Total 55,731 skills
Showing 12 of 55731 skills
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.
Track engagement metrics, measure campaign ROI, and analyze content performance across Instagram, Facebook, YouTube, and TikTok.
Transmission Psychology Decoder. Given a piece of content, use 5 classic communication theories to decode why it resonates with the audience, analyze the underlying audience emotions and effective stance, and output discussion directions for chatrooms. Triggers: /dbs-spread, "Transmission Psychology Decoder", "Why did this go viral", "What do the audience want to hear", "What emotion does this content hit" Transmission psychology decoder. Given a piece of content, analyze the psychological mechanism that makes it resonate, identify the emotional core and effective stance, and output direction for chatroom discussion. Trigger: /dbs-spread, "why does this resonate", "what emotion does this hit", "decode this content"
Run a second round on a contested question by circulating each subagent's independent proposal to the other authors and asking for structured pros and cons, then synthesize. Use this skill whenever you have multiple independent proposals or opinions on a contested decision — architecture tradeoffs, code review disagreements, design choices, competing root-cause theories — and want sharper analysis than you'd produce by synthesizing alone. Pairs naturally with the council and research skills; reach for it liberally whenever proposals diverge.
Compare a pull request's implementation against spec context in spec_context.md and feed any material mismatches into review.json. Use during PR review when approved or repository spec context is available.
QA test a live website with Firecrawl browser and scrape evidence. Use when the user wants exploratory QA, form testing, navigation/link checks, responsive checks, performance observations, bug reports, or a pre-launch quality review.
Support for organising events/meetings and sending invitations by email.
Create or edit images with Pilio GPT Image 2 through the unified Pilio developer API. Use when the user wants text-to-image generation, prompt-based image editing, restyling, product-photo transformation, or composition from one or more local reference images.
Retrieve the status of the last diagnosis to continue using it. Use in conjunction with dbs-save. Trigger methods: /dbs-restore, /continue, "continue from last time", "previous conclusion", "where did we leave off in the last diagnosis" Restore the most recent diagnosis snapshot saved by dbs-save. Trigger: /dbs-restore, "continue from last time", "where did we leave off"
Content extraction for Chinese news sites. Supports WeChat Official Accounts, Toutiao, NetEase News, Sohu News, and Tencent News. Activated when users need to extract Chinese news content, crawl official account articles, scrape news, or obtain news in JSON/Markdown format.
TypeScript strict mode with eslint and jest
Extract text from images and scanned PDFs using OCR. Supports 100+ languages, table detection, structured output (markdown/JSON), and batch processing.