Showing 58111–58140 of 77205 skills
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
orlandoneto/agent-skills
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
orlandoneto/agent-skills
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework
orlandoneto/agent-skills
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.
orlandoneto/agent-skills
React useEffect best practices from official docs. Use when writing/reviewing useEffect, useState for derived values, data fetching, or state synchronization. Teaches when NOT to use Effect and better alternatives.
orlandoneto/agent-skills
Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.
orlandoneto/agent-skills
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
orlandoneto/agent-skills
Analyze product screenshots to extract feature lists and generate development task checklists. Use when: (1) Analyzing competitor product screenshots for feature extraction, (2) Generating PRD/task lists from UI designs, (3) Batch analyzing multiple app screens, (4) Conducting competitive analysis from visual references.
orlandoneto/agent-skills
This skill should be used when the user asks to "create a Telegram bot", "build a Telegram chatbot", "set up a Telegram webhook", "add inline keyboards to a bot", "handle Telegram callback queries", "implement Telegram payments", "send media via Telegram bot", "configure Telegram bot commands", "deploy a Telegram bot", or mentions the Telegram Bot API, telegram bot tokens, getUpdates, setWebhook, or bot frameworks like node-telegram-bot-api, grammy, python-telegram-bot, or aiogram. Provides comprehensive guidance for building production-ready Telegram bots with Node.js and Python.
orlandoneto/agent-skills
You MUST use this before writing or changing any production code, including one-line fixes and when the user is in a hurry: a new feature, a bug fix, a refactor, a behavior change. Write the failing test first, run it and watch it fail for the right reason, write the minimal code that passes, then run the whole test suite before saying it is done. Skip it only for throwaway prototypes, generated code or configuration-only changes, and only with the user's OK.
orlandoneto/agent-skills
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.
orlandoneto/agent-skills
Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.
orlandoneto/agent-skills
anyshift-io/sre-skills
anyshift-io/sre-skills
Scan Alex's Gmail for new job leads (NorthStar Staffing/Jordan, LinkedIn job alerts, MyJobHelper), screen them for fit, and log new candidates to the Job Search Tracker. Cloud-only — runs on the daily schedule, no computer/browser needed.
esscott1/job-search-assistant
On-demand deep-dive: fetch the real job description for one or more tracker rows (especially LinkedIn/MyJobHelper leads) using Alex's own signed-in browser, and upgrade the row's fit score and gaps from Tier 1 to a full read. Run only when Alex asks, or when he's at his computer.
esscott1/job-search-assistant
Scan Alex's Gmail for new job leads (NorthStar Staffing/Jordan, LinkedIn job alerts, MyJobHelper), screen them for fit, and log new candidates to the Job Search Tracker. Cloud-only — runs on the daily schedule, no computer/browser needed.
esscott1/job-search-assistant
On-demand deep-dive: fetch the real job description for one or more tracker rows (especially LinkedIn/MyJobHelper leads) using Alex's own signed-in browser, and upgrade the row's fit score and gaps from Tier 1 to a full read. Run only when Alex asks, or when he's at his computer.
esscott1/job-search-assistant
Scan Alex's Gmail for new job leads (NorthStar Staffing/Jordan, LinkedIn job alerts, MyJobHelper), screen them for fit, and log new candidates to the Job Search Tracker. Cloud-only — runs on the daily schedule, no computer/browser needed.
esscott1/job-search-assistant
On-demand deep-dive: fetch the real job description for one or more tracker rows (especially LinkedIn/MyJobHelper leads) using Alex's own signed-in browser, and upgrade the row's fit score and gaps from Tier 1 to a full read. Run only when Alex asks, or when he's at his computer.
esscott1/job-search-assistant
Scan Alex's Gmail for new job leads (NorthStar Staffing/Jordan, LinkedIn job alerts, MyJobHelper), screen them for fit, and log new candidates to the Job Search Tracker. Cloud-only — runs on the daily schedule, no computer/browser needed.
esscott1/job-search-assistant
On-demand deep-dive: fetch the real job description for one or more tracker rows (especially LinkedIn/MyJobHelper leads) using Alex's own signed-in browser, and upgrade the row's fit score and gaps from Tier 1 to a full read. Run only when Alex asks, or when he's at his computer.
esscott1/job-search-assistant
Scan Alex's Gmail for new job leads (NorthStar Staffing/Jordan, LinkedIn job alerts, MyJobHelper), screen them for fit, and log new candidates to the Job Search Tracker. Cloud-only — runs on the daily schedule, no computer/browser needed.
esscott1/job-search-assistant
On-demand deep-dive: fetch the real job description for one or more tracker rows (especially LinkedIn/MyJobHelper leads) using Alex's own signed-in browser, and upgrade the row's fit score and gaps from Tier 1 to a full read. Run only when Alex asks, or when he's at his computer.
esscott1/job-search-assistant
Scan Alex's Gmail for new job leads (NorthStar Staffing/Jordan, LinkedIn job alerts, MyJobHelper), screen them for fit, and log new candidates to the Job Search Tracker. Cloud-only — runs on the daily schedule, no computer/browser needed.
esscott1/job-search-assistant
On-demand deep-dive: fetch the real job description for one or more tracker rows (especially LinkedIn/MyJobHelper leads) using Alex's own signed-in browser, and upgrade the row's fit score and gaps from Tier 1 to a full read. Run only when Alex asks, or when he's at his computer.
esscott1/job-search-assistant
Scan Alex's Gmail for new job leads (NorthStar Staffing/Jordan, LinkedIn job alerts, MyJobHelper), screen them for fit, and log new candidates to the Job Search Tracker. Cloud-only — runs on the daily schedule, no computer/browser needed.
esscott1/job-search-assistant
On-demand, requires Alex's computer: for tracker rows job-lead-tier2-scoring flagged as unreachable by web search (LinkedIn postings with no JD body, sites that block fetch), read the real JD using Alex's own browser session and update the row.
esscott1/job-search-assistant
Cloud-only, cron-friendly: for tracker rows still tagged Tier 1, search the open web and fetch the real JD from company/ATS pages (never LinkedIn directly), then score and update the row. Rows it can't resolve get flagged in Notes recommending job-lead-manual-jd-lookup.
esscott1/job-search-assistant
Scan Alex's Gmail for new job leads (NorthStar Staffing/Jordan, LinkedIn job alerts, MyJobHelper), screen them for fit, and log new candidates to the Job Search Tracker. Cloud-only — runs on the daily schedule, no computer/browser needed.
esscott1/job-search-assistant