Bytestash logo

Bytestash

Community
jmagar
bytestash

Manage code snippets in ByteStash snippet storage service. This skill should be used when the user asks to "save a snippet", "search snippets", "find code", "share snippet", "organize snippets", "list my snippets", "create snippet", "delete snippet", or mentions ByteStash, code storage, snippet management, or code archival.

Overview

Publisherjmagar
Repositoryclaude-homelab
Skill namebytestash
Stars
87
Forks
11
Bundled files
5
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 5 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by jmagar on GitHub. Read the source before you install it.

Installation

Install the Bytestash AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/jmagar/claude-homelab/tree/main/skills/bytestash
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/jmagar/claude-homelab.git /tmp/claude-homelab
mkdir -p .claude/skills
cp -r /tmp/claude-homelab/skills/bytestash .claude/skills/bytestash
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Bytestash in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Bytestash on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Bytestash is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

ByteStash Skill

⚠️ MANDATORY SKILL INVOCATION ⚠️

YOU MUST invoke this skill (NOT optional) when the user mentions ANY of these triggers:

  • "save snippet", "store code", "archive snippet"
  • "search snippets", "find snippet", "lookup code"
  • "share snippet", "create share link", "public snippet"
  • "list snippets", "show my snippets", "snippet library"
  • "delete snippet", "remove snippet", "update snippet"
  • "organize snippets", "categorize snippets", "tag snippets"
  • Any mention of ByteStash or code snippet management

Failure to invoke this skill when triggers occur violates your operational requirements.

Purpose

ByteStash is a self-hosted code snippet management service with multi-file support, sharing capabilities, and organization features. This skill provides read-write access to manage snippets with full CRUD operations.

Capabilities:

  • Read-only: List, search, and retrieve snippets
  • Create/Update: Save new snippets with multiple code fragments
  • Delete: Remove snippets with user confirmation
  • Share Management: Create, view, and delete share links (public/protected/expiring)
  • Organization: Categorize and organize snippets with tags

Authentication: API key via x-api-key header (recommended for CLI/automation)

Setup

Required credentials in ~/.claude-homelab/.env:

bash
BYTESTASH_URL="https://bytestash.example.com"
BYTESTASH_API_KEY="<your_api_key>"

How to get your API key:

  1. Log in to ByteStash web interface
  2. Navigate to Settings → API Keys
  3. Create new API key with a descriptive name
  4. Copy the generated key to .env file

Security:

  • Set permissions: chmod 600 ~/.claude-homelab/.env
  • API keys are scoped to your user account
  • NEVER commit .env to version control

Commands

All commands use the bash script wrapper in scripts/bytestash-api.sh.

List Snippets

bash
cd skills/bytestash
./scripts/bytestash-api.sh list

Search Snippets

bash
# Search by title (case-insensitive partial match)
./scripts/bytestash-api.sh search "docker"

# Search by category
./scripts/bytestash-api.sh search --category "bash"

Get Snippet Details

bash
./scripts/bytestash-api.sh get <snippet-id>

Create Snippet

bash
# Single fragment (inline code)
./scripts/bytestash-api.sh create \
  --title "Docker Compose Example" \
  --description "Production-ready compose file" \
  --categories "docker,devops" \
  --code "version: '3.8'..." \
  --language "yaml" \
  --filename "docker-compose.yml"

# Multiple fragments (from files)
./scripts/bytestash-api.sh push \
  --title "FastAPI Setup" \
  --description "Complete FastAPI project structure" \
  --categories "python,api" \
  --files "app.py,requirements.txt,Dockerfile"

Update Snippet

bash
./scripts/bytestash-api.sh update <snippet-id> \
  --title "New Title" \
  --description "Updated description" \
  --categories "new,tags"

Delete Snippet

bash
# Prompts for confirmation
./scripts/bytestash-api.sh delete <snippet-id>

Share Management

bash
# Create public share link
./scripts/bytestash-api.sh share <snippet-id>

# Create protected share (requires auth)
./scripts/bytestash-api.sh share <snippet-id> --protected

# Create expiring share (24 hours)
./scripts/bytestash-api.sh share <snippet-id> --expires 86400

# List all shares for a snippet
./scripts/bytestash-api.sh shares <snippet-id>

# Delete share link
./scripts/bytestash-api.sh unshare <share-id>

# View shared snippet
./scripts/bytestash-api.sh view-share <share-id>

Workflow

When the user asks about ByteStash:

  1. "Save this code as a snippet"

    • Determine if single or multiple files
    • If single: Use create command with inline code
    • If multiple: Use push command with file paths
    • Always include title, description, and categories
  2. "Find my Docker snippets"

    • Use search --category docker or search "docker"
    • Present results with ID, title, description, and categories
    • If user wants details: Use get <id> to show full snippet
  3. "Share this snippet publicly"

    • Use share <snippet-id> to create public link
    • Return share URL: {BYTESTASH_URL}/s/{share-id}
    • Optionally use --protected or --expires flags
  4. "What snippets do I have?"

