Obsidian Bases
Atmosphere/atmosphere
Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries.
Implement vault data backup, sync, and recovery strategies. An agent skill from jeremylongshore/tons-of-skills-marketplace.
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill obsidian-data-handling -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install jeremylongshore/tons-of-skills-marketplace obsidian-data-handling --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/.curated/obsidian-data-handling .claude/skills/obsidian-data-handling && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "obsidian-data-handling" agent skill from https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/main/skills/.curated/obsidian-data-handling into .claude/skills/obsidian-data-handling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "obsidian-data-handling", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/main/skills/.curated/obsidian-data-handlingType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill obsidian-data-handling -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install jeremylongshore/tons-of-skills-marketplace obsidian-data-handling --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/.curated/obsidian-data-handling .agents/skills/obsidian-data-handling && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "obsidian-data-handling" agent skill from https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/main/skills/.curated/obsidian-data-handling into .agents/skills/obsidian-data-handling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "obsidian-data-handling", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill obsidian-data-handling -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install jeremylongshore/tons-of-skills-marketplace obsidian-data-handling --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/.curated/obsidian-data-handling .cursor/skills/obsidian-data-handling && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "obsidian-data-handling" agent skill from https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/main/skills/.curated/obsidian-data-handling into .cursor/skills/obsidian-data-handling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "obsidian-data-handling", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/jeremylongshore/tons-of-skills-marketplace.git --path skills/.curated/obsidian-data-handling--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill obsidian-data-handling -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install jeremylongshore/tons-of-skills-marketplace obsidian-data-handling --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/.curated/obsidian-data-handling .gemini/skills/obsidian-data-handling && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "obsidian-data-handling" agent skill from https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/main/skills/.curated/obsidian-data-handling into .gemini/skills/obsidian-data-handling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "obsidian-data-handling", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install jeremylongshore/tons-of-skills-marketplace obsidian-data-handlingInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill obsidian-data-handling -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/.curated/obsidian-data-handling .github/skills/obsidian-data-handling && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "obsidian-data-handling" agent skill from https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/main/skills/.curated/obsidian-data-handling into .github/skills/obsidian-data-handling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "obsidian-data-handling", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill obsidian-data-handling -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install jeremylongshore/tons-of-skills-marketplace obsidian-data-handling --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/.curated/obsidian-data-handling .opencode/skills/obsidian-data-handling && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "obsidian-data-handling" agent skill from https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/main/skills/.curated/obsidian-data-handling into .opencode/skills/obsidian-data-handling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "obsidian-data-handling", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
obsidian-data-handlingImplement vault data backup, sync, and recovery strategies. An agent skill from jeremylongshore/tons-of-skills-marketplace.
Obsidian Data Handling is an agent skill from jeremylongshore/tons-of-skills-marketplace. Implement vault data backup, sync, and recovery strategies. Use when building backup features, implementing data export, or handling vault synchronization in your plugin. Trigger with phrases like "obsidian backup", "obsidian sync", "obsidian data export", "vault backup strategy".
Its SKILL.md is about 2.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/implementation-guide.md`). Compatibility notes: Designed for Claude Code
It works with Obsidian. The repository describes itself as: Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com. The licence is MIT.
6 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
ReadWriteEditFrom allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are typescript).
From the folder's file list and the shell code blocks in SKILL.md.
Links to these hosts (documentation or services it may open):
docs.obsidian.mdhelp.obsidian.mdFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Designed for Claude Code
From compatibility in the SKILL.md frontmatter.
Obsidian Data Handling loads about 2.8k tokens when it runs, and up to ~7k if it reads all its reference files. Until then it costs about 76 tokens; SKILL.md has 443 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 443 words, ~2,846 tokens.
