Graham
Community@grahama1970 · Buffalo, NY
Applied research engineering for agentic systems — multi-agent orchestration, self-improving skills, verified autonomy. No claim ships without a receipt.
Agent Skills by Graham
Showing 21 vetted skills indexed across 1 GitHub repositories.
grahama1970brave-search
Retrieve raw Brave Search web and local results via API.
grahama1970doc-to-qra
Convert PDFs, URLs, and text inputs into in-memory QRA pairs.
grahama1970treesitter
Parse source files to extract functions, classes, and symbols into structured JSON.
grahama1970agent-inbox
Sends, lists, reads, and acknowledges messages between projects via a local JSON inbox.
grahama1970memory
Query a memory store for prior solutions before scanning a codebase.
grahama1970youtube-transcripts
Extract YouTube video transcripts via API, proxy, and Whisper fallbacks.
grahama1970context7
Fetch current library documentation from the Context7 API via CLI.
grahama1970code-review
Coordinates GitHub Copilot, Claude, Codex, Gemini APIs to generate unified diffs from review requests.
grahama1970edge-verifier
Audit relationships between new content and Knowledge Graph nodes using LLM scoring.
grahama1970episodic-archiver
Embed conversation turns and store them in ArangoDB for search and retrieval.
grahama1970fetcher
Fetch web pages and PDFs with content extraction and structured exports.
grahama1970distill
Convert PDFs, URLs, or text into memory-ready Q&A pairs.
grahama1970assess
Identify drift between user intent and project reality through collaborative assessment.
grahama1970perplexity
Fetch real-time web search results with citations via the Perplexity API.
grahama1970surf
Control Chrome via CLI to open URLs, click elements, and type forms.
grahama1970scillm
Automate batch LLM calls and Lean4 theorem proving with JSON workflows.
grahama1970skills-sync
Sync local skills with an upstream agent-skills repository via rsync.
grahama1970arxiv
Fetch arXiv paper metadata and PDFs via CLI queries.
grahama1970pdf-fixture
Generate deterministic PDF fixtures from JSON or inline specs for testing extraction pipelines.
grahama1970qra
Extract grounded question–reasoning–answer items from text with optional domain context.
grahama1970runpod-ops
Provision, manage, and terminate RunPod GPU instances for LLM workflows.