare, audit, and safely install reusable AI Agent Skills with OpenAgentSkill. Use whenever an agent needs a capability it does not already have, must compare Skill alternatives, or needs evidence before installing third-party instructions.
@Leon-DrqOther358Review before useView detailsRepository push
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 51/100
- Quality
- 67/100
- Freshness
- 100/100
- Agent evidence
- 0/100
- Evidence confidence
- 0/100
- Install readiness
- 90/100
- 02
find-skills
Find, compare, audit, and safely install reusable AI agent skills from OpenAgentSkill. Use when a user asks for a skill, plugin, reusable agent workflow, or the best tool for a task.
@Leon-DrqOther358Review before useView detailsRepository push
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 51/100
- Quality
- 61/100
- Freshness
- 100/100
- Agent evidence
- 0/100
- Evidence confidence
- 0/100
- Install readiness
- 90/100
- 03
babysit-pr
Watch a PR on a self-paced timer and keep it mergeable — answer review feedback with the respond-to-review skill, fix failing CI, and resolve merge conflicts — until it is reviewed clean, green, and conflict-free. Use when the user says "babysit this PR".
@rome-osOther748Review before useView detailsRepository push
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 58/100
- Quality
- 70/100
- Freshness
- 100/100
- Agent evidence
- 0/100
- Evidence confidence
- 0/100
- Install readiness
- 90/100
- 04
krillinai-cli
Use when an agent needs to build or operate the embedded KrillinAI CLI, choose a supported command, or interpret its JSON, manifest, subtitle, dubbing, render, cover, speech, and voice outputs.
@krillinaiCoding12,682Review before useView detailsRepository push
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 82/100
- Quality
- 77/100
- Freshness
- 100/100
- Agent evidence
- 0/100
- Evidence confidence
- 0/100
- Install readiness
- 90/100
- 05
krillinai-cover
Use when generating a cover image with the KrillinAI CLI from a complete image prompt, including validating image-provider configuration and inspecting the generated image and saved prompt.
@krillinaiCoding12,682Review before useView detailsRepository push
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 82/100
- Quality
- 77/100
- Freshness
- 100/100
- Agent evidence
- 0/100
- Evidence confidence
- 0/100
- Install readiness
- 90/100
- 06
krillinai-pipeline
Use when validating or documenting a multi-stage KrillinAI CLI output plan; the current pipeline command supports dry-run planning only, not end-to-end execution.
@krillinaiCoding12,682Review before useView detailsRepository push
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 82/100
- Quality
- 77/100
- Freshness
- 100/100
- Agent evidence
- 0/100
- Evidence confidence
- 0/100
- Install readiness
- 90/100
- 07
krillinai-render-horizontal
Use when rendering landscape videos with KrillinAI CLI, including original video plus bilingual subtitles or dubbed video plus target-language subtitles.
@krillinaiVideo12,682Review before useView detailsRepository push
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 82/100
- Quality
- 77/100
- Freshness
- 100/100
- Agent evidence
- 0/100
- Evidence confidence
- 0/100
- Install readiness
- 90/100
- 08
krillinai-render-vertical
Use when rendering portrait videos with KrillinAI CLI, including converting source video to vertical format, adding short bilingual subtitles, rendering dubbed vertical videos, and checking vertical subtitle readability.
@krillinaiVideo12,682Review before useView detailsRepository push
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 82/100
- Quality
- 77/100
- Freshness
- 100/100
- Agent evidence
- 0/100
- Evidence confidence
- 0/100
- Install readiness
- 90/100
- 09
krillinai-subtitle
Use when generating subtitles with KrillinAI CLI from a YouTube link, Bilibili/local video, or existing media, including platform caption download, Whisper fallback, translation, bilingual SRT, and short vertical subtitle output.
@krillinaiVideo12,682Review before useView detailsRepository push
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 82/100
- Quality
- 77/100
- Freshness
- 100/100
- Agent evidence
- 0/100
- Evidence confidence
- 0/100
- Install readiness
- 90/100
- 10
krillinai-tts
Use when generating target-language dubbing with KrillinAI CLI from SRT subtitles, including TTS audio creation and optional dubbed video generation.
@krillinaiVideo12,682Review before useView detailsRepository push
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 82/100
- Quality
- 77/100
- Freshness
- 100/100
- Agent evidence
- 0/100
- Evidence confidence
- 0/100
- Install readiness
- 90/100
- 11
opencreator-runtime
OpenCreator 内部 Creator Agent 的稳定运行规则，仅由应用自动安装和激活。
@krillinaiOther12,682Review before useView detailsRepository push
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 82/100
- Quality
- 77/100
- Freshness
- 100/100
- Agent evidence
- 0/100
- Evidence confidence
- 0/100
- Install readiness
- 90/100
- 12
subagent-task-orchestrator
Decomposition playbook and anti-temptation rules for an orchestrator agent that routes work through the Surogates subagent task layer. Pair this skill with an AgentDef whose tool filter strips the implementation tools (terminal, file, web, code) — that's how 'don't do the work yourself' is enforced structurally, not just behaviorally.
