100 skills · sorted by relevance
Find LLM workflows in a codebase and label them by the job they perform, so Caveman Cloud can separate spending by workflow. Present a labeling proposal for approval, apply focused code changes, and check an affected execution path.
Review buttons for missing or unclear names, including controls that contain only icons. Add text or labels that explain each action to screen reader users, and replace buttons used for page navigation with links.
Check checkboxes, radio buttons, and switches for descriptive names that screen readers can announce. Identify missing or unclear labels, suggest appropriate HTML or ARIA labeling, and explain how to verify the changes with accessibility tools.
Transcribe audio with Azure AI Speech and obtain word timestamps, speaker labels, and language identification. Use the resulting transcript in OpenMontage subtitle workflows, with a compatible local transcription fallback when Azure is unavailable.
Record and inspect source history, trust scores, and handling labels on AI-generated or modified files. Use AKF metadata, information attached to files, to support review, handoff, and advisory audit checks without treating labels as proof of compliance.
Add boxes, arrows, labels, and color-coded highlights to screenshots and diagrams using Pillow. Includes automatic label placement, detection of changed image regions, and guidance for timing annotations in animated GIF demonstrations.
Organize human review in Arize by defining label choices, numeric ranges, or free-text feedback fields. Manage review queues and reviewers, submit annotations for individual records, and apply existing labels to project spans, or individual processing records, in bulk.
Create shareable links that open specific Arize resources, including traces, datasets, and evaluators. Use IDs from logs or exported data, with suitable time ranges, to direct teammates to the relevant view.
Classify skills CLI pull requests, or proposed code changes, as documentation, bug fixes, or enhancements using their descriptions and patches. Add one label when the evidence is clear, while preserving existing classification labels.
Explore code structure and history using an index of code relationships and meaning-based search. Trace calls, assess change impact, find likely bug locations, generate architecture reports, and review pull requests for risk and conflicts.
Prepare for FDA medical device quality audits through six evidence-focused questions. Review complaints, adverse event reports, process validation, manufacturing records, corrective actions, labeling, and inspection history, then organize readiness gaps and three next actions with owners.
Investigate failed tests, type checks, builds, and CI jobs by recording exact evidence and repeating checks in a clean comparison environment. Use the results to distinguish existing failures, newly introduced problems, environment issues, and unresolved cases.
Audit and strengthen security for applications running on GKE. Configure pod traffic restrictions, sandbox isolation, namespace security standards, and Secret Manager volume mounts to protect workloads at the application and namespace level.
Sort a Superhuman inbox into messages needing a reply, waiting for others, useful information, and noise. Receive a clear attention list, then apply requested actions such as archiving, labeling, reminders, or unsubscribing.
Analyze incoming Slack messages, emails, or escalations before replying. Separate the explicit request from the outcome behind it, clarify requirements and success criteria, and develop a reply or counterproposal while clearly labeling assumptions.
Develop public equity trade pitches for portfolio managers, covering long, short, or paired positions. Explain the difference from market expectations, potential catalysts, gains and losses, risk considerations, and exit rules, while labeling assumptions and missing evidence.
Design a dark interface with matte-black surfaces, emerald accents, framed cards, and restrained glow. Apply consistent styling across navigation, typography, charts, and motion to create a calm, technical dashboard.
Create a dark interface built around fine gradient borders, asymmetrical panels, and precise labels. Apply a consistent visual system to page frames, typography, controls, and backgrounds, using restrained monochrome colors and subtle motion.
Classifies existing tests by standard traits and reports their distribution. USE FOR: tagging all tests with category attributes, categorizing/tagging/ labeling each test, compare happy vs error paths, audit the test mix, describe coverage shape by test type, or tag then verify the project builds. Read bodies when names mislead. Apply canonical attributes; otherwise report only. DO NOT USE FOR: requests owned by test-anti-patterns, coverage-analysis, crap-score, test-gap-analysis, code-testing, or migration skills.
The English summary is being prepared. Showing the original description.
Use this skill whenever the user asks for a chart, graph, plot, or visualization of data — 'chart this by month', 'show me a breakdown by category', 'visualize the trend'. Covers picking the right chart type for the question being asked, labeling/readability rules, and which plotting library to reach for. Pair with data-analysis for the underlying data prep.
The English summary is being prepared. Showing the original description.
Review chart choice, labeling, accessibility, and storytelling quality for existing visualizations. Use as an explicit/manual helper for critique and cleanup, not as the main owner for scientific figure production or general chart generation.
The English summary is being prepared. Showing the original description.
Run the PAIDF Orchestration Event Video Generation DAG on Kubernetes - image-to-video anomaly generation, auto-labeling, and anomaly dataset generation. Select for requests about event video generation, anomaly video generation, image-to-video synthesis, Cosmos3 image2video, anomaly dataset creation, safety/surveillance SDG, or generating person-falling, person-climbing, person-running, fighting, smoking/vaping, fire/smoke, or shoplifting video clips from a seed image. Runs environment setup first when controller readiness is unknown. Not for person-crop clothing/attribute augmentation (that is image-attribute-augmentation-workflow) and not for video style transfer.
The English summary is being prepared. Showing the original description.
Use when the user wants to orchestrate defect image generation with NVIDIA Cosmos AnomalyGen (Cosmos-Predict2-derived) on OSMO for PCBA, metal surface, and glass inspection. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint, cosmos defect generation, cosmos-predict2 defect, cosmos-anomalygen, cosmos predict2 finetune.
The English summary is being prepared. Showing the original description.
Query, search, and download data from the openFDA API for drugs, devices, foods, tobacco, cosmetics, animal and veterinary products, substances, and transparency data. Use for FDA adverse events, recalls, labeling, approvals, shortages, 510(k) clearances, NDC lookups, and any FDA safety or regulatory data query across all 28 API endpoints.
The English summary is being prepared. Showing the original description.