Recently Added
Fresh skills just added to the collection. Be the first to try them out!
SYADAGENTIC — SKILL.md (Skill Reference & Dispatch)
by Sekolah76
Jangan overclaim. Verified = bukti nyata.
tanteki
by iwasa-kosui
日本語の業務・技術文書を、必要な情報を保ちながら短く分かりやすく書く。製品要求書（PRD）、設計書（Design Doc）、設計上の決定記録（ADR）、仕様書、手順書、調査・計画・報告書などの作成や推敲で使う。構成を確認してから本文を書き、内容と textlint の両方で検査する。通常の質問への回答には適用しない。
blogwatcher
by magnusthovsland
"Monitor blogs and RSS/Atom feeds via blogwatcher-cli tool."
arxiv
by magnusthovsland
"Search arXiv papers by keyword, author, category, or ID."
apple-reminders
by magnusthovsland
"Apple Reminders via remindctl: add, list, complete."
apple-notes
by magnusthovsland
"Manage Apple Notes via memo CLI: create, search, edit."
serving-llms-vllm
by magnusthovsland
"vLLM: high-throughput LLM serving, OpenAI API, quantization."
segment-anything-model
by magnusthovsland
"SAM: zero-shot image segmentation via points, boxes, masks."
verify
by ahmadzayan-hub
Run every check Agentic OS has (Python suite, brain check, typecheck, frontend unit tests, production build, interface budget, and optionally the Playwright suite) with one command, and report the real counts. Use before saying a change works, before a commit that touches behaviour, before the session-end skill logs results, or when the user says "verify", "run the checks" or "is it green?".
ui-ux-pro-max
by ahmadzayan-hub
"UI/UX design intelligence for web, mobile, and desktop. This skill should be used when designing, building, reviewing, or fixing interfaces, including pages, components, design systems, accessibility, interaction, responsive layout, typography, color, charts, and stack-specific UI implementation. Searchable local data: 79 searchable styles (50 active), 192 product palettes and reasoning profiles, 74 font pairings, 119 UX guidelines, 105 icons, 17 GSAP presets, 25 chart types, and 22 stacks."
ui-styling
by ahmadzayan-hub
Create beautiful, accessible user interfaces with shadcn/ui components (built on Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs. Use when building user interfaces, implementing design systems, creating responsive layouts, adding accessible components (dialogs, dropdowns, forms, tables), customizing themes and colors, implementing dark mode, generating visual designs and posters, or establishing consistent styling patterns across applications.
slides
by ahmadzayan-hub
Create strategic HTML presentations with Chart.js, design tokens, responsive layouts, copywriting formulas, and contextual slide strategies.
session-start
by ahmadzayan-hub
Orient at the start of a working session on Agentic OS. Read the session briefing, Memory.md, project-progress.md, the last session-logs.md entry and the brain's core notes; check the repository's state; then state the plan in a few lines. Use when the SessionStart hook's briefing asks for it, or when the user says "start session" or "where are we?".
session-end
by ahmadzayan-hub
Close a working session on Agentic OS. Append the session's entry to session-logs.md, update project-progress.md, keep durable lessons in Memory.md, update the brain notes the work touched (with wikilinks), check the brain, then commit and push to the working branch. Use before a session ends, when the user says "wrap up", "end session" or "log this", or when the Stop hook asks for it.
rta-style
by ahmadzayan-hub
The user's house style for agent outputs, taken from their own executive-dashboard work: a red brand bar, navy and grey charts, tiles with a coloured leading edge, system fonts with Arabic support, light and dark. Colours, type and layout only, never a logo, name or data of any organisation. Use when a dashboard, evaluation report, clip, page or Claude Dashboard should look like the user's RTA-style work, or when the user asks for "RTA style".
review-loop
by ahmadzayan-hub
Run a deliverable or a change through review rounds until it is 100% validated, meaning every gate passes or is accepted by a named person, or until the loop must stop and say why. Deterministic gates first, then specialist reviewer subagents in parallel, then fixes, then gates again. Use before submitting a report, deck, dashboard or clip, before a release, or when the user says "review until it passes", "validate everything" or "make sure it is 100%".
motion
by ahmadzayan-hub
Make a short animated explainer (MP4) from verified figures. It has title cards, counting KPI cards, growing bar charts and statement cards, in English or Arabic, rendered frame by frame from code like Claude Motion, so no video model is involved. Use when a deliverable needs motion, such as a presentation's animated opener or backup, a dashboard teaser, a capstone briefing clip or a social cut of a finding. The motion-designer subagent runs this skill.
design-system
by ahmadzayan-hub
Token architecture, component specifications, and slide generation. Three-layer tokens (primitive→semantic→component), CSS variables, spacing/typography scales, component specs, strategic slide creation. Use for design tokens, systematic design, brand-compliant presentations.
design
by ahmadzayan-hub
"Comprehensive design skill: brand identity, design tokens, UI styling, logo generation (55 styles, Gemini, Atlas Cloud, or MuAPI AI), corporate identity program (50 deliverables, CIP mockups), HTML presentations (Chart.js), banner design (22 styles, social/ads/web/print), icon design (15 styles, SVG, Gemini 3.1 Pro), social photos (HTML→screenshot, multi-platform). Actions: design logo, create CIP, generate mockups, build slides, design banner, generate icon, create social photos, social media images, brand identity, design system. Platforms: Facebook, Twitter, LinkedIn, YouTube, Instagram, Pinterest, TikTok, Threads, Google Ads."
dashboards
by ahmadzayan-hub
Deep analysis of a dataset through the governed pipeline (scripts/analyse.py), then a dashboard where every figure shows its source. In claude.ai cloud sessions it builds a real Claude Dashboard with the Dashboard artifact type; anywhere else, or offline, it writes a free self-contained HTML dashboard (render.py). Use for KPI pages, scorecards, management dashboards, capstone or client dashboards, and "analyse this file and show me".
brand
by ahmadzayan-hub
Brand voice, visual identity, messaging frameworks, asset management, brand consistency. Activate for branded content, tone of voice, marketing assets, brand compliance, style guides.
brain-maintenance
by ahmadzayan-hub
Daily gardening of the second brain in brain/. Refresh stale values against their sources, merge duplicate notes, repair broken wikilinks, link unlinked mentions, strengthen connections between User, Identity, Soul and the other notes, and record what changed. Use once a day (the SessionStart briefing says when it is due), or when the user asks to tidy, update, merge or reorganise the brain.
banner-design
by ahmadzayan-hub
"Design banners for social media, ads, website heroes, creative assets, and print. Multiple art direction options with optional generated or supplied visuals. Actions: design, create, generate banner. Platforms: Facebook, Twitter/X, LinkedIn, YouTube, Instagram, Google Display, website hero, print. Styles: minimalist, gradient, bold typography, photo-based, illustrated, geometric, retro, glassmorphism, 3D, neon, duotone, editorial, collage."
gronify-json-flatten-search
by 1solomonwakhungu
Flattens, transforms, and queries JSON into greppable key-value path lines using the Gronify CLI (gron and ungron workflow). Use when an AI agent needs to flatten JSON, grep JSON, search nested JSON structure, inspect API payloads, diff JSON as sorted text lines, or replace jq with path-based queries.