@invergent-aiCoding28Review before useView detailsRepository push
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 29/100
- Quality
- 56/100
- Freshness
- 100/100
- Agent evidence
- 0/100
- Evidence confidence
- 0/100
- Install readiness
- 90/100
- 13
agent-kotlin-expert
Specialist subagent: Kotlin Multiplatform, Compose Multiplatform, coroutines, Ktor, and JVM ecosystem specialist. Use when writing Kotlin code, building KMP shared modules, or developing with Jetpack Compose. Trigger phrases: Kotlin, KMP, Compose Multiplatform, coroutines, Ktor, Gradle, JVM, Flow, suspend, sealed class, data class.
@travisjneumanCoding100Review before useView detailsRepository push
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 40/100
- Quality
- 61/100
- Freshness
- 100/100
- Agent evidence
- 0/100
- Evidence confidence
- 0/100
- Install readiness
- 90/100
- 14
agent-graphql-architect
Specialist subagent: Expert GraphQL architect for API design, schema development, and performance optimization
@travisjneumanDesign100Review before useView detailsRepository push
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 40/100
- Quality
- 55/100
- Freshness
- 100/100
- Agent evidence
- 0/100
- Evidence confidence
- 0/100
- Install readiness
- 90/100
- 15
agent-i18n-specialist
Specialist subagent: Expert internationalization specialist for multi-language support and localization
@travisjneumanOther100Review before useView detailsRepository push
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 40/100
- Quality
- 55/100
- Freshness
- 100/100
- Agent evidence
- 0/100
- Evidence confidence
- 0/100
- Install readiness
- 90/100
- 16
agent-macos-developer
Specialist subagent: Expert macOS native developer for AppKit, Catalyst, and macOS-specific features
@travisjneumanCoding100Review before useView detailsRepository push
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 40/100
- Quality
- 55/100
- Freshness
- 100/100
- Agent evidence
- 0/100
- Evidence confidence
- 0/100
- Install readiness
- 90/100
- 17
agent-microservices-architect
Specialist subagent: Expert microservices architect for distributed system design, service decomposition, and resilience patterns
@travisjneumanDesign100Review before useView detailsRepository push
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 40/100
- Quality
- 55/100
- Freshness
- 100/100
- Agent evidence
- 0/100
- Evidence confidence
- 0/100
- Install readiness
- 90/100
- 18
paywalls
When the user wants to create or optimize in-app paywalls, upgrade screens, upsell modals, or feature gates. Also use when the user mentions "paywall," "upgrade screen," "upgrade modal," "upsell," "feature gate," "convert free to paid," "freemium conversion," "trial expiration screen," "limit reached screen," "plan upgrade prompt," "in-app pricing," "free users won't upgrade," "trial to paid conversion," or "how do I get users to pay." Use this for any in-product moment where you're asking users to upgrade. Distinct from public pricing pages (see cro) — this focuses on in-product upgrade moments where the user has already experienced value. For pricing decisions, see pricing.
@coreyhaines31Automation54,079Review before useView detailsRepository push
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 95/100
- Quality
- 92/100
- Freshness
- 100/100
- Agent evidence
- 0/100
- Evidence confidence
- 0/100
- Install readiness
- 90/100
- 19
marketing-psychology
When the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'mental models,' 'cognitive bias,' 'persuasion,' 'behavioral science,' 'why people buy,' 'decision-making,' 'consumer behavior,' 'anchoring,' 'social proof,' 'scarcity,' 'loss aversion,' 'framing,' or 'nudge.' Use this whenever someone wants to understand or leverage how people think and make decisions in a marketing context. For applying psychology to specific pages, see cro; for pricing tactics, see pricing; for copy framing, see copywriting.
@coreyhaines31Business54,079Review before useView detailsRepository push
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 95/100
- Quality
- 92/100
- Freshness
- 100/100
- Agent evidence
- 0/100
- Evidence confidence
- 0/100
- Install readiness
- 90/100
- 20
Market Environment Analysis
Create a global market conditions report spanning equities, rates, FX, commodities, risk appetite, and sector rotation.
