Recently Added
Fresh skills just added to the collection. Be the first to try them out!
macos-computer-use
by HMS091
Drive the macOS desktop in the background — screenshots, mouse, keyboard, scroll, drag — without stealing the user's cursor, keyboard focus, or Space. Works with any tool-capable model. Load this skill whenever the computer_use tool is available.
hotspot-survey
by leodearden
"Multi-agent historical bug-hotspot survey — mines git history, fix-task history, and postmortems for where bugs have clustered, deep-reviews each hotspot cluster for the root structural cause against docs/code-quality.md, adversarially verifies every finding against the code, and synthesizes cross-system improvement proposals into a ranked report + keyed findings JSON (docs/quality-findings-contract.md) that feeds deliberation and then /prd. Runs in REFRESH mode by default when a previous survey report exists (mines only the commits since its as_of_sha, re-verifies its open findings, re-reviews only materially changed clusters); --full re-derives everything. ALWAYS use this skill for: /hotspot-survey commands, 'conduct a systematic survey for bug hotspots', 'which parts of the code have been buggy historically', 'mine git history for where bugs cluster', 'what should we refactor next based on bug history', refreshing a previous hotspot survey, or a /review-all run asking for a hotspot refresh. Long-running and many-agent (full: ~28 agents, ~2.5M subagent tokens, 60-90 min; refresh: sized from the prior report in the cost gate) — state the cost up front, and if the ask is vague ('are there bugs here?') confirm scope before launching. NOT for: current-state correctness review (/review), comprehension of a single target (/study), root-causing one specific problem (/deb), authoring the remediation PRDs (/prd — feed it this skill's report), or a project's deterministic detector sweep (e.g. reify /audit)."
census
by leodearden
"Run an operator-initiated LEGIBILITY CENSUS: an attended first census for a newly-enabled project (run with cost caps and review-before-filing, before the nightly trickle auto-fires an unattended one), or an ad-hoc forced census on demand (e.g. after a big remediation wave). ALWAYS use this skill for: '/census <project-root>', 'run a census', 'run a legibility census', 'first census for <project>', 'force a census now'. Recurring census runs need NO skill — the nightly trickle's evaluate_census_step launches scripts/legibility/census.py automatically when census_trigger fires; this skill covers only the cases where a human kicks it off by hand. NOT in scope: editing scripts/legibility/* code, the nightly trickle, or the census trigger logic itself — this is an operator run-and-verify skill, not a dev skill."
ado-backlog
by GitQuuu
Conventions for running the QuGents agent team from an Azure DevOps (Scrum) backlog - work item types and fields, the agent tag workflow (agent-plan, agent-proposed, agent-ready, agent-working, agent-pr-open, needs-human), WIQL queries, branch/commit/PR naming and the Azure DevOps MCP tools. Loaded by ado-plan and ado-deliver; use directly when reading or updating backlog items for the agents.
findmy
by HMS091
"Track Apple devices/AirTags via FindMy.app on macOS."
apple-notes
by HMS091
"Manage Apple Notes via memo CLI: create, search, edit."
software-download-sourcing
by HMS091
Use when 用户要找"纯净/绿色版"软件下载或核验渠道。先定软件形态→找官方源→识别下载墙→核验纯净度，中文报告。
lightpanda
by HMS091
"Lightpanda headless browser (Zig, AI-focused) — use via Hermes MCP tools (mcp_lightpanda_*) for fast local bulk scraping / markdown dumps. When user asks to grab a page's content fast, batch-fetch many URLs, or dump a site to markdown/html without anti-bot concerns. NOT for anti-bot/login sites — use Scrapling/browser there."
hermes-dashboard
by HMS091
"Architecture, rendering pipeline, and modification guide for the Hermes Dashboard Web UI (TUI/Ink). Know what renders where before writing code."
github-gfw-sync
by HMS091
"Sync git repos to GitHub through the Great Firewall of China — HTTPS + token auth instead of blocked SSH, silent-failure pitfalls, and cron auto-sync."
environment-enhancement
by HMS091
Systematically enhance a Docker/Linux environment with tools and capabilities — browser, media, document processing, development tools, and data extraction. Designed for Docker containers on NAS (Synology) with limited initial tooling.
crypto-trading
by HMS091
Real-time cryptocurrency market monitoring with technical analysis (RSI, MACD, SMA), signal generation, price tracking in SQLite, and automated trading strategy automation. Build, maintain, and iterate crypto monitoring and trading bots.