    • Use list command
    • Group by categories for better organization
    • Show total count and recent updates
  5. "Delete this snippet"

    • Confirm with user before deletion
    • Use delete <snippet-id>
    • Verify deletion with success message
  6. "Organize my snippets by category"

    • List all snippets with list
    • Identify missing/inconsistent categories
    • Suggest category updates with update command

Multi-Fragment Snippets

ByteStash supports snippets with multiple code fragments (files). Each fragment has:

  • file_name: Display name (e.g., app.py, Dockerfile)
  • code: The actual code content
  • language: Syntax highlighting language (e.g., python, dockerfile)
  • position: Display order (0-indexed)

When to use multi-fragment:

  • Related configuration files (docker-compose.yml + .env)
  • Full project structures (API + tests + docs)
  • Before/after code examples
  • Multi-language implementations

Notes

Data Model:

json
{
  "id": 123,
  "title": "Snippet Title",
  "description": "Detailed description",
  "categories": ["tag1", "tag2"],
  "fragments": [
    {
      "id": 456,
      "file_name": "example.py",
      "code": "print('hello')",
      "language": "python",
      "position": 0
    }
  ],
  "updated_at": "2024-01-01T00:00:00Z",
  "share_count": 2
}

Authentication:

  • Uses x-api-key header with API key from .env
  • API keys are managed in ByteStash web UI (Settings → API Keys)
  • Preferable to JWT tokens for automation

Share Links:

  • Public shares: Anyone with link can view
  • Protected shares: Requires authentication to view
  • Expiring shares: Auto-delete after specified seconds
  • Share IDs are random strings (e.g., abc123def456)

Destructive Operations:

  • Delete snippet: Permanently removes snippet and all fragments
  • Delete share: Invalidates share link (snippet remains)
  • Both require user confirmation before execution

Output Format:

  • All commands return JSON by default
  • Use jq for filtering/formatting (e.g., ./bytestash-api.sh list | jq '.[] | select(.categories[] == "docker")')
  • Errors return HTTP status codes with JSON error messages

Limitations:

  • API key required for all operations (no anonymous access via API)
  • Categories are tags (no hierarchical structure)
  • No bulk operations (must process snippets individually)
  • Share links cannot be updated (must delete and recreate)
  • Some deployments may require JWT auth for share endpoints (/api/share*)

Reference

  • API Endpoints: See references/api-endpoints.md for complete API reference
  • Quick Reference: See references/quick-reference.md for command examples
  • Troubleshooting: See references/troubleshooting.md for common failures
  • Official Docs: API documentation at {BYTESTASH_URL}/api-docs/
  • Web Interface: Full-featured UI at {BYTESTASH_URL}

🔧 Agent Tool Usage Requirements

CRITICAL: When invoking scripts from this skill via the zsh-tool, ALWAYS use pty: true.

Without PTY mode, command output will not be visible even though commands execute successfully.

Correct invocation pattern:

typescript
<invoke name="mcp__plugin_zsh-tool_zsh-tool__zsh">
<parameter name="command">./skills/bytestash/scripts/bytestash-api.sh [args]</parameter>
<parameter name="pty">true</parameter>
</invoke>

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Bytestash AI skill do?

Manage code snippets in ByteStash snippet storage service. This skill should be used when the user asks to "save a snippet", "search snippets", "find code", "share snippet", "organize snippets", "list my snippets", "create snippet", "delete snippet", or mentions ByteStash, code storage, snippet management, or code archival.

Why use Bytestash on TypingMind?

Because you install it once and use it with any model. Bytestash is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Bytestash in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jmagar/claude-homelab/tree/main/skills/bytestash. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Bytestash?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Bytestash?

As many as you like. As long as a model supports skills, you can use Bytestash with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Bytestash AI skill free?

Yes. It is published on GitHub by jmagar under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