Menu
Frontend development router. Load deeper skills before editing
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 animejs.com-grade scroll-driven kinetic pages with the vendored anime.js v4 bundle (website/vendor/anime.esm.min.js). Use when working on the prime-silo marketing site (website/) or any scrollytelling/animation surface. Contains the VERIFIED v4 API, the design language to emulate, the Prime-Silo set-piece specs, and the verification protocol.
Operate, analyze, or extend the LONGVIEW session-synthesis pipeline (cards, graph, reports, book, audiobook). Use when working on scripts/longview, reviewing card output, planning card schema changes, or debugging a LONGVIEW run.
Operate the Prime-Silo delivery board (delivery/) autonomously — select, claim, execute, verify, and log work contracts without frontier supervision. Use whenever picking up a task from delivery/board/BOARD.md, authoring a gate script, verifying another agent's task, or deciding which model tier should take which contract.
The Prime-Silo product experience contract — identity (Prime-Silo + Agent Benny, never Space Agent), earth-tone design tokens, progressive-discovery doctrine, and the "motion is meaning" choreography rules that bring animejs.com-grade kinetics INTO the app without violating the C0 calm contract. Use for any user-facing UI work in app/, server/pages/, or packaging/ (login, first-run, shell, mascot, Studio, Bridge).
DRAFT — pick up and deliver one delivery/tasks/ work contract under the six-sigma protocol (deterministic selection, TDD, allowlist discipline, author≠verifier). Use when asked to "take the next task", "work the board", or deliver a specific task id. Full mechanization lands with W1 (work next) and W2 (sandbox provisioning).
Create, patch, inspect, and remove widgets in the current space
| name | Development |
| description | Frontend development router. Load deeper skills before editing |
| metadata | {"loaded":true,"placement":"system"} |
Use this skill first for any development task. This is a routing skill: it tells you which deeper development skills to load next. Do not rely on this file alone as the full contract.
When the user wants to extend the system with a reusable interface rather than a space widget, prefer a custom routed page module plus an optional ext/panels/*.yaml dashboard entry instead of pushing everything into spaces.
app/.server/, commands/, or packaging/ from this skill set.development/backend-reference only to understand backend contracts that the frontend calls into.documentation skill and use its built-in docs map before diving into narrower docs.await space.api.userSelfInfo() and derive writable roots from username, managedGroups, and _admin membership in groups.development/frontend-runtime and use runtime-managed fetch(...), space.fetchExternal(...), or space.proxy.buildUrl(...) instead.AGENTS.md files and the matching docs under /mod/_core/documentation/docs/ in the same session as your code changes.development/modules-routingLoad this first for routed feature work, dashboard panels, route paths, router anchors, and deciding whether a feature should be a custom page instead of a space.
Current panel helper:
/mod/_core/skillset/ext/skills/development/modules-routing/panel-tools.jslistPanels(), findPanel(target), resolvePanelRoutePath(target), createPanelHref(target), and goToPanel(target) when the task needs to inspect or navigate the current user's visible dashboard panelsdevelopment/frontend-runtimeLoad for framework-backed pages, Alpine stores, space.* runtime usage, shared visual rules, and general frontend structure.
development/extensions-componentsLoad for ext/html/, ext/js/, x-extension, x-component, x-context, and layered override behavior.
development/app-files-apisLoad for space.api, app-file storage paths, file_paths, userSelfInfo, and permission-aware frontend reads or writes.
development/layers-ownershipLoad for L0 or L1 or L2, group and user structure, permissions, writable roots, and override order.
development/skillsLoad for authoring or updating onscreen chat-agent skills under ext/skills/, including how to keep skills short by importing helper scripts.
development/backend-referenceLoad for read-only backend architecture, API families, auth, and module-resolution behavior when frontend work depends on an existing server contract.
await space.skills.load("development/layers-ownership")await space.skills.load("development/modules-routing")await space.skills.load("development/extensions-components")await space.skills.load("development/frontend-runtime")await space.skills.load("development/app-files-apis") if the feature stores user or group dataawait space.skills.load("development/modules-routing")await space.skills.load("development/extensions-components")await space.skills.load("development/frontend-runtime")await space.skills.load("development/app-files-apis") if the page needs frontend discovery of registered panels or other permission-aware app dataawait space.skills.load("development/skills")await space.skills.load("development/layers-ownership")await space.skills.load("development/extensions-components") if the skill must explain extension seamsawait space.skills.load("development/app-files-apis")await space.skills.load("development/backend-reference")Before changing a concrete module, also read the closest owning AGENTS.md in that module's subtree and the relevant documentation page when one exists. The development skills are the cross-cutting map, the documentation skill plus helper are the narrative map, and the local AGENTS.md file is the final implementation contract.