crypto-token-dd
by HMS091
Crypto token/project due diligence — analyze a contract address or project for scam, rug pull, honeypot, or ponzi indicators. Multi-source data collection, risk signal framework, structured Chinese report with tables and risk flags.
business-project-evaluation
by HMS091
"Evaluate business project ideas OR stock/investment theses with a reality-checked framework. Covers business model analysis (service vs product), competition assessment, distribution strategy, and equity research (supply chain chokepoint analysis, influencer due diligence). For a solo developer with AI/automation capabilities."
autonomous-freelancing
by HMS091
"Full-stack autonomous freelancing pipeline — research platforms, register accounts, monitor tasks, auto-bid, auto-deliver code. User handles accounts/wallets, agent handles ALL technical work."
ai-creator-platform
by HMS091
Operate the platform-owned AI creator system on JustFans 18080 through the local Agent API client.
video-shotlist-prompt
by lsi9923
짧은 영상(15~30초) 멀티샷 프롬프트를 샷 리스트로 설계한다. 샷마다 시간·카메라·인물·대사·사운드·네거티브를 고정해 한 번의 생성으로 여러 컷을 뽑는다. "영상 프롬프트", "샷 리스트", "멀티샷 프롬프트", "브이로그 영상 만들어줘", "15초 영상 프롬프트" 요청에 쓴다.
thread-content-strategist
by lsi9923
소재(메모·경험·강의·인터뷰·기존 글)를 받아 핵심 메시지 하나로 재구성해 스레드/짧은 글을 쓰는 스킬. 독자 욕구 분석, 후킹 유형 10종, 통념 충돌 설계, CTA 강도 조절을 포함한다. "스레드 글 써줘", "후킹 만들어줘", "이 소재로 글로 써줘", "조회수 터지는 글" 요청에 쓴다.
side-hustle-design
by lsi9923
개인의 경력·시간·자본을 기준으로 부업 후보를 만들고 시장 검증 질문·가격안·90일 실행 계획을 세운다. 수익·시장 규모는 가정과 계산식을 분리해 제시한다. "부업 뭐가 좋을까", "부업 설계해줘", "사이드 프로젝트 계획", "수익 모델 짜줘" 요청에 쓴다.
reference-video-editing-skill
by lsi9923
레퍼런스 영상의 편집 스타일을 분해해 '편집 규칙집'으로 만들고, 그 규칙대로 자동 편집하는 프로그램을 만들어 계속 재사용하는 스킬. "영상 편집 자동화", "레퍼런스 편집 스타일 따라하기", "편집 규칙집 만들어줘", "자동 편집기 만들어줘" 요청에 쓴다.
multi-agent-session-brief
by lsi9923
여러 에이전트(Claude·Codex·GJC·OmO 등)에게 같은 작업을 나눠 맡길 때, 각자에게 줄 역할 브리핑과 인수인계 형식을 만든다. "에이전트 역할 나눠줘", "멀티 세션 분담", "여러 놈한테 시킬 지시서", "에이전트한테 일 나눠" 요청에 쓴다.
motion-video-brief-builder
by lsi9923
광고·쇼릴·뮤직비디오 같은 짧은 영상의 콘셉트 브리프와 초 단위 샷 리스트, 생성 프롬프트, 사운드·금지 조건을 함께 설계한다. "뮤직비디오 기획", "광고 영상 브리프", "쇼릴 만들어줘", "영상 콘셉트 잡아줘" 요청에 쓴다.
image-prompt-portrait
by lsi9923
인물 사진 이미지 생성 프롬프트를 섹션 구조(IDENTITY/SUBJECT/WARDROBE/POSE/LIGHT/CAMERA/ENVIRONMENT/COLOR/MOOD/QUALITY)로 만들어 준다. "인물 사진 프롬프트", "화보 프롬프트 만들어줘", "저조도 인물 사진", "이미지 프롬프트 구조", "포트레이트 프롬프트" 요청에 쓴다.
hyperframes-renderer
by lsi9923
Hyperframes CLI로 음성·자막·B-roll을 자동 컷편집해 최종 mp4를 빌드하는 스킬 생성 지시문과 실행 절차. "하이퍼프레임즈로 영상 렌더", "쇼츠 자동 합성", "음성+자막+B롤 자동 편집" 요청에 쓴다. Claude Skill 형태로 만들 때 이 문서를 그대로 지시문으로 쓴다.