By siv2r
Opinionated writing skills for Obsidian, tuned for cryptography and mathematics
Convert aha moments from conversations or thinking sessions into polished mental model notes for an Obsidian vault. Use whenever the user asks to create a mental model note, capture an insight, write up an aha moment, turn a conversation into a knowledge note, or says /create-mental-model. Also trigger when the user has just had a breakthrough in understanding and wants to preserve it, mentions "mental model", or asks to distill a conversation into a knowledge note. Do NOT use for general note-taking, meeting logs, or concept summaries that lack a specific insight.
Converts source material (AI conversations, blog posts, textbook excerpts, PR reviews, explainer docs) into a short reference concept note in Sivaram's Obsidian vault under `knowledge/`. Use this skill whenever the user asks to "write a concept note", invokes `/write-concept-note`, says "capture this concept", "add this to knowledge", or otherwise wants a polished 300-800 word reference explanation of a technical concept written in explanatory-clarity voice (Brilliant-wiki / 3Blue1Brown register). Do NOT trigger for aha-moment / insight notes (that's `/create-mental-model`), for meeting or conference notes, for blog drafts or other long-form writing, or for task tracking.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Opinionated writing skills for Obsidian, tuned for cryptography and mathematics. The target voice is "past you explaining to future you": technical precision with casual delivery, the way you'd explain an insight to your future self who might have forgotten it.
Marketplace:
/plugin marketplace add siv2r/obsidian-writing-skills
/plugin install writing@obsidian-writing-skills
npx:
npx skills add [email protected]:siv2r/obsidian-writing-skills.git
These skills invoke other Obsidian skills for markdown syntax and diagram generation. Install these first:
/plugin marketplace add kepano/obsidian-skills
/plugin install obsidian@obsidian-skills
/plugin marketplace add axtonliu/axton-obsidian-visual-skills
/plugin install obsidian-visual-skills
The /humanizer skill is recommended for voice verification but not required.
| Skill | Description |
|---|---|
| create-mental-model | Extract the single aha moment from a conversation or thinking session and write it up so future-you can re-create the insight months later, even if you've forgotten the details. Generates LaTeX equations and Excalidraw diagrams where the insight needs them, written in clear technical prose that skips the textbook tone. |
| write-concept-note | Convert source material (AI conversations, blog posts, textbook excerpts, PR reviews, explainer docs) into a short 300-800 word reference concept note under knowledge/ in your Obsidian vault. Written in explanatory-clarity voice (Brilliant-wiki / 3Blue1Brown register) — a standalone reference, not a personal insight. |
The shared voice across all skills is "past you explaining to future you." Short declarative sentences, first-person reasoning at stuck points, no textbook-neutral phrasing ("Consider the set..."), no performative casualness ("Pretty cool, huh?"). Each skill's SKILL.md has the full voice spec, with curated examples in references/.
The skills are calibrated for cryptography and mathematics: elliptic curves, provable security, probability, and abstract algebra. The structural templates and failure modes are general enough for any technical domain, but the voice and examples are from this field.
npx claudepluginhub siv2r/obsidian-writing-skills --plugin writingClaude + Obsidian knowledge companion. Sets up a persistent, compounding wiki vault (Karpathy's LLM Wiki pattern). v1.7 "Compound Vault" + v1.8 methodology modes close 5 of 5 priority gaps from the May 2026 compass artifact. Ships: substrate alignment with kepano/obsidian-skills, default Obsidian CLI transport, hybrid retrieval (contextual prefix + BM25 + cosine rerank per Anthropic's Sept 2024 research), per-file advisory locking for multi-writer safety, pre-commit verifier agent, AND methodology modes (LYT / PARA / Zettelkasten / Generic) for first-class organizational support no other Claude+Obsidian competitor offers. v1.7.x audit closure: every BLOCKER + HIGH + MEDIUM + LOW finding from the v1.7.0 audit is CLOSED or DEFERRED-with-rationale. Optional DragonScale Memory extension (log folds, deterministic addresses, semantic tiling lint, boundary-first autoresearch).
Create and edit Obsidian vault files including Markdown, Bases, and Canvas. Use when working with .md, .base, or .canvas files in an Obsidian vault.
Kit completo de skills pra transformar uma pasta em vault Obsidian profissional + dashboard local com ML. 6 skills: init (scaffold), librarian (cura contínua), migrate (adoção não-destrutiva), organizer (clusters/duplicatas), expand (notas-ponte via LLM restrito), pulse (dashboard localhost com FSRS, recommendations, anomalies). 100% local, privacy-first, pt-br.
LLM-maintained knowledge base skill — structured wiki with Obsidian, milestone-based source clustering, proactive write-back, and autonomous lint
Claude Code skill pack for Obsidian plugin development and vault management (24 skills)
Persistent, compounding knowledge base maintained by LLMs in Obsidian — agent-first edition. Four task-oriented agents (Researcher / Advisor / Curator / Scribe) with citations, confidence, supersession, and rolling session cache. Inspired by Karpathy's LLM Wiki pattern.