agentleFS
danicatdanicat/speedgrapher/llms.txt

speedgrapher

llms.txt51 starsChanged 17 days agoApache-2.0View on GitHub

Open-source technical writing assistant, side-panel Markdown editor, Model Context Protocol (MCP) server, and Agent Skills suite for Google Antigravity. Measures Gunning Fog readability, detects synthetic AI slop tropes, mitigates status-signaling corporate jargon, lints grammar with Vale, and audits technical SEO and Generative Engine Optimization (GEO). This file provides a curated, token-efficient Markdown index for Large Language Models (LLMs), AI search engines, and coding agents.

Files
llms.txt
# Speedgrapher

> Open-source technical writing assistant, side-panel Markdown editor, Model Context Protocol (MCP) server, and Agent Skills suite for Google Antigravity. Measures Gunning Fog readability, detects synthetic AI slop tropes, mitigates status-signaling corporate jargon, lints grammar with Vale, and audits technical SEO and Generative Engine Optimization (GEO).

This file provides a curated, token-efficient Markdown index for Large Language Models (LLMs), AI search engines, and coding agents.

## Core Documentation
- [README.md](README.md): Architecture overview, installation guide, four-mode sidecar panel walkthrough (`Reader`, `Editor`, `Reviewer`, and `Raw`), MCP server tools (`fog`, `slop`, `vale`, and `seo`), and CLI usage.
- [Agent Rules (`rules/AGENTS.md`)](rules/AGENTS.md): Workspace rules for opening the Speedgrapher side panel, handling inline `<!-- review: ... -->` HTML comments, and routing writing tasks.
- [Plugin Manifest (`plugin.json`)](plugin.json): Antigravity plugin configuration, version metadata, and suggested prompts.
- [MCP Server Configuration (`mcp_config.json`)](mcp_config.json): Stdio MCP server launch definition for `speedgrapher mcp`.

## Writing Lifecycle Agent Skills
- [Speedgrapher Side Panel & Orchestrator (`skills/speedgrapher/SKILL.md`)](skills/speedgrapher/SKILL.md): Master orchestrator skill for launching the side panel, resolving inline review comments, and coordinating multi-stage writing workflows.
- [Socratic Ideation & Inverted Pyramid Outlining (`skills/ideate/SKILL.md`)](skills/ideate/SKILL.md): One-question-at-a-time technical interviewing workflow and inverted-pyramid outline generator for blog posts, `README.md` files, and `SKILL.md` files.
- [Adaptive-Voice Technical Drafting (`skills/draft/SKILL.md`)](skills/draft/SKILL.md): Technical drafting workflow enforcing voice fingerprinting, 150-word outcome leads, why-before-how code pedagogy, and sentence-case headings.
- [Readability, Jargon Mitigation & Deslopification (`skills/readability/SKILL.md`)](skills/readability/SKILL.md): Copyediting workflow grounded in the Harvard Business Review jargon study and five-dimension AI slop elimination.
- [Tropes & Jargon Reference (`skills/readability/references/tropes-and-jargon.md`)](skills/readability/references/tropes-and-jargon.md): Diagnostic tables of synthetic AI lexical/structural tells and status-signaling corporate jargon replacements.
- [Editorial Review & Technical SEO/GEO Publishing (`skills/publish/SKILL.md`)](skills/publish/SKILL.md): Two-stage release gate for inline review annotations, line-indexed editorial scorecards, dual-purpose `summary` vs. `description` metadata, GEO citability, and localization.

## Go MCP Tools & Packages
- [CLI & MCP Entrypoint (`cmd/speedgrapher/main.go`)](cmd/speedgrapher/main.go): Go binary supporting `speedgrapher mcp`, `speedgrapher audit`, `speedgrapher call`, and `speedgrapher version`.
- [Gunning Fog & HBR Jargon Analyzer (`internal/tools/fog/fog.go`)](internal/tools/fog/fog.go): Document and per-paragraph Gunning Fog readability index, complex word spans, unexpanded acronym detector, and status-signaling jargon analyzer.
- [AI Slop Detector (`internal/tools/slop/slop.go`)](internal/tools/slop/slop.go): Calibrated five-dimension synthetic prose detector measuring structural clichés, lexical tells, filler words, sentence rhythm variance, and passive/nominalized voice.
- [Vale Grammar Linter & Rule Manager (`internal/tools/vale/vale.go`)](internal/tools/vale/vale.go): Static style and grammar linter using `Google`, `proselint`, and `write-good` rule sets, with live `.vale.ini` rule toggling and custom vocabulary management in [`internal/tools/vale/rules.go`](internal/tools/vale/rules.go).
- [Technical SEO & GEO Analyzer (`internal/tools/seo/seo.go`)](internal/tools/seo/seo.go): HTML, Markdown, and Hugo auditor checking titles, `summary` vs. `description` metadata split, inverted-pyramid lead blocks, heading hierarchy, image `alt` text, and link hygiene.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.