Loading...
Loading...
Found 56 Skills
Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.
The meta-skill that powers all other AI tools. Prompt engineering for creative applications is the art and science of communicating with AI models to produce exactly what you envision—in images, video, audio, and text. This isn't just "write better prompts." It's understanding how different models interpret language, how to structure requests for different modalities, how to iterate systematically, and how to build prompt libraries that encode your creative vision. The best prompt engineers have developed intuition for what words trigger what responses in each model. This skill is foundational—it amplifies the effectiveness of every other AI creative skill. Master this, and you master the interface to all AI creation. Use when "prompt, prompting, prompt engineering, better prompts, prompt optimization, how to prompt, prompt strategy, prompt library, prompt template, make AI understand, prompt-engineering, prompting, meta-skill, ai-creative, foundational, optimization, iteration" mentioned.
FFmpeg-based 4-step video creation: Validate, Prepare, Encode, Verify. Use when user wants to combine a static image with audio to create an MP4 video, create a music video from cover art, or produce podcast/YouTube video from an image and audio file. Use for "image to video", "static video", "mp4 from image", "album art video", or "audio visualization". Do NOT use for video editing, live streaming, or generating images.
PointPillars for 3D object detection from LiDAR point clouds. Encodes point clouds into a pseudo-image via a pillar-based representation, then applies 2D detection — used in autonomous driving and robotics. Use when training, evaluating, exporting, pruning, retraining, or running inference for a TAO PointPillars model. Trigger phrases include "train PointPillars", "LiDAR 3D detection", "point-cloud object detection", "pillar-based 3D detector".
Data validation patterns including schema validation, input sanitization, output encoding, and type coercion. Use when implementing validate, validation, schema, form validation, API validation, JSON Schema, Zod, Pydantic, Joi, Yup, sanitize, sanitization, XSS prevention, injection prevention, escape, encode, whitelist, constraint checking, invariant validation, data pipeline validation, ML feature validation, or custom validators.
Extracts hidden or encoded text from GCODE files by analyzing toolpath geometry and coordinate data. This skill should be used when tasks involve decoding text from 3D printing files, recovering embossed or engraved text from GCODE, or CTF-style challenges involving GCODE analysis. Applies to any task requiring geometric reconstruction of text from CNC or 3D printer movement commands.
Video/audio/image processing with FFmpeg and ImageMagick. Tools: FFmpeg (video/audio), ImageMagick (images). Capabilities: format conversion, encoding (H.264/H.265/VP9/AV1), streaming (HLS/DASH), filters, effects, thumbnails, watermarks, batch processing, hardware acceleration (NVENC/QSV). Actions: convert, encode, resize, crop, compress, extract, merge, stream, transcode media. Keywords: FFmpeg, ImageMagick, video encoding, audio extraction, image resize, thumbnail, watermark, HLS, DASH, H.264, H.265, VP9, AV1, codec, bitrate, framerate, resolution, aspect ratio, filter, overlay, concat, trim, fade, batch processing. Use when: converting video/audio formats, encoding with specific codecs, generating thumbnails, creating streaming manifests, extracting audio from video, batch processing images, adding watermarks, optimizing file sizes.
Render JSON artifacts into readable UI with an inspect-first, facts-first workflow. Use when Codex needs to turn JSON files, JSON-producing shell commands, CLI output artifacts, or unknown structured payloads into a declarative UI spec that can be rendered natively by the harness or through a terminal-native reference renderer, including cases with repeated child records encoded as aligned arrays.
Audit a test suite to find tests that give false confidence — tests that encode bugs, duplicate coverage, or are so heavily mocked they can't catch real regressions. Use to improve robustness, audit coverage, or harden a risky area.
Internal sub-skill: agentic review of a printed CLI's sampled command output for plausibility issues that rule-based checks can't encode (substring-match relevance, format bugs, silent source drops, ranking failures). Invoked via the Skill tool by main printing-press SKILL.md (Phase 4.85) and printing-press-polish SKILL.md during the diagnostic loop. Not for direct user invocation — its actionable wrappers are /printing-press and /printing-press-polish.
Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction. Encode the rule as a lint, metadata flag, runtime check, or script instead of more text.
Encode and decode Swift types to and from JSON, property lists, and other external representations using Codable, JSONEncoder, and JSONDecoder. Use when implementing API response parsing, custom CodingKeys for key remapping, custom init(from:) or encode(to:) for complex transformations, nested or flattened JSON structures, heterogeneous array decoding, date and data decoding strategies, lossy array wrappers, Codable integration with URLSession, SwiftData, or UserDefaults, or when configuring encoder/decoder output formatting and key strategies.