398 skills · sorted by relevance
Design document processing pipelines for extraction and routing. TRIGGERS - Use when user needs help with ai-document-processor related tasks.
The English summary is being prepared. Showing the original description.
Build AI audio processing pipelines. TRIGGERS - Use when user needs help with ai-audio-processor related tasks.
The English summary is being prepared. Showing the original description.
Build AI batch processing systems for scale. TRIGGERS - Use when user needs help with ai-batch-processor related tasks.
The English summary is being prepared. Showing the original description.
Create a new find-XXXX preprocessor Python script from scratch (no existing SKILL.md), add configs/<GAMEVER>.yaml skill and symbol entries. Covers xref-string-based and LLM_DECOMPILE-based discovery patterns. Use when a GitHub issue or user instruction specifies a new function to find.
The English summary is being prepared. Showing the original description.
Convert an existing find-XXXX SKILL.md into a preprocessor Python script, updating configs/<GAMEVER>.yaml and removing the old SKILL.md. Covers xref-string-based and LLM_DECOMPILE-based discovery patterns.
The English summary is being prepared. Showing the original description.
Helps contributors develop and fix Airflow’s Java SDK for JVM tasks. Explains public API boundaries, JAR packaging, Python coordination, communication schema updates, and the test commands used to validate changes.
Create breadboard layout diagrams with HTML5 Canvas to show electronic components and wire connections. Use the skill for LED circuits, 555 timers, and 6502 computer projects, with component references, labels, and color-coded wiring.
Deploy and configure Snort 3 to detect suspicious network traffic. Create custom detection rules, tune community rules to reduce false alerts, test them against captured traffic, and forward alerts to a central security monitoring platform.
Turns sales and stock data into a reorder plan with quantities, costs, and estimated stockout dates. Prepares supplier purchase orders, email drafts, and accounting memos for later invoice checks, while flagging slow stock and requiring approval before sending.
Process vendor bills, assign accounting categories, check cash forecasts, and prepare a payment run for approval. Separate approvals for recording bills and paying them help owners review both the accounting entries and the proposed spending.
Prepare accountant review materials from closed books: US quarterly estimated tax calculations or year-end contractor payment lists. The output records assumptions, flags missing W-9 forms containing taxpayer details, and highlights payment processor records that need review.
Coordinate month-end reconciliation, owner sign-off, and a 30/60/90-day cash forecast based on closed books. Combine the results into a reporting packet with financial explanations and open items, with approval required before external delivery.
Process vendor bills from email, PDFs, or photos into proposed accounting entries and a payment plan. Checks duplicates, assigns accounts and jobs, matches purchase and receiving records, and requires separate approval for ledger entries and payments.
Finds the base image needed to create a custom GKE node image. It translates requirements such as GKE version, operating system, processor architecture, accelerators, and sandbox settings into a matching image name.
Explore computer architecture and circuit design settings by repeatedly running programs, measuring results, and adjusting parameters. Compare configurations against a baseline, respect design constraints, and receive a report with the best configuration found and the search history.
Explore hardware and electronic design configurations by repeatedly running programs, measuring results, and adjusting parameters. Track constraints and every trial, then report the best configuration found within the time and iteration limits.
Optimize and troubleshoot MNN's Hexagon DSP backend, which runs computation on a dedicated processor. The workflow uses device measurements to identify bottlenecks, compare v79 and v81 architectures, verify correctness, and investigate crashes or memory usage.
Diagnose errors and incorrect inference results in MNN's QNN backend for Qualcomm HTP processors. Compare intermediate calculation data against CPU results to locate the first faulty operator, distinguish bugs from precision limits, and guide operator support and performance fixes.
Review a data processing agreement against internal review standards, using the appropriate criteria for your company's role. Receive a clause-by-clause memo with risks, proposed edits, fallback positions, and inconsistencies with privacy policy commitments.
Review SaaS subscription terms against your team's standards, covering renewals, price increases, data export, and service availability commitments. Examine AI training rights and liability, with findings rated for both legal risk and business impact.
Convert, resize, and compress videos and images, including batches of files. Combine steps such as scaling and compression, specify output formats and quality settings, and check that the resulting files match the requested parameters.
Add a white, twinkling dotted trail that follows the mouse behind website content. The skill guides WebGPU rendering, which uses the graphics processor, with static backgrounds for unsupported devices and accessibility preferences.
Assess file upload and import features for weaknesses in file checks and processing. The skill covers extension and content-type bypasses, unsafe image and document handling, archive extraction flaws, and evidence needed to confirm execution or browser-side impact.
Prepare research papers for RAG, a method that supplies retrieved documents to AI. Download PDFs, extract and split text, and build a local searchable database, with parallel processing for document batches.