Top Rated
Highest quality-scored skills across all categories
Showing 9,601–9,660 of 13,466 skills · Page 161 of 225
mukul975 / analyzing-ethereum-smart-contract-vulnerabilities
34.7kPerform static and symbolic analysis of Solidity smart contracts using
mukul975 / Create Fake Materials: Fake Website
34.7kImplement a phishing report button (Microsoft 365 built-in Report button
mukul975 / configuring-tls-1-3-for-secure-communications
34.7kConfigures TLS 1.3 (RFC 8446) on servers, covering cipher suite and
KKKKhazix / leader
21.5k把一句话的想法拆成 AI agent 能独立跑完的目标任务书。用户说「帮我给 agent 写个目标」「帮我详细拆一下这个目标」「写个任务书/brief 给 agent」「写个 goal 提示词」「让 agent 自己跑这个项目」「把活分给几个 agent 并行」时使用。先进代码库实测、必要时联网调研,再一次性提问(≤5 个),产出一份 ≤4000 字符、直接粘进 /goal 就能跑的任务书,含实测数字、白名单地界、防作弊验收和断点续跑。执行型与探索型(调研/选型/找方案)自动分流。
wanshuiyin / patent-novelty-check
17.7kAssess patent novelty and non-obviousness against prior art
AgriciDaniel / wiki-query
15.7kAnswer an explicitly vault-scoped question from an Obsidian wiki without changing it
uvwt / skill-installation
1.1k审查、安装、配置、验证、更新和移除 AgentDock Skill 时使用;负责来源校验、安全评估、环境配置、content digest、精确 skill_ref 与当前 managed 内容验收。
jnMetaCode / dispatching-parallel-agents
8.3k当面对 2 个以上可以独立进行、无共享状态或顺序依赖的任务时使用
jnMetaCode / executing-plans
8.3k当你要在当前会话里亲自担任实现者执行一份实现计划时使用——你的人类伙伴选择了内联执行,或者没有可用的子智能体工具
jnMetaCode / receiving-code-review
8.3k收到代码审查反馈后、实施建议之前使用,尤其当反馈不明确或技术上有疑问时——需要技术严谨性和验证,而非敷衍附和或盲目执行
jnMetaCode / writing-skills
8.3k当创建新技能、编辑现有技能或在部署前验证技能是否有效时使用
zenstory-ai / story
7.8k网络小说工具箱主入口。根据用户需求自动路由到对应 skill,并可启动本地 Dashboard。触发方式:/story、$story、/story dashboard、/网文、「我想写小说」「记住我的写作习惯」「打开工作台」「检查更新」。
Devin-AXIS / daytona-dev
7.1kDaytona development environment overview
tech-leads-club / confluence-assistant
7.1kExpert in Confluence operations using Atlassian MCP
internet-court / nla-fulfill
6.8kFulfill an existing NLA escrow and collect tokens
internet-court / dflow-phantom-connect
6.8kBuild Solana wallet-connected apps with Phantom Connect SDKs and DFlow spot trading
internet-court / jupiter-vrfd
6.8kUse when a user mentions Jupiter token verification, VRFD eligibility, paying 1000 JUP to verify a token, submitting a verification request, or updating metadata via the Jupiter express verification flow.
internet-court / okx-activity
6.8kRegister for the OKX.AI Trading Hackathon or explain its entry requirements and eligibility. Trigger on requests in any language to register, sign up, join, enter, or participate in the hackathon. Registers an existing Trading ASP; never creates one.
epoko77-ai / humanize-scan
6.1k한글 글에 AI 티가 얼마나 있는지 재고, 실제로 고치면 어떻게 되는지 표본으로 보여주는 정찰 스킬. 실측 판별력 상위 6개만 본다. 워크스페이스·진단·게이트·서브에이전트 없이 이 대화 안에서 끝낸다(파일 0개, 서브에이전트 0회). 손볼 게 많다고 나오면 전수 윤문은 humanize-korean(=/humanize)으로 넘긴다. 트리거 — "이 글 AI 같아?", "AI 티 있나 봐줘", "스캔해줘", "윤문 돌릴 값어치 있나", "AI 티 점수", "quick humanize", "/humanize-scan".
