Results for “baseline-capture”

Measure Jetson DRAM and NvMap usage, capture before/after baselines, and verify memory reclamation with live audit data.

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

Enforces an opinionated UI baseline to fix spacing, hierarchy, typography, and layout issues in AI-generated interfaces.

Capture frames or clips from RTSP/ONVIF cameras.

Find adjacent vendors and subs (not top market primes) who fill a capability gap against a displacement target using USASpending flows and SAM entity signals. Use when user defines a teaming gap and wants vault-ready partner shortlist with citations.

One-shot lifecycle command that chains init → baseline → spawn → eval → merge in a single invocation.

Capture durable project memory from work, debates, debugging discoveries, learned conventions, deferred options, and session outcomes. Load when the user says remember this, save this learning, record what happened, update project memory, or preserve context for future agents.

Captures and organizes chaotic brain dumps into a structured, actionable system with zero information loss. Use this skill whenever the user says 'capture this', 'brain dump', 'let me dump some ideas', 'I've got a bunch of thoughts', 'here's every...

GLIP: Grounded Language-Image Pre-training

Generates a per-target knowledge-base markdown file by walking the BSP root and source tree, documenting image layout, source tree structure, and document references.

Generate pragmatic CI/CD pipelines from detected project stack signals, with fast baseline generation, repeatable checks, and environment-aware deployment stages.

Capture snapshots, clips, or motion events from RTSP/ONVIF cameras using the camsnap CLI.

Capture frames or clips from RTSP/ONVIF cameras.

Capture frames or clips from RTSP/ONVIF cameras.

Capture frames or clips from RTSP/ONVIF cameras.

One-shot lifecycle command that chains init → baseline → spawn → eval → merge in a single invocation.

Transforms unstructured streams of mixed thoughts, tasks, and ideas into a clean four-section actionable system with zero information loss.

Generate heightmaps, map reference images, and water feature splines (rivers, lakes, oceans) from real-world geographic data (terrain_data tool). Use when the user asks to build terrain from a real location/coordinates, download a real-world heightmap, or add rivers/lakes/oceans from map data. Downloads Mapbox tiles server-side and produces UE5-compatible heightmaps + landscape splines.

Validates animation durations, enforces typography scale, checks component accessibility, and prevents layout anti-patterns in Tailwind CSS projects. Use when building UI components, reviewing CSS utilities, styling React views, or enforcing design consistency.

OI-3 spike harness — heavy consumer skill, BASELINE arm. Builds an incident post-mortem and sources the readability standard mid-workflow by reading a file directly, with NO Skill-tool call. Use only when explicitly invoked by the spike harness with a TRIAL_ID and data path.

Capture frames or clips from RTSP/ONVIF cameras.

Captures quick notes as timestamped markdown files, lists them, and promotes them into todos with zero friction.

Access AWS Bedrock foundation models for generative AI, including text generation, embeddings, and image generation, with CLI and Python examples.

Pose-conditioned generation on RunComfy via the `runcomfy` CLI. Routes across Kling 2-6 Motion Control Pro / Standard (transfer the motion / blocking of a reference video onto a target character), community Wan 2-2 Animate (audio-driven character animation with pose conditioning), and Z-Image Turbo ControlNet LoRA (pose-conditioned image generation from an OpenPose / DWPose / canny / depth control image). Picks the right route based on video vs still and stylized vs photoreal. Triggers on "controlnet", "control net", "pose control", "openpose", "DWPose", "transfer pose", "motion control", "pose driven", "character pose", "depth control", "canny edge", "use this pose", or any explicit ask to condition generation on a pose / skeleton / motion / depth / canny reference.

Improved Baselines with Visual Instruction Tuning

Flamingo: A Visual Language Model for Few-Shot Learning

Play Yoink, an onchain capture-the-flag game on Base. Yoink the flag from the current holder, check game stats and leaderboards, view player scores, and compete for the trophy. Uses Bankr for transaction execution.

High-fidelity website/app clone design pipeline. Use when asked to clone, replicate, copy, or recreate any existing website or app screen. Captures real assets (images, SVGs, fonts, colors), extracts exact design tokens, generates the clone in Stitch, composites real assets into the output, then runs section-by-section visual comparison against the reference. Produces 90%+ accurate clones by combining Stitch generation with real asset injection.

DreamLIP: Language-Image Pre-training with Long Captions

Nocaps: Novel Object Captioning at Scale

Pose-conditioned generation on RunComfy via the `runcomfy` CLI. Routes across Kling 2-6 Motion Control Pro / Standard (transfer the motion / blocking of a reference video onto a target character), community Wan 2-2 Animate (audio-driven character animation with pose conditioning), and Z-Image Turbo ControlNet LoRA (pose-conditioned image generation from an OpenPose / DWPose / canny / depth control image). Picks the right route based on video vs still and stylized vs photoreal. Triggers on "controlnet", "control net", "pose control", "openpose", "DWPose", "transfer pose", "motion control", "pose driven", "character pose", "depth control", "canny edge", "use this pose", or any explicit ask to condition generation on a pose / skeleton / motion / depth / canny reference.

One-shot lifecycle command that chains init → baseline → spawn → eval → merge in a single invocation.

Chameleon: Mixed-Modal Early-Fusion Foundation Models