Agent skill

Library

by disler in disler/the-library

Private skill distribution system. An agent skill from disler/the-library.

MITAuto-check passed

Install Library

skills CLI
$ npx skills add disler/the-library --skill library -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install disler/the-library library --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
library
GitHub stars
428
Token cost
~2.2k tokens
SKILL.md length
717 words
Files
20
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Private skill distribution system. An agent skill from disler/the-library.

  • Works in 4 steps: Clone the repo with git clone --depth 1… → Navigate to the parent directory of the… → Copy that entire directory to the target… → …
  • The user wants to install
  • SKILL.md covers Variables, How It Works, Commands and Cookbook, plus 7 more sections
  • Calls git and gh; reaches github.com and raw.githubusercontent.com; needs GITHUB_TOKEN

What it does

Library is an agent skill from disler/the-library. Private skill distribution system. Use when the user wants to install, use, add, push, remove, sync, list, or search for skills, agents, or prompts from their private library catalog. Triggers on /library commands or mentions of library, skill distribution, or agentic management.

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 21 other files (for example `README.md`, `cookbook/add.md` and `cookbook/install.md`).

The repository describes itself as: A Meta-Skill for Private-First Distribution of Agentics (Skills, Agents, and Prompts) across your Agents, Devices, and Teams. The licence is MIT.

When your agent uses it

  • The user wants to install
  • Search for skills
  • Prompts from their private library catalog
  • /library commands

Example prompts

  • “/library”

Requirements

  • A credential in GITHUB_TOKEN

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Clone the repo with git clone --depth 1 into a temporary directory
  2. Navigate to the parent directory of the referenced file
  3. Copy that entire directory to the target local directory
  4. The temporary directory is cleaned up automatically

What it can do on your machine

Read from SKILL.md and the folder at commit 47f455c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git
    • gh

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com
    • raw.githubusercontent.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • GITHUB_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Library loads about 2.2k tokens when it runs. Until then it costs about 72 tokens; SKILL.md has 717 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~72
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from disler/the-library at commit 47f455c, republished under its MIT licence (© disler). 717 words, ~2,162 tokens.

Download SKILL.mdSave it as .claude/skills/library/SKILL.md (or your agent's skills folder). This skill also uses 19 other files; get the full folder from GitHub.
name
library
description
Private skill distribution system. Use when the user wants to install, use, add, push, remove, sync, list, or search for skills, agents, or prompts from their private library catalog. Triggers on /library commands or mentions of library, skill distribution, or agentic management.
argument-hint
[command or prompt] [name or details]

The Library

A meta-skill for private-first distribution of agentics (skills, agents, and prompts) across agents, devices, and teams.

Variables

Update these after forking and cloning the library repo.

  • LIBRARY_REPO_URL: <your forked repo url>
  • LIBRARY_YAML_PATH: ~/.claude/skills/library/library.yaml
  • LIBRARY_SKILL_DIR: ~/.claude/skills/library/

How It Works

The Library is a catalog of references to your agentics. The library.yaml file points to where skills, agents, and prompts live (local filesystem or GitHub repos). Nothing is fetched until you ask for it.

The library.yaml is a catalog, not a manifest. Entries define what's available — not what gets installed. You pull specific items on demand with /library use <name>.

Commands

CommandPurpose
/library installFirst-time setup: fork, clone, configure
/library add <details>Register a new entry in the catalog
/library use <name>Pull from source (install or refresh)
/library push <name>Push local changes back to source
/library remove <name>Remove from catalog and optionally local
/library listShow full catalog with install status
/library syncRe-pull all installed items from source
/library search <keyword>Find entries by keyword

Cookbook

Each command has a detailed step-by-step guide. Read the relevant cookbook file before executing a command.

CommandCookbookUse When
installcookbook/install.mdFirst-time setup on a new device
addcookbook/add.mdUser wants to register a new skill/agent/prompt in catalog
usecookbook/use.mdUser wants to pull or refresh a skill from the catalog
pushcookbook/push.mdUser improved a skill locally and wants to update the source
removecookbook/remove.mdUser wants to remove an entry from the catalog
listcookbook/list.mdUser wants to see what's available and what's installed
synccookbook/sync.mdUser wants to refresh all installed items at once
searchcookbook/search.mdUser is looking for a skill but doesn't know the exact name

When a user invokes a /library command, read the matching cookbook file first, then execute the steps.

Source Format

The source field in library.yaml supports these formats (auto-detected):

  • /absolute/path/to/SKILL.md — local filesystem
  • https://github.com/org/repo/blob/main/path/to/SKILL.md — GitHub browser URL
  • https://raw.githubusercontent.com/org/repo/main/path/to/SKILL.md — GitHub raw URL

Both GitHub URL formats are supported. Parse org, repo, branch, and file path from the URL structure. For private repos, use SSH or GITHUB_TOKEN for auth automatically.

