master-plan-builder
Skill0 starsChanged 43 days agoMITView on GitHub
Use this skill when the user wants to compile, rebuild, or update the logical Master Plan index files of their Obsidian vault categories (such as AI Engineer or Machine Learning). Triggers include "update master plan", "rebuild master plan", "regenerate navigation map", "rebuild notes index".
In this repository68 other files it gives its agents.
- .agents/AGENTS.mdAGENTS.md
- ai-engineering-chip-huyenSkill
- ask-mattSkill
- book-to-skillSkill
- claude-handoffSkill
- codebase-designSkill
- code-reviewSkill
- daily-noteSkill
- diagnosing-bugsSkill
- domain-modelingSkill
- getContextSizeSkill
- git-guardrails-claude-codeSkill
- graphify-querySkill
- grillingSkill
- grill-meSkill
- grill-with-docsSkill
- handoffSkill
- implementSkill
- improve-codebase-architectureSkill
- knowledge-linkSkill
- knowledge-synthesisSkill
- loop-meSkill
- migrate-to-shoehornSkill
- note-captureSkill
- note-reviewSkill
- notion-curatorSkill
- obsidian-knowledge-curatorSkill
- okc-bookFlashcardsSkill
- okc-bookSummarySkill
- okc-diagnosticsAndSynchronizationSkill
- okc-docSkill
- okc-doctorSkill
- okc-driftSkill
- okc-emergeSkill
- okc-exploreSkill
- okc-findSkill
- okc-linterSkill
- okc-normalizeSkill
- okc-setupSkill
- okc-study-multichoiceSkill
- okc-studySkill
- okc-syncSkill
- okc-traceSkill
- okc-urlArticleSkill
- okc-urlPlaylistSkill
- okc-urlPodcastSkill
- okc-urlSpotifySkill
- okc-urlTwitterSkill
- okc-urlYoutubeSkill
- prototypeSkill
- researchSkill
- resolving-merge-conflictsSkill
- scaffold-exercisesSkill
- setup-matt-pocock-skillsSkill
- setup-pre-commitSkill
- setup-ts-deep-modulesSkill
- tddSkill
- teachSkill
- to-specSkill
- to-ticketsSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 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.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
Strictly use native tools: Never shell out to terminal commands.
- Very specific: line 16
Search and list all .md files in the raw/ folder of the target category recursively (e.g.
- Very specific: line 21
Read note content: Use view_file to inspect the contents.
- Distinctive: line 40
If file does not exist: Create a fresh Master Plan note using the vault's standard template (H1, Description, Notes table, Themes covered, …
- Very specific: line 41
If file exists: Read its contents and replace the table section dynamically between the ## Notes in this category header and the next …
≈ “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
Master Plan Builder Skill
Goal
Natively read curated notes in the raw/ directories, extract their metadata (Author, Date, Type, Category), and dynamically rebuild or update the navigation index table inside the respective Master Plan — <Category>.md file keylessly and prompt-free using native file tools.
Prerequisites
- Vault Directory Permissions: Recursively authorized.
- Strictly use native tools: Never shell out to terminal commands. Use native file tools.
Step 1 — Scan Curated Raw Notes
Search and list all .md files in the raw/ folder of the target category recursively (e.g. dataScienceKnowledgeBase/AI Engineer/raw or software engineer/raw):
- Ignore other Master Plans, outlines, or temporary files.
Step 2 — Parse Note Metadata (Zero-YAML Blockquotes)
For each note:
- Read note content: Use
view_fileto inspect the contents. - Parse Title: Extract the unique H1 title from the first line.
- Parse Blockquote Metadata: Locate the blockquote directly under the H1 title and extract:
- Channel/Author: From fields like
Channel/Author,Canal/Autor,Author,Autor. Clean up formatting. - Date/Published: From
Published,Publicado,Date,Fecha. - Content Type: From
Type,Tipo. - Category: Determined from the relative path under the
raw/zone (e.g.raw/Feature Engineering for Machine Learning/Section-08).
- Channel/Author: From fields like
Step 3 — Generate Index Table
Format the note metadata into a beautifully structured Markdown table. For example, for Machine Learning:
| Note / Link | Author | Date | Type | Section / Category |
| --- | --- | --- | --- | --- |
| [[FEML - 25 - Categorical Encoding Introduction]] | Carlos Ibarra | May 2026 | course note | raw/Feature Engineering for Machine Learning/Section-08 — Categorical Encoding Basic |Step 4 — Write to Master Plan File
Locate the Master Plan file (e.g., dataScienceKnowledgeBase/Machine Learning/Master Plan — Machine Learning.md):
- If file does not exist: Create a fresh Master Plan note using the vault's standard template (H1, Description, Notes table, Themes covered, and Related links).
- If file exists: Read its contents and replace the table section dynamically between the
## Notes in this categoryheader and the next section separator---. Usereplace_file_contentto execute this update silently.
Step 5 — Verify Changes
Natively read the updated Master Plan file to verify that all links are clickable, format is clean, and indices are aligned.
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.

