Receber por email
← Voltar para o catálogo

Autor no catálogo

braxtonROSE4

123 skills 861 estrelas no total GitHub ↗

Skills publicadas

Mostrando 12 de 123

nano-pdf

7

Edit PDFs with natural-language instructions using the nano-pdf CLI. Modify text, fix typos, update titles, and make content changes to specific pages without manual editing.

Documentos #ai #pdf por braxtonROSE4

youtube-content

7

Fetch YouTube video transcripts and transform them into structured content (chapters, summaries, threads, blog posts). Use when the user shares a YouTube URL or video link, asks to summarize a video, requests a transcript, or wants to extract and reformat content from any YouTube video.

Escrita e Conteúdo #ai por braxtonROSE4

memento-flashcards

7

Spaced-repetition flashcard system. Create cards from facts or text, chat with flashcards using free-text answers graded by the agent, generate quizzes from YouTube transcripts, review due cards with adaptive scheduling, and export/import decks as CSV.

Dados e Análise #ai por braxtonROSE4

plan

7

Plan mode for Zorro — inspect context, write a markdown plan into the active workspace's `.zorro/plans/` directory, and do not execute the work.

Outros #ai #markdown por braxtonROSE4

requesting-code-review

7

Pre-commit verification pipeline — static security scan, baseline-aware quality gates, independent reviewer subagent, and auto-fix loop. Use after code changes and before committing, pushing, or opening a PR.

Segurança #ai por braxtonROSE4

github-pr-workflow

7

Full pull request lifecycle — create branches, commit changes, open PRs, monitor CI status, auto-fix failures, and merge. Works with gh CLI or falls back to git + GitHub REST API via curl.

Automação #ai #api por braxtonROSE4

distributed-llm-pretraining-torchtitan

7

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.

Outros #ai #llm por braxtonROSE4

axolotl

7

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

Design e Frontend #ai #llm por braxtonROSE4

apple-reminders

7

Manage Apple Reminders via remindctl CLI (list, add, complete, delete).

Outros #ai por braxtonROSE4

ascii-art

7

Generate ASCII art using pyfiglet (571 fonts), cowsay, boxes, toilet, image-to-ascii, remote APIs (asciified, ascii.co.uk), and LLM fallback. No API keys required.

Design e Frontend #ai #api por braxtonROSE4

subagent-driven-development

7

Use when executing implementation plans with independent tasks. Dispatches fresh delegate_task per task with two-stage review (spec compliance then code quality).

Produtividade #ai por braxtonROSE4

github-auth

7

Set up GitHub authentication for the agent using git (universally available) or the gh CLI. Covers HTTPS tokens, SSH keys, credential helpers, and gh auth — with a detection flow to pick the right method automatically.

Desenvolvimento #ai #git por braxtonROSE4