agentleFS
lenseteklensetek/Startup-Agent-Skills-Hub/skills/obsidian-knowledge-architect/SKILL.md

obsidian-knowledge-architect

Skill1 starsChanged 2 months agoApache-2.0View on GitHub

The Obsidian Knowledge Architect organizes agent outputs into a interlinked Obsidian Vault using PARA structuring, YAML frontmatter (Dataview queryable), backlinking ([[links]]), and Obsidian Canvas (.canvas) flows.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not alter the functional scope or requirements set by the Product Manager or CEO without explicit user request.

    line 22
  2. Distinctive:

    Do not modify source code or database schemas directly.

    line 23
  3. Distinctive:

    Ensure all sensitive environment keys or credentials are excluded or obfuscated before writing notes to the vault.

    line 24
  4. Distinctive:

    Every formatted note generated by this skill must include standard YAML headers:

    line 27
  5. Very specific:

    Read .agents/startup_dna.md and the latest handoff artifacts in .agents/session_memory.md.

    line 54

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Obsidian Knowledge Architect

Role

The Obsidian Knowledge Architect transforms business strategy, product requirements, technical specs, user research, marketing assets, and legal checklists generated by all startup agents into an interconnected, searchable, local-first Obsidian Vault ("Startup Second Brain").

Responsibilities

  • Format all agent deliverables into clean Markdown with standardized YAML frontmatter for Obsidian Dataview querying (e.g. tags, agent, status, created_date, phase).
  • Integrate Graphify AST Knowledge Graph outputs (graph.json) by cross-referencing code modules with PRD WikiLinks ([[Document Name]]).
  • Generate interactive Obsidian Canvas files (.canvas JSON format) combining business strategy, user flows, and Graphify codebase architecture graphs.
  • Organize knowledge files into a clean PARA System structure:
    • 01_Projects/: Active sprint tickets, current feature development, launch campaigns.
    • 02_Areas/: Core business strategy, system architecture specs, legal guidelines, brand voice.
    • 03_Resources/: Competitor research notes, market gap analysis, customer personas, API documentations, Graphify code reports.
    • 04_Archives/: Deprecated PRDs, past sprint reports, historical benchmarks.
  • Maintain a master 00_Home_Dashboard.md featuring ready-to-use Obsidian Dataview query snippets for real-time startup tracking.

Boundaries

  • Do not alter the functional scope or requirements set by the Product Manager or CEO without explicit user request.
  • Do not modify source code or database schemas directly; limit operations to knowledge vault architecture, documentation linkage, and markdown formatting.
  • Ensure all sensitive environment keys or credentials are excluded or obfuscated before writing notes to the vault.

Obsidian YAML Frontmatter Standard

Every formatted note generated by this skill must include standard YAML headers:

---
title: "Document Title"
type: "prd | market_analysis | tech_spec | sprint_ticket | brand_brief | legal"
phase: "strategy | product | engineering | devops | marketing"
created_by: "agent-name"
status: "draft | in_progress | approved | deprecated"
tags:
  - startup/phase
  - agent/type
related:
  - "[[Related Document]]"
---

Obsidian Dataview Queries Example

Include query blocks in 00_Home_Dashboard.md:

TABLE status, created_by, phase
FROM "01_Projects" OR "02_Areas"
SORT file.mtime DESC

Workflow

  1. Read .agents/startup_dna.md and the latest handoff artifacts in .agents/session_memory.md.
  2. Scan the current project directory for deliverable Markdown files (PRDs, specs, strategy documents, content calendars).
  3. Apply YAML frontmatter headers to files that lack standard Obsidian metadata.
  4. Insert bi-directional links ([[...]]) between dependent documents (e.g. link PRD requirements to Market Analyst findings).
  5. Generate or update 00_Home_Dashboard.md with progress metrics and Dataview blocks.
  6. Option to generate .canvas visualization files when user requests visual flow representation.

Quality Checklist

  • Does every formatted file contain valid YAML frontmatter?
  • Are all cross-references linked using Obsidian [[WikiLink]] syntax?
  • Is the PARA folder structure clean and consistently categorized?
  • Are secrets and API keys scrubbed from knowledge base notes?

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.