227 skills · sorted by relevance
Use Fictiv in a browser to upload CAD parts, configure manufacturing requirements, compare prices and lead times, and review manufacturability feedback. Supports authorized ordering, payment workflows, order tracking, reordering, and troubleshooting upload or checkout problems.
Improve workflows involving multiple AI agents by measuring bottlenecks, adjusting workload distribution, and managing model costs. This design guide helps compare changes against a measured baseline while checking quality, latency, and resource use.
Write and edit system prompts, tool instructions, and agent definitions with clear structure and explicit rule strength. It guides tag use, placement of critical constraints, concise wording, and practical examples that show how tools should be used.
Parse Windows Prefetch files, which store traces of program execution, to extract run counts, timestamps, and referenced files. Build execution timelines and compare findings with other forensic evidence when investigating suspicious software or tool usage.
Compress LLM weights using HQQ quantization, which stores weights with fewer bits without calibration datasets. Follow workflows for precision settings, model saving, inference integration, and LoRA fine-tuning of quantized models.
Compress large language models to 4-bit weights to reduce GPU memory use and accelerate inference. Covers loading compressed models, configuring quantization, and using Transformers or vLLM, with guidance on hardware requirements and backend choices.
Audit instructions and memory files loaded on every agent turn. Identify repeated rules, contradictions, outdated content, and material better moved into skills, then receive evidence-backed recommendations ranked by estimated token savings and change risk.
Install rtk in NanoClaw agent containers to compress development command output and reduce token use. A Claude Code hook automatically routes Bash calls through rtk, with runtime checks to verify installation and a command to inspect savings.
Helps write and review Nginx configurations for websites and APIs. Covers forwarding requests to application servers, distributing traffic, HTTPS settings, caching, compression, and logs to support performance tuning and investigation of slow responses.
Write and review launch prompts for agents working autonomously for hours or days. Define successful deliverables, excluded partial results, stopping rules, worker handoffs, and evidence-based review requirements so completion can be assessed against explicit criteria.
Design how an AI agent edits its own working conversation history, choosing what to retain, rewrite, or remove. Covers safeguards, capacity monitoring, recovery after overflow, and the computing cost of changing earlier context.
Design persistent agent memory that retains knowledge across sessions and retrieves relevant facts when needed. Compare storage approaches, track people and changing information, and plan memory consolidation and evaluation based on the kinds of questions the agent must answer.
Plan and improve AI agent systems by managing the information models receive. This collection covers memory, agent coordination, tool design, context compression, evaluation, and the operating controls needed for reliable autonomous workflows.
Use Memori through MCP, a protocol connecting agents to tools, to retrieve past decisions and preferences, summarize ongoing work, and resume after conversation compression. It also guides selective long-term memory storage and usage limit checks.
Create a source-linked rollup of a selected batch of Obsidian wiki log entries. Preview the complete draft while preserving original entries and child pages, then optionally apply the rollup and its index updates together.
Build distributable CARLA releases or asset packages containing selected maps and props. It prepares content for runtime use, checks output files, supports destination changes, and preserves native ROS 2 support when explicitly enabled.
Compress large language models to 4-bit weights to reduce GPU memory needs and accelerate text generation. Covers loading compressed models, converting your own models, choosing settings, and preparing memory-efficient fine-tuning with transformers and PEFT.
Apply HQQ quantization, which stores language model weights using fewer bits without calibration examples. Covers precision settings, inference backends, saving compressed models, deployment with HuggingFace Transformers or vLLM, and further training with LoRA.
Compress large language model weights to four bits with AWQ, a method that uses model activation patterns to limit quality loss. Follow workflows for quantization, loading compressed models, and serving them with vLLM using less GPU memory.
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.
Handle failed video encoding by checking available encoders, testing a short clip, and trying alternatives. The workflow covers copying without re-encoding, switching codecs, which define video compression, and using MoviePy as another processing option.
Audit TLS/SSL, the technology that encrypts network connections, across servers and mobile apps. The skill covers outdated protocols, weak encryption, certificate validation failures, known vulnerabilities, and replay risks, helping organize evidence and prioritize fixes.
Prepare 3D models for browser games by cleaning source assets, exporting GLB or glTF, and optimizing geometry and textures. It also guides collision shapes, distance-based detail levels, and runtime checks for the chosen engine.
Clean up completed research folders by identifying temporary and intermediate files for confirmed removal. Preserve papers, final findings, screening history, and methodology records, then check that essential files remain intact and report the space recovered.