prime-silo

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

Build, test-package, and release the Prime-Silo desktop app (Space Agent). Use when asked to build the app, make a local/test build, package for Windows/macOS/Linux, cut a release, bump the version, or debug the release CI. Covers the Open-Studio companion services (opencode + open-notebook) bundling.

DevOps, SDLC, Tagging, and Release management instructions for Prime-Silo. Use this when asked to tag a new release, check CI/CD build status, or manage the SDLC.

Initializes a new repository or workspace utilizing the Prime-Silo framework.

Performs data auditing and generation of move-analysis validations over Pypes executions.

Ingests documents, extracts entities/relationships, and populates the localized Neo4j Knowledge Graph.

Queries Neo4j for Prime-Silo run lineage, memory graphs, and session states.

Trigger browser file downloads from app filesystem paths, runtime-generated in-memory content, or external URLs.

Read the supplemental project documentation module

Persist user-scoped behavior and notes through prompt-include memory files

Inspect, navigate, and interact with open browser surfaces through space.browser

Open or close stand-alone browser windows

Place first-party modules correctly, make them routable, and use router seams instead of hardwiring features into shells.

Frontend development router. Load deeper skills before editing

Download app files, generated blobs, or external URLs

Create and download browser-generated PDFs from structured data or HTML

Capture the current page or a DOM target as a PNG

Run a guided, hands-on tour of the product — UI, spaces, the CLI, and environment variables

Open, create, remove, or edit spaces

Answer questions about THIS project — Benny / Prime-Silo itself: what it is, how it's built, the cognitive mesh, the Bridge cockpit, every workflow, the CLI, where the docs and code live, and how to use it. Load this whenever the user asks "what is this", "how does X work here", "what can this do", "where is the code for Y", "what workflows do we have", or anything about the product/project rather than their own content.

Be the operator's grounded co-pilot inside the Bridge cockpit (#/_prime_silo/bridge). Load this when the user is on the Bridge and asks "what am I looking at", "explain this graph", "what did I work on", "ingest these docs", "re-run the last manifest", or any question about the mesh on screen — memory, documents, code graph, flows, or runs.

Answer "what was I working on", "which sessions touched file X", or "show me the lineage of Y" by querying the Memo-Ray memory graph (the operator's agent-session history across Claude + Antigravity). Load this when the user asks about past work, prior sessions, file history, or what an agent did.

Extract data from PDFs and query CSV files

Read, write, and list workspace files

Semantic search capability over the workspace Knowledge Graph using ChromaDB