SKILLEMALL.ai
GitHub ↗ RU Sign in

DD obsidian-second-brain

Operate any Obsidian vault as a living, self-rewriting second brain (an evolution of Karpathy's LLM Wiki pattern: sources rewrite existing pages, contradictions reconcile automatically, scheduled agents maintain the vault while you sleep). Use this skill whenever the user asks Claude to read, write, update, search, or manage their Obsidian vault - including saving notes from conversation, creating daily entries, updating kanban boards, logging dev work, managing people notes, capturing decisions, tracking deals, or maintaining any vault structure. Also triggers when the user wants to bootstrap a new vault from scratch, run a vault health check, or drop a _CLAUDE.md into their vault so all Claude surfaces share the same operating rules. Also runs Crew (/crew): one shared logbook so Claude Code, Codex, Cursor, and Grok Bot know what each other did, in any plain folder or the vault. Includes a research toolkit (7 commands: /x-read, /x-pulse, /research, /research-deep, /notebooklm, /youtube, /podcast) for AI-powered research via Grok, Perplexity, NotebookLM, YouTube, and podcast feeds - findings save to the vault automatically following the AI-first vault rule. Use proactively whenever the conversation produces information worth preserving (decisions, people met, projects started, tasks completed, lessons learned, research findings).

eugeniughelbur/obsidian-second-brain Agent Skills author: eugeniughelbur MIT 80 files · 9 scripts body ≈ 22 270 tokens Open the sourcegithub.com↗ analyzed 7 h ago

Operate any Obsidian vault as a living, self-rewriting second brain (an evolution of Karpathy's LLM Wiki pattern: sources rewrite existing pages…

As a process D 46/100 · Unfinished process — References files that are not bundled: references/ai-first-rules.md, hooks/validate-ai-first.hook.yaml, references/claude-md-assistant-template.md

ProcedureObsidianYouTubeAI and agentsMedia and videotype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
D
64/100
safety, quality, tests
Safety 60%
91
Quality 40%
23
Run on models
none yet
Process rating
D
46/100
Unfinished process
References files that are not bundled: references/ai-first-rules.md, hooks/validate-ai-first.hook.yaml, references/claude-md-assistant-template.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. Shorten the description to 1024 characters.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  3. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 9

✓ No critical or high findings

Medium and low: 9
  • low Risky intent intent-offensive-security commands/obsidian-challenge.md:4
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
    triggers_en: ["challenge this", "grill me on this", "red team my idea", "stress test this"]
    quoted
  • low Risky intent intent-offensive-security commands/obsidian-challenge.md:7
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
    triggers_pt: ["desafie isto", "questione minha ideia", "faça um red team da minha ideia", "teste esta ideia"]
    quoted
  • low Risky intent intent-offensive-security commands/obsidian-challenge.md:22
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
    5. Synthesize a structured "Red Team" analysis:
    quoted
  • low Exfiltration read-dotenv CONTRIBUTING.md:43
    Reads a .env file (documentation of a security skill)
    cp .env.example ~/.config/obsidian-second-brain/.env
    security skill
  • low Dangerous commands cmd-pipe-to-shell-known-host SKILL.md:75
    Pipe-to-shell installer from a well-known host (still executes remote code) (documentation of a security skill)
    curl -sL https://raw.githubusercontent.com/eugeniughelbur/obsidian-second-brain/main/scripts/quick-install.sh | bash
    security skill
  • low Risky intent intent-offensive-security SKILL.md:810
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
    4. Synthesize a structured "Red Team" analysis:
    quoted

A further 3 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 78. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-long description is 1352 chars, limit 1024
  • warning body-long SKILL.md body ≈ 22270 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: references/ai-first-rules.md
  • warning missing-ref reference to a missing file: hooks/validate-ai-first.hook.yaml
  • warning missing-ref reference to a missing file: references/claude-md-assistant-template.md
  • warning missing-ref reference to a missing file: references/vault-schema.md
  • warning missing-ref reference to a missing file: references/write-rules.md
  • warning missing-ref reference to a missing file: references/claude-md-template.md
  • warning missing-ref reference to a missing file: references/folder-map.md
  • warning missing-ref reference to a missing file: references/taxonomy-format.md
  • warning missing-ref reference to a missing file: references/freshness-policy.md
  • warning missing-ref reference to a missing file: scripts/eval/retrieval_eval.py
  • warning missing-ref reference to a missing file: scripts/merge_notes.py
  • warning missing-ref reference to a missing file: scripts/checkin.py
  • warning missing-ref reference to a missing file: references/bases/*.template
  • warning missing-ref reference to a missing file: scripts/architect_scan.py
  • warning missing-ref reference to a missing file: scripts/mine_commit_decisions.py
  • warning missing-ref reference to a missing file: scripts/link_graph.py
  • warning missing-ref reference to a missing file: references/crew.md
  • warning missing-ref reference to a missing file: scripts/document_to_pdf.py
  • warning missing-ref reference to a missing file: scripts/setup.sh
  • warning missing-ref reference to a missing file: scripts/bootstrap_vault.py
  • warning missing-ref reference to a missing file: scripts/vault_health.py
  • warning missing-ref reference to a missing file: scripts/check_notes.py

Process rating: all ten parameters 46/100

Will not run. References files that are not bundled: references/ai-first-rules.md, hooks/validate-ai-first.hook.yaml, references/claude-md-assistant-template.md
  • 0Tools and files. 22 referenced file(s) missing: references/ai-first-rules.md, hooks/validate-ai-first.hook.yaml, references/claude-md-assistant-template.md
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 10Execution cost. Instruction body is 22270 tokens: crowds the task out of the window
  • 60Steps. 306 steps, 4 vague phrases
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 11 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 15 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (32 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 1351: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -5TODO / placeholder text left in the skill
  • -4Absolute local paths (C:\Users, /home/…): not portable
  • -214 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +4Structure: 97 headings
  • +3Step-by-step instructions: 306 items
  • +4Has examples (26 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 23.