Important: The source points to a specific file (SKILL.md, AGENT.md, or prompt file). We always pull the entire parent directory, not just the file.

Source Parsing Rules

Local paths start with / or ~:

  • Use the path directly. Copy the parent directory of the referenced file.

GitHub browser URLs match https://github.com/<org>/<repo>/blob/<branch>/<path>:

  • Parse: org, repo, branch, file_path
  • Clone URL: https://github.com/<org>/<repo>.git
  • File location within repo: <path>

GitHub raw URLs match https://raw.githubusercontent.com/<org>/<repo>/<branch>/<path>:

  • Parse: org, repo, branch, file_path
  • Clone URL: https://github.com/<org>/<repo>.git
  • File location within repo: <path>
Show full SKILL.md (288 more words)Show less

GitHub Workflow

When working with GitHub sources, prefer gh api for accessing single files (e.g., reading a SKILL.md to check metadata). For pulling entire skill directories, clone into a temp dir per the steps below.

Fetching (use):

  1. Clone the repo with git clone --depth 1 <clone_url> into a temporary directory
  2. Navigate to the parent directory of the referenced file
  3. Copy that entire directory to the target local directory
  4. The temporary directory is cleaned up automatically

Pushing (push):

  1. Clone the repo with git clone --depth 1 <clone_url> into a temporary directory
  2. Overwrite the skill directory in the clone with the local version
  3. Stage only the relevant changes: git add <skill_directory_path>
  4. Commit with message: library: updated <skill name> <what changed>
  5. Push to remote
  6. The temporary directory is cleaned up automatically

Typed Dependencies

The requires field uses typed references to avoid ambiguity:

  • skill:name — references a skill in the library catalog
  • agent:name — references an agent in the library catalog
  • prompt:name — references a prompt in the library catalog

When resolving dependencies: look up each reference in library.yaml, fetch all dependencies first (recursively), then fetch the requested item.

Target Directories

By default, items are installed to the default directory from library.yaml:

yaml
default_dirs:
    skills:
        - default: .claude/skills/
        - global: ~/.claude/skills/
    agents:
        - default: .claude/agents/
        - global: ~/.claude/agents/
    prompts:
        - default: .claude/commands/
        - global: ~/.claude/commands/
  • If the user says "global" or "globally", use the global directory.
  • If the user specifies a custom path, use that path.
  • Otherwise, use the default directory.

Library Repo Sync

The library skill itself lives in <LIBRARY_SKILL_DIR> as a cloned git repo. When running add (which modifies library.yaml), always:

  1. git pull in the library directory first to get latest
  2. Make the changes
  3. git add library.yaml && git commit && git push

This keeps the catalog in sync across devices.

Example Filled Library File

yaml
default_dirs:
  skills:
    - default: .claude/skills/
    - global: ~/.claude/skills/
  agents:
    - default: .claude/agents/
    - global: ~/.claude/agents/
  prompts:
    - default: .claude/prompts/
    - global: ~/.claude/prompts/

library:
  skills:
    - name: firecrawl
      description: Scrape, crawl, and search websites using Firecrawl CLI
      source: /Users/me/projects/tools/skills/firecrawl/SKILL.md

    - name: meta-skill
      description: Creates new Agent Skills following best practices
      source: /Users/me/projects/tools/skills/meta-skill/SKILL.md

    - name: diagram-kroki
      description: Generate diagrams via Kroki HTTP API supporting 28+ languages
      source: https://github.com/myorg/private-skills/blob/main/skills/diagram-kroki/SKILL.md
      requires: [skill:firecrawl]

    - name: green-screen-captions
      description: Generate and burn AI-powered captions onto green screen videos
      source: https://raw.githubusercontent.com/myorg/video-tools/main/skills/green-screen-captions/SKILL.md
      requires: [agent:video-processor, prompt:caption-style]

  agents:
    - name: video-processor
      description: Processes video files with ffmpeg and whisper transcription
      source: /Users/me/projects/tools/agents/video-processor/AGENT.md

    - name: code-reviewer
      description: Reviews code for quality, security, and performance
      source: https://github.com/myorg/agent-configs/blob/main/agents/code-reviewer/AGENT.md

  prompts:
    - name: caption-style
      description: Style guide for generating video captions
      source: /Users/me/projects/content/prompts/caption-style.md

    - name: commit-message
      description: Standardized commit message format for all projects
      source: https://github.com/myorg/team-prompts/blob/main/prompts/commit-message.md

© disler, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 19 other files in the repository root of disler/the-library.

