notemdpro
Skill2 starsChanged 38 days agoMITView on GitHub
NoteMD Pro skill pack for markdown knowledge workflows: linking, generation, research, translation, concept extraction, diagram generation, and syntax healing.
In this repository15 other files it gives its agents.
- batch-processorSkill
- concept-extractorSkill
- content-generatorSkill
- diagram-generatorSkill
- formula-healerSkill
- link-analyzerSkill
- mermaid-healerSkill
- mermaid-summarizerSkill
- qa-extractorSkill
- selection-processorSkill
- system-architectureSkill
- test-driven-developmentSkill
- text-translatorSkill
- web-researcherSkill
- workflow-runnerSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
Use this file as the top-level router to select the correct skill folder.
- Very specific: line 16
Add wiki-links to existing notes -> skills/link-analyzer/SKILL.md
- Very specific: line 37
Run workflows over many files safely -> skills/batch-processor/SKILL.md
- Distinctive: line 78
Keep workflows file-system agnostic: avoid direct Obsidian API assumptions when running outside plugin runtime.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
NoteMD Pro - Skill Router
Overview
notemdpro is a portable skill library that mirrors modern NotEMD workflows for non-Obsidian runtimes.
Use this file as the top-level router to select the correct skill folder.
Workflow Decision Tree
Content + Knowledge Graph
- Add wiki-links to existing notes ->
skills/link-analyzer/SKILL.md - Generate long-form content from title/topic ->
skills/content-generator/SKILL.md - Extract core concepts from documents ->
skills/concept-extractor/SKILL.md - Process a selected excerpt instead of full file ->
skills/selection-processor/SKILL.md
Research + Translation
- Perform web research and summarize findings ->
skills/web-researcher/SKILL.md - Translate documents while preserving markdown ->
skills/text-translator/SKILL.md
Diagram Workflows
- Summarize document into Mermaid mindmap ->
skills/mermaid-summarizer/SKILL.md - Generate canonical diagram flow:
generate-diagram->skills/diagram-generator/SKILL.md - Legacy compatibility alias (NotEMD parity):
generate-experimental-diagram-> normalize togenerate-diagram - Preview command parity reference:
preview-diagram(UI/runtime-specific in plugin; keep as conceptual action in skill docs)
Syntax Healing
- Validate Mermaid and conservatively repair invalid flowcharts ->
skills/mermaid-healer/SKILL.md - Heal LaTeX math formatting ->
skills/formula-healer/SKILL.md
Extraction + Batch
- Extract Q&A or targeted passages ->
skills/qa-extractor/SKILL.md - Run workflows over many files safely ->
skills/batch-processor/SKILL.md - Compose stages with complete task diagnostics ->
skills/workflow-runner/SKILL.md
Architecture + Engineering
- Understand system composition and call chains ->
skills/system-architecture/SKILL.md - Apply TDD workflow for new changes ->
skills/test-driven-development/SKILL.md
Skills Index
| Skill Folder | Purpose |
skills/link-analyzer | Add/update [[wiki-links]] in markdown |
skills/content-generator | Generate technical markdown from title/topic |
skills/web-researcher | Web research + synthesis |
skills/text-translator | Translate markdown content |
skills/concept-extractor | Extract concept nodes for graph building |
skills/qa-extractor | Extract answers from reference text |
skills/selection-processor | Process selected text spans only |
skills/mermaid-summarizer | Create Mermaid summary diagrams |
skills/diagram-generator | Preserve semantic coverage and check export capabilities |
skills/workflow-runner | Retain task-wide stage outcomes and severity-separated diagnostics |
skills/mermaid-healer | Repair Mermaid syntax |
skills/formula-healer | Repair LaTeX syntax |
skills/batch-processor | Batch execution patterns |
skills/system-architecture | Runtime architecture map |
skills/test-driven-development | TDD planning and execution |
Prompt Variable Reference
| Variable | Typical Use |
{TITLE} | Title-driven generation |
{LANGUAGE} | Translation/target output language |
{TEXT} | Raw content payload |
{REFERENCE_CONTENT} | Reference corpus for extraction |
{USER_INPUT} | Query/question payload |
{TOPIC} | Research topic |
{SEARCH_RESULTS_CONTEXT} | Search snippets/context |
Notes
- Keep workflows file-system agnostic: avoid direct Obsidian API assumptions when running outside plugin runtime.
- For diagram command migration, prefer canonical action naming (
generate-diagram,preview-diagram) and keep legacy alias compatibility where needed.
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
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.