UniverLab
- 10 skills
- 0 followers
- 6 hours ago last updated
- ▌ Cadspec · univerlab bundleUse this skill when the user needs cadspec workflows for declarative CAD as code in TOML (.cf): creating projects, live-previewing in the browser (serve), compiling to DXF, validating layers/constraints, generating PNG/SVG previews for visual verification, importing DXF, formatting .cf files, or running watch mode. Activate for prompts mentioning cadspec commands (new/init/serve/build/check/layers/preview/schema/fmt/ watch/import/view), project.toml, .cf primitives, AGENTS.md in a CAD project, or CAD-as-code drawing pipelines.
- ▌ Texforge · univerlab bundleCLI tool for compiling LaTeX documents to PDF without TeX Live, MiKTeX, or any external LaTeX distribution. Use this skill whenever the user wants to create a LaTeX project, compile .tex files to PDF, format or lint LaTeX documents, spell-check prose, inspect the produced PDF, manage templates, or work with the texforge CLI. Activate when the user mentions "texforge new", "texforge build", "texforge fmt", "texforge check", "texforge init", "texforge template", "texforge outline", "texforge stats", "texforge preview", "texforge pdf", "texforge spell", "texforge doctor", creating a thesis or academic document, compiling LaTeX without installing TeX Live, using tectonic as a LaTeX engine, spell-checking a LaTeX document, project.toml configuration, or any workflow involving .tex files and the texforge tool.
- ▌ Demostage · univerlab bundleCLI tool for making terminal demos as reproducible code ("Demos as Code"). Use this skill whenever the user wants to capture, record, export, or edit a terminal demo, author a demo.toml score, produce a gif/mp4 of a CLI session, compose a terminal pane next to a browser/PDF pane, or manage sources and scenes. Activate when the user mentions "demo capture", "demo record", "demo export", "demo edit", demo.toml, macro.raw.toml, recording a terminal demo, gif/mp4 of a terminal, DemoStage, or a multi-scene terminal+browser demo.
- ▌ Canopy Sync · univerlab bundleUse this skill when the Canopy MCP server is available and you are about to act on a shared workspace: writing files, running builds or tests, installing dependencies, or committing. It defines the action-driven sync protocol (sync_get_context, sync_declare_intent, sync_broadcast, sync_report_status) that keeps solo history clean and multi-agent work conflict-free.
- ▌ Code Engineering · univerlab bundleUse this skill when implementing, refactoring, reviewing, or designing production code that needs structural judgment, not just syntax. It is most useful for multi-file changes, boundary design, pattern selection, naming, guard-clause refactors, dependency management, and maintainability decisions in any language.
- ▌ Architect Mindset · univerlab bundleUse this skill when designing systems rather than implementing them: choosing boundaries and contracts, comparing architecture options, planning multi-component work, decomposing a problem into independently verifiable parts, reviewing a design for failure modes, or writing specs and decision records that other agents (or cheaper models) will execute. It applies systemic thinking at the design level; for code-level structure use code-engineering instead.
- ▌ Execution Mindset · univerlab bundleUse this skill as the default operating mode for any task that needs judgment, safe execution, or reliable completion. Apply it when starting work, analyzing requests, editing code, running commands, reviewing results, or handling ambiguous instructions. It enforces right-sizing the response to the request, zero-indulgence clarity, interview-driven alignment when uncertain, a systemic resolution model for problems, verification before reporting, resourcefulness after failures, and token-efficient communication.
- ▌ Canopy Loop Design · univerlab bundleUse this skill when the user wants to turn a recurring or multi-step process into a reusable Canopy loop, write specs for a backlog or pool, inspect or reshape an existing loop graph, or coordinate background agent/check/gate flows with approvals and retries. Prefer reusable graph patterns over one-off pipelines, and build against the MCP loop tools that actually exist in the environment.
- ▌ Canopy Capabilities · univerlab bundleUse this skill when someone asks what Canopy can do: onboarding a new user, answering "what can I do here?", proposing automations for a workspace, or deciding whether a need maps to an agent, a loop, memory, or sync. It gives the capability map plus concrete starter ideas, and teaches how to discover the live tool surface instead of trusting a static list.
- ▌ Canopy Intelligence · univerlab bundleUse this skill when the Canopy MCP server is available in the session and you need to pull workspace context or persist durable knowledge. It covers the Project Intelligence Layer (PIL): when to call get_tools and intelligence_get_context, and when to register facts and patterns with intelligence_upsert so future sessions inherit what you learned.