Results for “grounding”

Draft or revise a scene on a goal-conflict-disaster spine with sensory grounding.

Parses external reviews, enforces coverage and grounding, and drafts a text-only rebuttal under venue limits, managing follow-up rounds.

Transforms content into the cinematic, vernacular voice of Tom Waits, grounding abstractions in concrete imagery and finding dignity in the downtrodden.

Conducts multi-turn iterative deep research on specific topics within a codebase, tracing actual code paths and grounding every claim in evidence.

Provides jurisdiction-specific legal context and contract scaffolding for the US, EU, and Canada, grounding agents in verified government references to reduce legal hallucinations.

Exploit-phase writing — assembles raw material into a journey of beats, grounding each term before a beat leans on it. Use when the user has raw material and wants it turned into an article.

Create and manage persistent AI agents with threads, messages, runs, and tools using the Azure AI Agents SDK for .NET.

Generates phrase-grounded bounding box annotations from image-caption pairs using a VLM, producing cleaned captions, referring expressions, and pixel-space bounding boxes.

Generate images using Google Gemini 3.1 Flash Image Preview via the inference.sh CLI, with support for text-to-image, image editing, multi-image input, and Google Search grounding.

GLIP: Grounded Language-Image Pre-training

Deploys a secure, enterprise-grade Google Cloud landing zone foundation with organization policies, resource hierarchy, billing association, and centralized logging and monitoring.

Trains, evaluates, exports, and runs inference on FoundationStereo models for stereo depth estimation and 3D reconstruction from stereo image pairs.

Advanced Geology Testing Skill

Configure deployment settings for /land-and-deploy.

Grilling

Load this skill when the user says "prepare base", "prepare-base", or "/prepare-base". Prunes remote tracking references, checks out a base branch, pulls latest, and cleans up local-only feature branches after confirmation.

Create and edit landscape terrain — heightmaps, sculpting, paint layers, terrain analysis, mesh projection, and procedural features like mountains/valleys/craters (LandscapeService). Use when the user asks to create a landscape, sculpt/raise/lower terrain, import or export a heightmap, paint terrain layers, or add procedural terrain features. For terrain materials load landscape-materials; for real-world heightmaps load terrain-data.

Creates a structured, queryable snapshot of a domain's current state, capturing entities, relationships, and properties with confidence scores and evidence anchors.

Use this skill for context gathering, file triage, source maps, assumptions, task framing, prompt hygiene. Trigger when the task involves programming work related to Context Engineering, production implementation, audits, debugging, strategy, or validation.

Sets up a codebase for reliable agent-driven development by making it legible (structured docs, custom lints, code graph), executable (one-command dev stack, cloud sandbox), and verifiable (e2e gate, verify-before-ship loop).

Deploy and verify smart contracts on Base with Foundry, including testnet faucet access, encrypted keystore management, and BaseScan verification.

Use this skill for property tests for parsers, validators, transforms, state machines, edge cases. Trigger when the task involves programming work related to Property Based Testing, implementation, audits, debugging, strategy, or validation.

Full project analysis for an unfamiliar Sage/Acorn/Lando project — discovers CPTs, routes, ACF field groups, Livewire components, Service Providers, active plans, installed packages; produces a structured project overview with health status and recommended next steps. Invoke for: "/onboarding", "I'm new to this project", "what does this project do", "show me what exists", "project overview", "orient me to this codebase", "what exists in this project". Skip when: you already know the project — the session-start hook already provided basic stack info; invoke the target skill directly instead.

Land and deploy workflow. Merges the PR, waits for CI and deploy, verifies production health via canary checks. Takes over after /ship creates the PR. Use when: "merge", "land", "deploy", "merge and verify", "land it", "ship it to production". (gstack)

Sets up a Spring Boot 3.2 project with clean architecture, Maven configuration, database setup, and exception handling.

Land and deploy workflow. (gstack)

Interrogates a plan against real third-party documentation, extracting hard constraints and asking doc-cited questions before producing a constraints appendix.

Procedurally design an AAA-style open-world FPS map blockout (roads, POIs, fields, forests/treelines, railway/bridges) from a landscape, validate it through gated checks, and materialize it into engine geometry. Use when the user asks to block out or lay out an open-world/FPS map, place roads/POIs/forests/railways procedurally, or turn a blockout plan into splines, paint layers, foliage, and actors.

Evaluates text-to-image generation models by decomposing assessment into five specialized skills (object presence, count, spatial relations, scale, and text rendering) and open-ended prompts, producing interpretable binary scores with visual and textual explanations.

Surface every assumption embedded in a plan, strategy, or document, assess how critical and how validated each one is, and identify which ones to test first. Load when the user asks to map assumptions, surface hidden beliefs, find what must be true for this to work, run an assumption audit, or when deep-thinking diagnoses an assumption frame. Also triggers on "what are we assuming", "what must be true for this to work", or "find the untested beliefs". Based on David Bland and Alex Osterwalder's assumption mapping method from Testing Business Ideas.