breaking-brake / next-qa-idea
5.4kRun one unattended IDEATION iteration of the quality-assurance loop — find the highest-value untested behavior in the codebase, judge it against the QA value bar, and file ONE locked `qa` issue specifying the test to write.
breaking-brake / next-task
5.4kRun one unattended IMPLEMENTATION iteration of the autonomous value-creation loop — steward any in-flight PR, fix interrupts (red CI / security / human bugs), or else build ONE queued `idea` issue on a branch off auto-dev and open a PR that squash-merges on green CI.
ThinkInAIXYZ / add-provider
6.4kAdd a DeepChat LLM provider through explicit reviewed source changes
ThinkInAIXYZ / computer-use
6.4kDrive native desktop apps through DeepChat's built-in Computer Use tools
oh-my-mermaid / omm-scan
2.3kScan codebase architecture and generate/update .omm/ documentation
cth9191 / animate
707Make a short procedural animation in any style — an explainer, a history, a little story — as a single-file canvas video with a synthesized score, rendered to MP4.
RandallLiuXin / fx-bundle
554Produce a standalone static Texture2D effect or one explicitly timed animated SpriteFrames effect.
RandallLiuXin / tileset
554Generate a fixed-profile terrain atlas and compile it into a native Godot TileSet. Use for reusable terrain libraries, never for designing a TileMap.
RandallLiuXin / gm-accept
554Present final results to the user for acceptance. Shows evaluation results, evaluator screenshots, and asks for confirmation. Explicit invocation only — use /gm-accept.
RandallLiuXin / mcp-driver
554Runtime debugging and live project inspection via godot-mcp. Use when headless tools cannot diagnose the problem: code compiles but runtime behavior is wrong, tests pass but the game does not work as expected, or you need to inspect live state (node tree, console output, rendering).
notque / content-engine
441Repurpose source assets into platform-native social content.
notque / video-editing
441Video editing pipeline: cut footage, assemble clips via FFmpeg and Remotion.
notque / cve-source-check
441Audit CVE/vulnerability source coverage for a technology stack. Maps each component (container, library, base image, runtime) to authoritative CVE feeds, flags gaps, and produces audit-ready reports. Generic: works for any service or stack.
notque / workflow-help
441Interactive guide to workflow system: agents, skills, routing, execution patterns.
notque / pr-workflow
441Pull request lifecycle: commit, codex review, sync, review, fix, status, cleanup, and PR mining
notque / process
441Process: retrospectives, session handoff, pair programming, subagent-driven development, condition-based waiting.
notque / research
441Research: structured investigation, fact-checking, explanation traces.
notque / security
441Security: review git changes for vulnerabilities, threat-model a system's attack surface, audit supply-chain risks.
giuseppe-trisciuoglio / spring-data-jpa
359Provides patterns to implement persistence layers with Spring Data JPA
giuseppe-trisciuoglio / unit-test-service-layer
359Provides patterns for unit testing service layer with Mockito. Creates isolated tests that mock repository calls, verify method invocations, test exception scenarios, and stub external API responses
giuseppe-trisciuoglio / unit-test-wiremock-rest-api
359Provides patterns for unit testing external REST APIs using WireMock. Stubs API responses, verifies request details, simulates failures (timeouts, 4xx/5xx errors), and validates HTTP client behavior without real network calls
giuseppe-trisciuoglio / drizzle-orm-patterns
359Provides comprehensive Drizzle ORM patterns for schema definition, CRUD operations, relations, queries, transactions, and migrations.