@tradermontyFinance2,981Review before useView detailsRepository push
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 70/100
- Quality
- 86/100
- Freshness
- 99/100
- Agent evidence
- 0/100
- Evidence confidence
- 0/100
- Install readiness
- 90/100
- 21
grill-me
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
@youdotcom-ossCreative87Review before useView detailsRepository push
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 39/100
- Quality
- 59/100
- Freshness
- 98/100
- Agent evidence
- 0/100
- Evidence confidence
- 0/100
- Install readiness
- 90/100
- 22
Taste Skill: Anti-Slop Frontend
Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.
@LeonxlnxDesign94,461Review before useView detailsRepository push
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 100/100
- Quality
- 100/100
- Freshness
- 97/100
- Agent evidence
- 0/100
- Evidence confidence
- 100/100
- Install readiness
- 100/100
- 23
Frontend Design
Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
@anthropicsDesign180,366Review before useView detailsRepository push
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 100/100
- Quality
- 100/100
- Freshness
- 97/100
- Agent evidence
- 0/100
- Evidence confidence
- 94/100
- Install readiness
- 100/100
- 24
Webapp Testing
Use Playwright to interact with and test local web applications, capture screenshots, debug UI behavior, and inspect browser logs.
@anthropicsBrowser Automation180,366Review before useView detailsRepository push
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 100/100
- Quality
- 100/100
- Freshness
- 97/100
- Agent evidence
- 0/100
- Evidence confidence
- 69/100
- Install readiness
- 100/100
- 25
Canvas Design
Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.
@anthropicsDesign180,366Review before useView detailsRepository push
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 100/100
- Quality
- 100/100
- Freshness
- 97/100
- Agent evidence
- 0/100
- Evidence confidence
- 85/100
- Install readiness
- 100/100
- 26
Anthropic Brand Guidelines
Apply Anthropic official brand colors, typography, and visual standards to appropriate Anthropic-related artifacts.
@anthropicsDesign180,366Review before useView detailsRepository push
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 100/100
- Quality
- 100/100
- Freshness
- 97/100
- Agent evidence
- 0/100
- Evidence confidence
- 44/100
- Install readiness
- 100/100
- 27
gpu-clean-conversion
Convert a PyTorch or Hugging Face model into a LiteRT model that runs fully on the GPU via the CompiledModel API with verified-correct output, and lay it out as a model recipe. Use when converting a new model, or when a converted model is rejected by the GPU, falls back to CPU, or returns wrong numbers on device.
@google-ai-edgeOther459Review before useView detailsRepository push
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 53/100
- Quality
- 68/100
- Freshness
- 97/100
- Agent evidence
- 0/100
- Evidence confidence
- 0/100
- Install readiness
- 90/100
- 28
litert-lm
Creates an Android app that runs an open text LLM on the device, on the CPU or the GPU, with the LiteRT-LM Kotlin API. Use this skill to build a new chat, summarization or extraction app with a .litertlm model from Hugging Face litert-community (Gemma, Qwen, Llama, Phi) - the dependency and manifest entries, getting the model file onto the device, engine initialization, a streamed multi-turn conversation, the ViewModel and screen.
@google-ai-edgeAi Knowledge459Review before useView detailsRepository push
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 53/100
- Quality
- 68/100
- Freshness
- 97/100
- Agent evidence
- 0/100
- Evidence confidence
- 0/100
- Install readiness
- 90/100
- 29
litert-runtime
Creates an Android app that runs a .tflite model on the CPU or the GPU with the LiteRT CompiledModel API in Kotlin. Use this skill to build a new app around a vision, audio or embedding model, or to add on-device inference to an existing app - the dependency, where the model file goes, the inference class, the ViewModel and screen, and checking the output on a device.
@google-ai-edgeVideo459Review before useView detailsRepository push
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 53/100
- Quality
- 68/100
- Freshness
- 97/100
- Agent evidence
- 0/100
- Evidence confidence
- 0/100
- Install readiness
- 90/100
- 30
accuracy-safe-quantization
Shrink a converted LiteRT model with ai-edge-quantizer (fp16 / int8 / int4) without losing accuracy, verifying parity against the float source after every step. Use when choosing a quantization recipe for a new model, when a quantized model fails to load, degrades on a task benchmark, or degenerates over long generations, or when deciding between dynamic-range, weight-only, and blockwise variants.
@google-ai-edgeOther459Review before useView detailsRepository push
Ranking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 53/100
- Quality
- 68/100
- Freshness
- 97/100
- Agent evidence
- 0/100
- Evidence confidence
- 0/100
- Install readiness
- 90/100
A shortlist from up to 480 directory candidates, not the entire registry. Stars belong to repositories. Signals are not safety guarantees or runtime verification.
How this list works
Ordered by recorded repository activity. A registry update is used when a push date was not recorded; the row identifies which date is shown.
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
30-day snapshot data