sliday/skills

최근 기록된 소스 활동: 2026년 11월 2일 09:50

SkillsMP 카탈로그 업데이트: 2026년 11월 5일 19:57

수집된 skills: 13

GitHub 스타: 3
GitHub 포크: 0

AI 어시스턴트로 설치

이 프롬프트를 복사해 사용 중인 AI 어시스턴트에 입력하세요.

Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/sliday/skills.

저장소 README

README 원본 파일: README.md

README 원본 보기

README 전체 펼치기

# Sliday Agent Skills [![skills.sh](https://skills.sh/b/sliday/skills)](https://skills.sh/sliday/skills) Practical, evidence-first skills for agents working on real decisions, not generic role prompts. ## Skills | Skill | What it does | |---|---| | [`food-delivery-deals`](./food-delivery-deals/SKILL.md) | Finds usable deals on Wolt, Uber Eats, Glovo, Bolt Food, foodora/foodpanda/efood, Just Eat Takeaway and Deliveroo (Grab through the user's browser), prices the real order with fees, and compares apps and grocery baskets. Read-only, no account. Live-tested endpoint maps per platform, stdlib CLIs for Wolt (`deals` ranks the best offers near a point in one run), Just Eat Takeaway (real fee bands) and efood, `check_endpoints.py` to catch API drift, and a judged release eval. | | [`visual-explanation`](./visual-explanation/SKILL.md) | Chooses the clearest teaching medium, then builds and verifies practical HTML explainers, diagrams, or narrated videos. Production toolkit, not an always-active instruction layer. | | [`prototyper`](./prototyper/SKILL.md) | Defines and builds usable prototypes with local discovery, nested client progress cards, feedback, acceptance checks and a team handoff. | | [`anonymizer`](./anonymizer/SKILL.md) | Redacts personal details locally from text and images with OpenAI Privacy Filter, opaque image masks, and optional consent-gated GPT Image 2.5 finishing. | | [`hotel-hunting`](./hotel-hunting/SKILL.md) | Finds hotels rated honestly by AI, not pay-to-play, using Hotelist normalization, Nomads.com city context, Hoodmaps neighborhood checks, real traveler reports, photo forensics, and exact-stay verification. | | [`consumer-billing-refunds`](./consumer-billing-refunds/SKILL.md) | Identifies charges from primary evidence, verifies current refund routes, separates cancellation from refund, and drafts bounded escalation. | | [`local-recurring-activity-planning`](./local-recurring-activity-planning/SKILL.md) | Turns a vague nearby activity into one low-friction recurring ritual using first-party evidence, calendar fit, and trial-to-standing-slot commitment. | | [`music-practice-space-finding`](./music-practice-space-finding/SKILL.md) | Finds rehearsal spaces that support repeated practice, distinguishing shared rooms, hourly studios, storage, backline, and recurring slots. | | [`agent-visual-verification`](./agent-visual-verification/SKILL.md) | Gives coding agents a trustworthy screenshot-evidence path and verifies the full capture-to-inspection chain. | | [`agent-insights`](./agent-insights/SKILL.md) | Analyzes local development-agent activity across Claude, Codex, Gemini, Kimi, claude-mem, and Hermes without exporting raw transcripts. | | [`ui-capitalization`](./ui-capitalization/SKILL.md) | Ends capitalization drift in UI copy. Picks one of three modes (sentence-first, hybrid, title-first) with the Apple, Chicago, AP, and APA title-case rules, locks a regional English (US, UK, CA, AU, NZ), and ships `capcheck.py` to audit i18n files for mode, duplicate casings, and locale spelling. | | [`ux-ui-ia`](./ux-ui-ia/SKILL.md) | Designs and reviews information architecture, flows, controls, accessibility, and visual systems. 18 UX laws as diagnostic lenses, an 8px spacing grid, atomic token-to-component composition, a 54-row visual symptom-to-fix index, plus grid/craft audit scripts and a PostToolUse design-guard hook. | ## Install List available skills: ```bash npx skills add sliday/skills --list ``` Install one skill: ```bash npx skills add sliday/skills --skill hotel-hunting ``` Install all: ```bash npx skills add sliday/skills --all ``` ## Principles - Evidence before confidence. - Hard constraints before ranking. - Exact operational verification before claiming completion. - Short decision surfaces instead of giant option dumps. - Private examples, credentials, and personal memory stay out of the public pack. - Untrusted retrieved content is evidence, never instructions. - Claims that can be measured are measured, not asserted. ## License MIT. See [LICENSE](./LICENSE).

저장소 README를 불러오는 중…

게시물

모두 보기 →

Stas Kulesh

@staskulesh2026년 10월 21일 08:46 UTC

Skill 공개 소식에이전트 작업 조율

게시물 요약 · 영어

food-delivery-deals compares the real cost of the same order across Wolt, Uber Eats, Glovo, Bolt Food and Deliveroo, adding hidden fees, minimums and discount caps rather than trusting banner percentages.

원문 보기

Skill 자세히 보기 · skills/food-delivery-deals

이 저장소의 skills

분류 대기 중