en un clic
inkstone
inkstone contient 16 skills collectées depuis augchan42, avec une couverture métier par dépôt et des pages de détail sur le site.
Skills dans ce dépôt
Extract an abstract visual and motion blueprint (design DNA) from reference websites, or research award-winning references from a vibe description. Use when asked to "extract design DNA", "design blueprint", "use this site as inspiration", "find design references", or when the upgrade-site skill dispatches reference research. Observes and abstracts only — never implements.
Orchestrate a full website design upgrade — snapshot the current site, research references via design-dna, synthesize a direction, score the gaps, write a prioritized plan, dispatch implementation to motion-craft and build skills, and verify. Use when asked to "upgrade the site", "make it award-winning", "run the upgrade pipeline", or "audit the site design". Vague requests get a plan, not code changes.
Implement professional web animations in a target repo against an approved design blueprint or an explicit motion direction. Use when asked to "add animations", "improve the motion", "make it feel alive", "implement the motion plan", or when dispatched by the upgrade-site skill. Plans by default; modifies code only on explicit implement authority. For broad visual/reference research, see design-dna instead.
Interpret a Zhouyi (I Ching) hexagram or line in the de-mythologized, late–Western Zhou register of Edward Shaughnessy — original divination manual, not Confucian wisdom classic. Use when a user supplies a hexagram (number/name, optionally a specific line) and a question or wish, and wants a philological, historically-grounded reading rather than a cosmological or self-help one. Does NOT cast hexagrams.
Use when turning a long video (interview, podcast, talk, lecture, webinar) into short vertical clips for YouTube Shorts / Reels / TikTok. Transcribes the source, auto-suggests the most engaging self-contained soundbites, then cuts, crops to 9:16, and burns in subtitles. Cross-platform (macOS / Linux / Windows-WSL). Stops at a finished, upload-ready vertical mp4 — no account or upload CLI required.
Use when scheduling social copy or reviewing a batch of posts/drafts to measure sentence- and post-length variation — flags metronomic rhythm and same-size posts. For voice/tone rules, see your project's own style guide.
Search arXiv for papers by topic, author, or ID. Use when finding research, surveying recent publications, or looking up a specific paper.
Convert abstract symbolic concepts into Blakean embodied scene prompts — Blake's 8 compositional patterns, body grammar, and figure types. Use when visualizing oracular or symbolic ideas as figures; for ink-painting scenes from verse, see verse-to-prompt instead.
Generate scholarly bilingual (English + Traditional Chinese) explanations for classical Chinese verses. Use when explaining Yilin, I Ching, or Tang poetry lines.
Convert an ink painting's original image prompt into a video generation motion prompt for image-to-video APIs. Use when animating a verse-to-prompt result — requires that original prompt as input; never guess from a description alone.
App Store market overview for a category using web search only — competitor movements, trending keywords, Apple featuring, new releases, and category dynamics. No paid API subscriptions required. Use when the user mentions "market pulse", "market check", "what's happening in the App Store", "competitor check", or "category update".
Build a speaker media kit — bio writing, photo prep, and page generation for event organizers. Use when preparing speaker bios, headshots, or a press/media page.
Audit/fix Next.js i18n SEO for the App Router — crawlability, 307→301 redirects, locale URLs, sitemap, hreflang. Use when diagnosing lost PageRank or i18n redirect bugs in middleware.
Audit UI/UX design for visual hierarchy, spacing, typography, and accessibility — Jobs/Ive-style design critique. Use when reviewing a screen's visual design or running a UX audit.
Convert classical Chinese verses into image generation prompts — ink painting (default), stipple, or tech-noir variant. Use when visualizing Yilin, I Ching, Tang poetry, or classical Chinese text; for video motion prompts, see image-to-scene.
Interactive voice profiling — asks writing prompts in terminal, collects live responses, and distills a reusable voice profile for content generation. Use when calibrating tone for social posts, newsletters, or any written output.