By brsbl
Manage Moss notes directly from Claude Code — create and edit notes with canvas diagrams, comments, formulas, frontmatter metadata, interactive HTML previews, wiki links, and enforce writing guidelines for scannable content.
Create or edit Moss canvas blocks and choose between moss-canvas and plain ASCII sketches for proposal notes, UI option cards, ASCII wireframes, rough diagrams, flows, and spatial visual thinking.
Comment annotation syntax for Moss notes. Use when adding, preserving, or editing note comments and their sidecar metadata.
Create or edit Moss formulas and variables, including editable anchors, derived values, bound references, display values, IDs, metadata, and table-cell usage.
YAML frontmatter rules for Moss note metadata. Use when adding or editing the optional metadata block at the top of a note.
Author self-contained moss-html blocks for HTML previews, embedded HTML, interactive prototypes, and behavior demos in Moss notes.
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.
This repository provides standalone skills for creating and editing Moss notes with coding agents. The skills teach Moss writing guidelines, note structure, Markdown syntax, formulas and variables, comments, links, frontmatter, canvas, and embedded HTML.
~/Moss/Notes/** without breaking note directories, sidecars, comments, links, or embedded moss-html / moss-canvas blocks.If you customize these skills, do not change the Moss note syntax itself. The Moss app expects specific Markdown and sidecar shapes. You can customize how agents apply the syntax, such as whether they leave comments instead of editing directly or how they style embedded HTML.
Forking this repository only affects agents that install skills from it. It does not change the default behavior of the in-app Moss agent.
moss-writing-guidelines: Read first when creating, editing, restructuring, or reviewing a note for quality. It covers reader-first structure, progressive disclosure, a node decision matrix, note archetypes, and a final review checklist.moss-notes: Start here for syntax when an agent needs to create or edit a Moss note. It explains note folders, the Markdown file, assets, sidecars, headings, tables, callouts, charts, and when to use the focused Moss skills below.moss-formulas-variables: Use when a note needs formulas or variables, including editable anchors, derived values, bound references, display values, IDs, and table-cell usage.moss-frontmatter: Use when a note needs structured metadata at the top, such as tags, status, dates, or other searchable fields.moss-comments: Use when adding or preserving inline review comments. It covers the body markers and matching comments.json metadata Moss needs.moss-links: Use when a note needs wiki note links, heading links, aliases, Markdown links, YouTube links, or media-link preservation.moss-canvas: Use when a note needs rough diagrams, wireframes, flows, or spatial visual thinking in a canonical moss-canvas block.moss-html: Use when a note needs embedded HTML, such as a UI prototype, behavior demo, or focused interactive preview.npx skills add brsbl/moss-skills
/plugin marketplace add brsbl/moss-skills
/plugin install moss-skills@moss-skills
codex plugin marketplace add brsbl/moss-skills
MIT. See LICENSE.
npx claudepluginhub brsbl/moss-skills --plugin moss-skillsProvider-agnostic skills for autonomous product development: spec, task, implement, test, review, and summarize changes.
Build and maintain an LLM-curated personal knowledge base in your project — Andrej Karpathy's LLM Wiki pattern, designed to scale to thousands of pages without becoming a context bottleneck. Now with an optional compiled graph layer for typed, provenance-backed relationships.
Claude + 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).
Complete AI coding workflow system. Self-correcting memory + persistent FTS5-indexed research wikis + auto-research loop + multi-LLM council on a single SQLite store. 33 skills, 8 agents, 22 commands, 37 hook scripts across 24 events. Cross-agent via SkillKit.
Make your AI agent code with your project's architecture, rules, and decisions.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Connect to Atlassian products including Jira and Confluence. Search and create issues, access documentation, manage sprints, and integrate your development workflow with Atlassian's collaboration tools.