  • SKILL.md
  • .gitignore
  • LICENSE
  • README.md
  • cookbook/add.md
  • cookbook/install.md
  • cookbook/list.md
  • cookbook/push.md
  • cookbook/remove.md
  • cookbook/search.md
  • cookbook/sync.md
  • cookbook/use.md
  • images/03_agentic_stack.svg
  • images/10_meta_skill.svg
  • images/26_problem_skill_sprawl.svg
  • images/27_solution_library_workflow.svg
  • images/32_problem_team_sharing.svg
  • images/45_solution_full_workflow.svg
  • justfile
  • … and 1 more

Open the folder on GitHubat commit 47f455c

Compare with similar skills

Library 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.

Library compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Library this skilldisler/the-library428—~2.2kAutomated safety check: PassMIT
Distributed Triagepytorch/pytorch104k—~2.8kAutomated safety check: PassCustom licence
Distributed Tracingwshobson/agents40k12 repos~527Automated safety check: PassMIT
Distribute Skill To All Agentssickn33/agentic-awesome-skills47k1 repos~1.2kAutomated safety check: PassMIT
Distributed Trainingaiming-lab/AutoResearchClaw15k—~216Automated safety check: PassMIT
Debug Distributed Hangsgl-project/sglang37k2 repos~2.4kAutomated safety check: PassApache-2.0

Similar skills

  • Distributed Triage

    pytorch/pytorch

    Sub-triages issues in the oncall:distributed queue by assigning distributed module labels, routing to sub-oncalls, and marking triaged.

    104k GitHub stars~2.8k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Distributed Tracing

    wshobson/agents

    Implement distributed tracing with Jaeger and Tempo to track requests across microservices and identify performance bottlenecks.

    40k GitHub starsUsed in 12 repos~527 tokens
    DevOps & CloudAuto-check passed
  • Distribute Skill To All Agents

    sickn33/agentic-awesome-skills

    Distribute a skill across configured agent skill folders while respecting local symlink layouts.

    47k GitHub starsUsed in 1 repo~1.2k tokens
    Auto-check passed
  • Distributed Training

    aiming-lab/AutoResearchClaw

    Multi-GPU and distributed training patterns with PyTorch DDP.

    15k GitHub stars~216 tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed
  • Debug Distributed Hang

    sgl-project/sglang

    Debug hanging issues in SGLang distributed inference (TP/PP/DP/EP).

    37k GitHub starsUsed in 2 repos~2.4k tokens
    DevelopmentAuto-check passed
  • Private Company Research

    HKUDS/Vibe-Trading

    Runs a six-lens research framework on pre-IPO and private companies, labels every data point by confidence, and produces a fair-value range, exit-path analysis and information-gap map.

    35k GitHub stars~3.5k tokensUpdated today
    Business, Finance & HRAuto-check passed

Questions about Library

What does Library do?

Private skill distribution system. An agent skill from disler/the-library. Library is an agent skill from disler/the-library. Private skill distribution system.

When should I use Library?

Library fits situations like: the user wants to install; search for skills; prompts from their private library catalog; /library commands.

How do I install Library in Claude Code?

Run `npx skills add disler/the-library --skill library -a claude-code`. Or copy the skill folder (the disler/the-library repository) into .claude/skills/library in your project. Claude Code loads it when a task matches its description.

How do I install Library in Codex?

Run `npx skills add disler/the-library --skill library -a codex`. Or copy the skill folder (the disler/the-library repository) into .agents/skills/library in your project. Codex loads it when a task matches its description.

Can I use Library in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add disler/the-library --skill library -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/library, .gemini/skills/library, .github/skills/library and .opencode/skills/library in your project.

What does Library need to run?

Going by SKILL.md and its folder, Library needs the command-line tools its instructions call (git and gh) and credentials named GITHUB_TOKEN. Our summary lists: A credential in GITHUB_TOKEN.

Does Library access the network?

SKILL.md names 2 domains. In commands or code: github.com and raw.githubusercontent.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Library safe to install?

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.

What licence does Library use?

Library is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Library use?

About 2.2k tokens (SKILL.md is roughly 8.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Library?

Skills that share tags, products or a category with Library: Distributed Triage (pytorch/pytorch, 104k stars), Distributed Tracing (wshobson/agents, 40k stars), Distribute Skill To All Agents (sickn33/agentic-awesome-skills, 47k stars) and Distributed Training (aiming-lab/AutoResearchClaw, 15k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Library?

disler (a GitHub user) maintains it in disler/the-library, which has 428 GitHub stars. The repository was last updated on March 15, 2026.

Source: disler/the-library on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.