Loading...
Loading...
Found 1,204 Skills
Extract text from PDFs as structured, semantic Markdown. Use when converting a PDF to Markdown, extracting text from a PDF, processing one or more PDFs into Markdown output, reading PDF contents for analysis, ingesting documents for RAG pipelines, preparing PDFs for LLM context, or any task where PDF text needs to be in a machine-readable format. ALWAYS use this skill when the user has a PDF and needs its content as text or Markdown — even if they don't explicitly say "convert to markdown".
Use when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature.
Install and configure LLMem for an agent harness. Handles CLI install, plugin deployment, skill registration, and provider setup. Triggers on: "install llmem", "set up memory", "configure memory", "add llmem to harness", "memory setup".
Script-First llms.txt generator. Uses a deterministic script to crawl the project structure, identify brand guides, and catalog content files. Provides a repo manifest for the agent to draft context-aware /llms.txt and /llms-full.txt files.
Browser automation MCP server using Playwright's accessibility tree for LLM-friendly web interaction
Structured learning roadmap for AI Agent development from LLM basics to multi-agent systems (bilingual Chinese/English)
Run, monitor, analyze, and debug LLM evaluations via nemo-evaluator-launcher. Covers running evaluations, checking status and live progress, debugging failed runs, exporting artifacts and logs, and analyzing results. ALWAYS triggers on mentions of running evaluations, checking progress, debugging failed evals, analyzing or analysing runs or results, run directories or artifact paths on clusters, Slurm job issues, invocation IDs, or inspecting logs (client logs, server logs, SSH to cluster, tail logs, grep logs). Do NOT use for creating or modifying evaluation configs.
Multi-platform public opinion analysis assistant with web scraping, LLM-powered analytics, topic clustering, sentiment analysis, and multi-channel alerts
Build and maintain a Karpathy-style LLM knowledge base — a self-compiling Obsidian markdown wiki where an Agent ingests raw sources, compiles cross-linked concept/entity/summary pages, answers queries against the corpus, lints the graph for health, and audits in-context human feedback filed from Obsidian or the local web viewer. Use when (1) scaffolding a new knowledge base for any research topic, (2) ingesting articles/papers/PDFs/web pages into raw/, (3) compiling or restructuring wiki articles from existing raw material, (4) answering questions against the wiki and filing durable answers back, (5) running lint passes for dead links / orphan pages / coverage gaps / audit shape, (6) processing human feedback from the audit/ directory and applying corrections. Not for general note-taking, daily journals, or non-wiki Obsidian use.
Generates llms.txt and llms-full.txt files for LLM-friendly project documentation following the llms.txt specification. Use when the user wants to create LLM-readable summaries, llms.txt files, or make their wiki accessible to language models.
Run an autonomous Humanize-governed SGLang SOTA performance loop for one LLM model: first perform the fixed fair SGLang/vLLM/TensorRT-LLM deployment search and benchmark, then start one RLCR loop that repeatedly decides the gap, profiles the current bottleneck, runs layer/kernel pipeline analysis, patches SGLang code, optionally uses ncu-report-skill for kernel evidence, and revalidates until SGLang matches or beats the best observed framework under the same workload and SLA.