.claude/skills/obsidian-data-handling/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.Data management patterns for Obsidian plugins: plugin config with loadData/saveData, vault file I/O, frontmatter parsing via metadataCache, handling renames and deletes, cross-device sync considerations, and IndexedDB fallback for large datasets.
export default class extends Plugin)Vault and MetadataCache APIsObsidian stores plugin data in .obsidian/plugins/<plugin-id>/data.json. Use loadData() and saveData() — never read that file directly.
interface PluginConfig {
version: number;
apiEndpoint: string;
syncInterval: number;
excludedFolders: string[];
}
const DEFAULT_CONFIG: PluginConfig = {
version: 1,
apiEndpoint: 'https://api.example.com',
syncInterval: 300,
excludedFolders: [],
};
export default class DataPlugin extends Plugin {
config: PluginConfig;
async onload() {
await this.loadConfig();
}
async loadConfig() {
const saved = await this.loadData();
this.config = Object.assign({}, DEFAULT_CONFIG, saved);
// Migrate from older config versions
if (this.config.version < 1) {
this.config.excludedFolders = [];
this.config.version = 1;
await this.saveConfig();
}
}
async saveConfig() {
await this.saveData(this.config);
}
}loadData() returns null on first run — Object.assign onto defaults handles this cleanly.
import { TFile, TFolder, normalizePath } from 'obsidian';
// Read a markdown file
async readNote(path: string): Promise<string | null> {
const file = this.app.vault.getAbstractFileByPath(normalizePath(path));
if (file instanceof TFile) {
return await this.app.vault.read(file);
}
return null;
}
// Write or create a markdown file
async writeNote(path: string, content: string): Promise<TFile> {
const normalized = normalizePath(path);
const existing = this.app.vault.getAbstractFileByPath(normalized);
if (existing instanceof TFile) {
await this.app.vault.modify(existing, content);
return existing;
}
// Ensure parent folder exists
const dir = normalized.substring(0, normalized.lastIndexOf('/'));
if (dir && !this.app.vault.getAbstractFileByPath(dir)) {
await this.app.vault.createFolder(dir);
}
return await this.app.vault.create(normalized, content);
}
// Append to a file (e.g., a log or journal)
async appendToNote(path: string, text: string): Promise<void> {
const file = this.app.vault.getAbstractFileByPath(normalizePath(path));
if (file instanceof TFile) {
await this.app.vault.append(file, '\n' + text);
}
}Use vault.cachedRead() instead of vault.read() when you don't need the absolute latest content — it avoids hitting disk on every call.
Never parse YAML frontmatter manually. Obsidian's metadataCache keeps a parsed cache of every file's frontmatter.
import { TFile, CachedMetadata } from 'obsidian';
// Read frontmatter from a file
getFrontmatter(file: TFile): Record<string, any> | null {
const cache: CachedMetadata | null = this.app.metadataCache.getFileCache(file);
return cache?.frontmatter ?? null;
}
// Update frontmatter using processFrontMatter (Obsidian 1.4+)
async setStatus(file: TFile, status: string): Promise<void> {
await this.app.fileManager.processFrontMatter(file, (fm) => {
fm.status = status;
fm.updated = new Date().toISOString();
});
}
// Bulk query: find all files with a specific tag
getFilesWithTag(tag: string): TFile[] {
const files: TFile[] = [];
for (const file of this.app.vault.getMarkdownFiles()) {
const cache = this.app.metadataCache.getFileCache(file);
const tags = cache?.tags?.map(t => t.tag) ?? [];
const fmTags = cache?.frontmatter?.tags ?? [];
if (tags.includes(tag) || fmTags.includes(tag.replace('#', ''))) {
files.push(file);
}
}
return files;
}processFrontMatter handles YAML serialization correctly — it preserves comments and formatting, and is the only safe way to update frontmatter programmatically.
Plugins that index file paths must update their state when files move or disappear.
async onload() {
// Track renames to update internal references
this.registerEvent(
this.app.vault.on('rename', (file, oldPath) => {
if (file instanceof TFile) {
this.onFileRenamed(file, oldPath);
}
})
);
// Clean up when files are deleted
this.registerEvent(
this.app.vault.on('delete', (file) => {
if (file instanceof TFile) {
this.onFileDeleted(file.path);
}
})
);
}
private onFileRenamed(file: TFile, oldPath: string) {
// Update any stored path references
if (this.config.pinnedFiles?.includes(oldPath)) {
const idx = this.config.pinnedFiles.indexOf(oldPath);
this.config.pinnedFiles[idx] = file.path;
this.saveConfig();
}
}
private onFileDeleted(path: string) {
// Remove from any indexes
if (this.config.pinnedFiles?.includes(path)) {
this.config.pinnedFiles = this.config.pinnedFiles.filter(p => p !== path);
this.saveConfig();
}
}Always use registerEvent — it automatically cleans up the listener when the plugin unloads.
