patientvibes-agents

A public catalog of skills, tools, and harnesses for AI agent work. Each entry's docs are pulled live from its source repo.

Skills

Tools

agent-tool-book-builder

dev

Renders Marker-OCR'd markdown into a typeset Kindle Scribe PDF (with annotation margins) plus an Obsidian-compatible markdown export. Handles chapters, images, blockquotes, figures.

tool

agent-tool-figure-scanner

dev

Scans source PDFs for figure / table / diagram references and produces a manifest of which were extracted and which are missing. Used by the kindle-pipeline harness as a pre-step before LLM proofreading.

tool

agent-tool-llm-proofreader

dev

LLM-powered OCR proofreading agent. Deterministic pre-pass surfaces likely-issue regions; langchain-openai (via OpenRouter) verifies and proposes fixes; a separate verifier subagent reviews each fix before it's applied. Persistent memory of known false positives accumulates across runs in `~/.local/state/agent-tool-llm-proofreader/memory.json` (Linux/macOS) or `%LOCALAPPDATA%\agent-tool-llm-proofreader\memory.json` (Windows).

tool

agent-tool-marker-cleanup

dev

Three deterministic CLIs for cleaning Marker OCR output before LLM proofreading. They run as a strip pipeline: `strip-marker-artifacts` → `strip-back-matter` → `clean-markdown`.

tool

agent-tool-pdf-builder

dev

Reportlab-based PDF builder library. Title pages, typography, margins, figure placeholders. Used as a library by `agent-tool-book-builder` (and as a smoke-test CLI for direct invocation).

tool

agent-tool-pr-reviewer

dev

CLI that reviews the current git branch's diff against a base ref using a single Pydantic AI call. Emits a typed `findings.json` plus a human-readable `review-output.md` under `<repo>/.ai-review/runs/<timestamp>/`.

tool

agent-tool-prose-quality

dev

Prose quality analyzer. Computes sentence-length stats, lexical density, and other readable signals over markdown / plain text.

tool

agent-tool-scrape-sources

dev

Fetches web essays / articles as clean markdown with YAML frontmatter (title, author, source URL, fetch date). Used by the kindle-pipeline harness as a source ingestion stage.

tool

Harnesses