giuseppe-trisciuoglio / aws-cloudformation-elasticache
359Provides AWS CloudFormation patterns for ElastiCache Redis or Memcached infrastructure, including subnet groups, parameter groups, security controls, and cross-stack outputs
giuseppe-trisciuoglio / aws-cloudformation-iam
359Provides AWS CloudFormation patterns for IAM roles, policies, managed policies, permission boundaries, and trust relationships
giuseppe-trisciuoglio / aws-cloudformation-task-ecs-deploy-gh
359Provides patterns to deploy ECS tasks and services with GitHub Actions CI/CD
giuseppe-trisciuoglio / aws-sam-bootstrap
359Provides AWS SAM bootstrap patterns: generates `template.yaml` and `samconfig.toml` for new projects via `sam init`, creates SAM templates for existing Lambda/CloudFormation code migration, validates build/package/deploy workflows, and configures local testing with `sam local invoke`
foryourhealth111-pixel / iso-13485-certification
3.4kComprehensive toolkit for preparing ISO 13485 certification documentation for medical device Quality Management Systems
wshobson / helm-chart-scaffolding
39.9kDesign, organize, and manage Helm charts for templating and packaging Kubernetes applications with reusable configurations
wshobson / event-store-design
39.9kDesign and implement event stores for event-sourced systems
davepoon / gsc-seo-optimizer
3.7kAnalyze Google Search Console exports or authorized API data to prioritize page improvements. Use for traffic changes, page/query opportunities, indexing evidence, and deciding when to leave recently edited or weakly supported pages alone.
davepoon / linkedin-profile-refresh
3.7kRefresh a LinkedIn profile for a job search from the user''s own resume — pick and check the profile photo, crop it locally to LinkedIn, Slack and GitHub sizes, and write a headline and About section grounded in the resume, then check that LinkedIn, GitHub and the resume tell the same story
gooseworks-ai / caption-burn
1.2kBurned-in captions for a finished vertical video, three kinds. transcribe.py gets word timings from the video's own audio through the GooseWorks proxy (fal Whisper, bills the Ads agent, cents); captions.py burns one to three words at a time with Pillow + ffmpeg (no libass needed), either pinned to a…
gooseworks-ai / render-3d-character-explainer
1.2kAssemble an animated character-explainer video ad (any art style — Pixar-style 3D, claymation, anime, paper-cut, felt) (~77s, 9:16) built on an "N types of X" listicle spine — a recurring human protagonist plus a locked cast of N persona characters, one per list item.
gooseworks-ai / render-hypermotion
1.2kAssemble the FREE steps of the product-hypermotion + kinetic-typography video format — dice ONE Seedance 2.0 hypermotion clip into 5-6 segments and intercut them with PIL kinetic-typography spec/CTA cards (italic skew, 1.08x outline echo, 3D extrusion, slam-with-shake, inversion flash) plus a real-l…
gooseworks-ai / render-logo-equation-card
1.2kRender the logo-equation card ad (7s, 9:16) — partner icon + brand icon joined by a plus sign as an equation, a two-line "= outcome" headline, four numbered steps, and a CTA that hard-cuts in at 2s, on a static black card over timelapse b-roll, no voice.
gooseworks-ai / render-whiteboard-explainer
1.2kAssemble a whiteboard explainer video ad from a beats file — a narrator explains one idea while a real whiteboard fills up in black marker, with a hand-lettered title, bulleted rows down the left, a drawing filling the right, and a payoff that letters the closing line and rings the claim.
gooseworks-ai / ugc-fixloop
1.2kthe UGC fix-loop toolkit — surgically re-render a bad window/beat of a single-take UGC master (stitch_replacement.py, pure FFmpeg) and GPT cross-model review a Seedance prompt before render (vet_seedance_prompt.py, routed through the openai-proxy).
gooseworks-ai / update-brand-kit
1.2kMaintain a brand kit — the canonical brand context an ad or content pipeline reads (positioning, audience, voice, standing instructions, brand-type, value-props, colors), plus manage the product list and attach product photos
gooseworks-ai / landing-page-intel
1.2kExtract competitor and customer intelligence from any company's landing page HTML. Discovers tech stack, analytics tools, ad pixels, customer logos, SEO metadata, CTAs, hidden elements, and more. No API keys required.
gooseworks-ai / competitor-monitoring-system
1.2kSet up and run ongoing competitive intelligence monitoring for a client. Tracks competitor content, ads, reviews, social, and product moves.
gooseworks-ai / job-scraper
1.2kSearch for job postings across LinkedIn and Indeed