Obsidian vaults synced via iCloud, Dropbox, or Obsidian Sync introduce eventual consistency issues.
// Problem: two devices modify data.json simultaneously
// Solution: merge-friendly data structures
interface SyncSafeConfig {
// Use a map keyed by unique IDs instead of arrays
// Maps merge better than arrays across sync conflicts
items: Record<string, { value: string; updatedAt: number }>;
}
// Timestamp-based last-write-wins merge
mergeConfigs(local: SyncSafeConfig, remote: SyncSafeConfig): SyncSafeConfig {
const merged: SyncSafeConfig = { items: {} };
const allKeys = new Set([
...Object.keys(local.items),
...Object.keys(remote.items),
]);
for (const key of allKeys) {
const l = local.items[key];
const r = remote.items[key];
if (!l) merged.items[key] = r;
else if (!r) merged.items[key] = l;
else merged.items[key] = l.updatedAt >= r.updatedAt ? l : r;
}
return merged;
}Guidelines for sync-friendly plugins:
data.json — they differ across devices with different vault locationsdata.json small — large files cause sync conflicts and slow syncWhen plugin data exceeds what's practical for data.json (more than ~1MB), use IndexedDB.
class PluginDatabase {
private db: IDBDatabase | null = null;
private dbName: string;
constructor(pluginId: string) {
this.dbName = `obsidian-${pluginId}`;
}
async open(): Promise<void> {
return new Promise((resolve, reject) => {
const request = indexedDB.open(this.dbName, 1);
request.onupgradeneeded = (event) => {
const db = (event.target as IDBOpenDBRequest).result;
if (!db.objectStoreNames.contains('cache')) {
db.createObjectStore('cache', { keyPath: 'id' });
}
};
request.onsuccess = (event) => {
this.db = (event.target as IDBOpenDBRequest).result;
resolve();
};
request.onerror = () => reject(request.error);
});
}
async put(id: string, data: any): Promise<void> {
if (!this.db) throw new Error('Database not open');
return new Promise((resolve, reject) => {
const tx = this.db!.transaction('cache', 'readwrite');
tx.objectStore('cache').put({ id, data, updatedAt: Date.now() });
tx.oncomplete = () => resolve();
tx.onerror = () => reject(tx.error);
});
}
async get(id: string): Promise<any | null> {
if (!this.db) throw new Error('Database not open');
return new Promise((resolve, reject) => {
const tx = this.db!.transaction('cache', 'readonly');
const request = tx.objectStore('cache').get(id);
request.onsuccess = () => resolve(request.result?.data ?? null);
request.onerror = () => reject(request.error);
});
}
close() {
this.db?.close();
this.db = null;
}
}
// Usage in plugin
async onload() {
this.db = new PluginDatabase(this.manifest.id);
await this.db.open();
}
onunload() {
this.db?.close();
}IndexedDB is per-device and does not sync across devices. Use it for caches and derived data that can be rebuilt, not for primary user data.
| Issue | Cause | Solution |
|---|---|---|
loadData() returns null | First run, no data.json yet | Object.assign onto defaults |
| Frontmatter returns undefined | File not yet indexed by cache | Listen for metadataCache.on('resolved') |
| File write fails | Parent folder doesn't exist | Create folder with vault.createFolder() first |
| Settings lost after sync | Concurrent writes from two devices | Use merge-friendly data structures with timestamps |
| data.json too large / slow | Storing too much data | Move large data to IndexedDB |
| stale cache after modify | cachedRead returns old content | Use vault.read() when freshness matters |
async exportTaggedNotes(tag: string): Promise<string> {
const files = this.getFilesWithTag(tag);
const notes = await Promise.all(
files.map(async (f) => ({
path: f.path,
content: await this.app.vault.read(f),
frontmatter: this.getFrontmatter(f),
}))
);
return JSON.stringify(notes, null, 2);
}async updateConfig<K extends keyof PluginConfig>(
key: K,
value: PluginConfig[K]
): Promise<void> {
this.config[key] = value;
await this.saveConfig();
}For team access control patterns, see obsidian-enterprise-rbac. For performance with large vaults, see obsidian-rate-limits.
© jeremylongshore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file (references) in skills/.curated/obsidian-data-handling of jeremylongshore/tons-of-skills-marketplace.
