LLMapper
Turns articles or text into focused concept maps via a 4-stage LLM pipeline
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 25, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Jul 30, 2026 · 9da4ebe
⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 25, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.
Mapped a short honeybee/colony-collapse passage both ways: the no-skill baseline gave a 7-node graph with mostly unlabeled 'has/includes' edges and no chosen angle, while the pipeline forced a focusing question, 10 plain-English concepts and 20+ labeled triples with strong verbs (threatens, fertilizes, depends-on), then saved a styled Mermaid file. The extra structure and the RDF-first edit path are a clear, repeatable win over an ad-hoc map. All five prompt files resolve and the install ran verbatim from a bare HOME.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 8/10
- Docs & honesty 5/5
What LLMapper does
Generates Mermaid concept maps from an uploaded file, a URL, or pasted text using a four-stage pipeline: user-chosen focusing question, panel-of-experts summarization, an RDF knowledge graph, then a styled diagram saved to /tmp. Triggers when you ask to map, visualize, or knowledge-graph the concepts in an article. Keeps the RDF as the source of truth so follow-up edits regenerate the map cleanly.
How to install LLMapper
Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.
Commands — how to trigger LLMapper
-
/llmapperTurns articles or text into focused concept maps via a 4-stage LLM pipeline
It also activates on plain-language prompts like these:
-
Turn this article into a focused Mermaid concept map -
Make a knowledge graph of the key concepts in this PDF -
Visualize the ideas in this pasted text as a concept map
Frequently asked questions
- Is the LLMapper skill free?
- Yes. The skill itself is free from jorgearango/llmapper-skill. SkillProof publishes the install command and an independent test verdict at no cost.
- Does LLMapper work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 25, 2026. Verdict: Tested · Works. Mapped a short honeybee/colony-collapse passage both ways: the no-skill baseline gave a 7-node graph with mostly unlabeled 'has/includes' edges and no chosen angle, while the pipeline forced a focusing question, 10 plain-English concepts and 20+ labeled triples with strong verbs (threatens, fertilizes, depends-on), then saved a styled Mermaid file. The extra structure and the RDF-first edit path are a clear, repeatable win over an ad-hoc map. All five prompt files resolve and the install ran verbatim from a bare HOME.
- What is the LLMapper SkillProof Score?
- 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
- How do I install LLMapper?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use LLMapper with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.