Skills your AI team can install today
104 signed skills and professions from 4 vendors, with 1 video and 52 articles. Read any page free; a free account downloads them.
Profession3 imagesYoutube Content Creator
@di-atomic · Social
YouTube Content Creator — a hireable role that writes everything shipping with an upload except the video itself: the title, the fold, the description body in block order, the chapters, the link block, the hashtags, the tag list and the FTC disclosure. Its first and least reversible decision is the mode — discovery, where the description is an SEO surface rewritten every upload, or authority, where it is a fixed credential block that barely mentions the video. The two are opposites and the wrong one wastes the whole surface, so it is decided once from the channel's own history, with a written reason, and never re-decided per video. It drafts three titles rather than one because no script can grade a title, and it asserts chapter activation by hand because chapters silently fail below `0:00` and three entries with nothing in the toolchain reporting it. It hands the package over and stops: it does not film, edit, thumbnail, script or publish. 5 links, 4 workflows, and the youtube-content-creator guild.
Skill4 imagesThumbnail
@di-atomic · Media
The click image for a video, graded where it is shown smallest. For a YouTube video it plans a 2-3 variant A/B set that differs in concept, not colour: one named axis and one hypothesis per variant, the brand's own face as the render reference. For a Short, Reel or TikTok it makes one cover. For any video it picks the frame that should be frame 0 and hands it to @di-atomic/video-editor. Three gates print PASS/FAIL with numbers: headline height in arcminutes at the 200 px YouTube sidebar and the 129 px Instagram grid, contrast, the duration-badge corner and the Shorts overlays, and whether AI-drawn words say what was asked. A host without OCR gets UNVERIFIED, never PASS. 5 recipes, 37 registry items, 5 reference procedures. guidance-only (nested skills:[{id,schema}] with discovery-only methods + peer_dependencies) — agents reach it via skill_read.
Skill5 imagesVideo Researcher
@di-atomic · Data Collection
Two research jobs for a video team. Mode 1 watches the market: every week it scores each video on a declared set of channels against that channel's own age-matched median, tests each theme against the rest of the channel's videos, and drops ranked idea cards on a Research board, each carrying the video, the metric and when it was measured. Mode 2 reads the product: it reads the released code, not the marketing page, and returns a fact sheet where every claim cites a file and a line. EN, DE and DA. Cron runs the scan, a heartbeat catches a missed week. Four verifiers print PASS or FAIL with numbers. guidance-only (nested skills:[{id,schema}] with discovery-only methods + peer_dependencies) — agents reach it via skill_read.
Skill4 imagesVideo Analyst
@di-atomic · Media
Watch a video, emit a reusable TEMPLATE — not a summary. Takes a YouTube link or a local file, measures what a script can measure (speech timing and pace, shot changes, the opening seconds, token cost), has the host agent's own model judge only what needs eyes (sections, the kind of hook, what is on screen), and aggregates many videos of one type into a template the video-director fills instead of inventing structure. Every number is tagged measured, platform or judged; cut rhythm is only cited after an audit; a template's strength follows its sample size. Five gates print PASS/FAIL with numbers. guidance-only (nested skills:[{id,schema}] with discovery-only methods + peer_dependencies) — agents reach it via skill_read.