Open the folder on GitHubat commit cfae287
Obsidian Data Handling next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Obsidian Data Handling this skilljeremylongshore/tons-of-skills-marketplace | 2.8k | — | ~2.8k | Automated safety check: Pass | MIT | |
| Obsidian BasesAtmosphere/atmosphere | 3.8k | 22 repos | ~3.2k | Automated safety check: Pass | Apache-2.0 | |
| Knap Markdown Templateskepano/obsidian-skills | 49k | 2 repos | ~986 | Automated safety check: Pass | MIT | |
| JSON Canvasheyitsnoah/claudesidian | 2.6k | 18 repos | ~3.5k | Automated safety check: Pass | MIT | |
| Obsidian MarkdownAtmosphere/atmosphere | 3.8k | 20 repos | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Obsidian CLIAtmosphere/atmosphere | 3.8k | 13 repos | ~795 | Automated safety check: Pass | Apache-2.0 |
Atmosphere/atmosphere
Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries.
kepano/obsidian-skills
Renders Markdown notes from Knap templates and JSON data on the command line, including notes built from Defuddle web page output.
heyitsnoah/claudesidian
Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections.
Atmosphere/atmosphere
Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax.
Atmosphere/atmosphere
Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more.
axtonliu/axton-obsidian-visual-skills
Create Obsidian Canvas files from text content, supporting both MindMap and freeform layouts.
jeremylongshore/tons-of-skills-marketplace
Execute this skill enables AI assistant to conduct a security-focused code review using the security-agent plugin.
jeremylongshore/tons-of-skills-marketplace
Build this skill automates the adaptation of pre-trained machine learning models using transfer learning techniques.
jeremylongshore/tons-of-skills-marketplace
Execute proactive auto-loading: automatically detects and loads agents.md files.
jeremylongshore/tons-of-skills-marketplace
Aggregate and centralize performance metrics from applications, systems, databases, caches, and services.
jeremylongshore/tons-of-skills-marketplace
Execute this skill enables AI assistant to analyze capacity requirements and plan for future growth.
jeremylongshore/tons-of-skills-marketplace
Process use when you need to work with database indexing. An agent skill from jeremylongshore/tons-of-skills-marketplace.
Works with
Implement vault data backup, sync, and recovery strategies. An agent skill from jeremylongshore/tons-of-skills-marketplace. Obsidian Data Handling is an agent skill from jeremylongshore/tons-of-skills-marketplace. Implement vault data backup, sync, and recovery strategies.
Obsidian Data Handling fits situations like: building backup features; implementing data export; handling vault synchronization in your plugin; with phrases like obsidian backup.
Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill obsidian-data-handling -a claude-code`. Or copy the skill folder (skills/.curated/obsidian-data-handling in jeremylongshore/tons-of-skills-marketplace) into .claude/skills/obsidian-data-handling in your project. Claude Code loads it when a task matches its description.
Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill obsidian-data-handling -a codex`. Or copy the skill folder (skills/.curated/obsidian-data-handling in jeremylongshore/tons-of-skills-marketplace) into .agents/skills/obsidian-data-handling in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill obsidian-data-handling -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/obsidian-data-handling, .gemini/skills/obsidian-data-handling, .github/skills/obsidian-data-handling and .opencode/skills/obsidian-data-handling in your project.
SKILL.md names no scripts, command-line tools or credentials: Obsidian Data Handling is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Write, Edit. Compatibility (from SKILL.md): Designed for Claude Code.
SKILL.md names 2 domains. As links in the text: docs.obsidian.md and help.obsidian.md. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Obsidian Data Handling is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.8k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.2k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Obsidian Data Handling: Obsidian Bases (Atmosphere/atmosphere, 3.8k stars), Knap Markdown Templates (kepano/obsidian-skills, 49k stars), JSON Canvas (heyitsnoah/claudesidian, 2.6k stars) and Obsidian Markdown (Atmosphere/atmosphere, 3.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
jeremylongshore (a GitHub user) maintains it in jeremylongshore/tons-of-skills-marketplace, which has 2,827 GitHub stars. The repository holds 3,342 skills in this directory. The repository was last updated on October 10, 2026.
Source: jeremylongshore/tons-of-skills-marketplace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.