Menu
Find likely duplicate Linear issues, compare evidence, and propose link, merge, or closure actions.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Build Remotion videos with remocn — a shadcn registry of copy-paste animation components and timeline-driven UI primitives. Use when composing video scenes, adding text animations, transitions, backgrounds, UI blocks, brand/social cards, or full compositions in a Remotion project. Triggers include "remocn", "video component", "add animation", "text reveal", "scene transition", "product demo video", "remotion component", "typewriter", "terminal simulator", "glass code block", and the UI-primitive tier: "video dialog", "video button", "command menu", "video select", "video tooltip". Even if the user doesn't mention remocn, activate when they need polished video primitives for Remotion.
Use when creating, modifying, or reviewing an installable Eve agent under registry/<slug> in the evex repository.
Deliver Eve agents end to end. Use when creating, modifying, testing, or deploying an Eve agent.
Scope and ship a brand-aligned pack of SVG assets for SaaS products. Use when the user wants a visual pack, feature launch assets, icons, empty states, hero illustrations, badges, feature graphics, onboarding visuals, changelog art, or dashboard/modal graphics.
Make page content citable by AI search — extractable structure, authority signals, and machine-readable files. Use when writing page body copy for AI visibility.
Apply on-page SEO checks when building a single branded HTML page — metadata, headings, schema, links, and images.
| name | duplicate-detection |
| description | Find likely duplicate Linear issues, compare evidence, and propose link, merge, or closure actions. |
Use when a user asks whether an issue is duplicated or related.
list_issues with targeted queries. Done when at least one search
has run.get_issue on the strongest candidates before recommending. Done when
each candidate's scope, symptoms, environment, impacted user flow, and status
are compared.Use the agent default response shape, plus candidate duplicates, why they match or do not match, recommended canonical issue, and proposed Linear action.