New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Skill Creator

by prapaa-ai in prapaa-ai/agav

Guide for authoring a new agav skill (SKILL.md). An agent skill from prapaa-ai/agav.

Apache-2.0Auto-check passedAgent Workflows

Install Skill Creator

skills CLI
$ npx skills add prapaa-ai/agav --skill skill-creator -a claude-code

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

GitHub CLI
$ gh skill install prapaa-ai/agav skill-creator --agent claude-code

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

Manual copy
$ git clone --depth 1 https://github.com/prapaa-ai/agav.git skills-src && mkdir -p .claude/skills && cp -r skills-src/source/skills/bundled/skill-creator .claude/skills/skill-creator && rm -rf skills-src

Use ~/.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/

Facts

Skill name
skill-creator
GitHub stars
147
Token cost
~792 tokens
SKILL.md length
379 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
Apache-2.0

At a glance

Guide for authoring a new agav skill (SKILL.md). An agent skill from prapaa-ai/agav.

  • Works in 8 steps: Interview the user first → Ask the user for an example of the task… → Create the skill as /SKILL.md where is… → …
  • Tasks that involve Skill authoring
  • Calls pnpm

What it does

Skill Creator is an agent skill from prapaa-ai/agav. Guide for authoring a new agav skill (SKILL.md)

Its SKILL.md is about 790 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Skill authoring. The repository describes itself as: Terminal-native AI coding assistant for real repositories. Inspect code, edit files, run tests, and verify changes from the CLI. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Skill authoring

Example prompts

  • “/skill-creator”

Requirements

  • Pre-approved tools (allowed-tools): read_file, write_file, edit_file, find_files, list_directory, run_command

Workflow steps

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

  1. Interview the user first
  2. Ask the user for an example of the task done well (a past output, an email they like) — real examples make skills far better than abstract…
  3. Create the skill as /SKILL.md where is lowercase-with-hyphens and matches the name` field. Location
  4. Use this frontmatter format (all fields shown; minimum is name + description)
  5. Rules that matter
  6. After writing the file, verify it loads: run the skill with /skills in the session or restart agav and check it appears. If it does not…
  7. Skills bundled into the agav repo itself (source/skills/bundled/) additionally require running pnpm gen:skills so the manifest picks them…
  8. Suggest testing with one real task, then tightening the instructions wherever the agent guessed wrong.

What it can do on your machine

Read from SKILL.md and the folder at commit 9e9582a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • read_file
    • write_file
    • edit_file
    • find_files
    • list_directory
    • run_command

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • pnpm

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

  • Network

    No URLs in SKILL.md. Its commands use pnpm, which can reach the network depending on how they are called.

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

  • Credentials

    Names no API keys, tokens, secrets or passwords.

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

Context cost

Skill Creator loads about 792 tokens when it runs. Until then it costs about 15 tokens; SKILL.md has 379 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~15
When it runs · the whole SKILL.md, loaded when a task matches
~792

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 prapaa-ai/agav at commit 9e9582a, republished under its Apache-2.0 licence (© prapaa-ai). 379 words, ~792 tokens.

Download SKILL.mdSave it as .claude/skills/skill-creator/SKILL.md (or your agent's skills folder).
name
skill-creator
description
Guide for authoring a new agav skill (SKILL.md)
allowed-tools
read_file, write_file, edit_file, find_files, list_directory, run_command
version
1.0.0
invocation
user
tags
meta, authoring

Skill Creator

Create a new skill for agav: a directory containing a SKILL.md file with YAML frontmatter and Markdown instructions.

Instructions

  1. Interview the user first:

    • What task should the skill handle, and what triggers it? (a phrase they type, a situation the agent should notice)
    • Who is it for: just them, their team, or public sharing?
    • What tools does the task need: reading files, writing files, running commands, web access?

  2. Ask the user for an example of the task done well (a past output, an email they like) — real examples make skills far better than abstract descriptions.

  3. Create the skill as <slug>/SKILL.md where <slug> is lowercase-with-hyphens and matches the name field. Location:

    • Personal skills: inside the agav config directory's skills folder — run /skills in a session to see the exact path for your platform.
    • Project skills: .agav/skills/<slug>/SKILL.md in the repo root — these override bundled/global skills of the same name.

  4. Use this frontmatter format (all fields shown; minimum is name + description):

    yaml
    ---
name: my-skill
description: One line — what it does and when to use it (this is what the agent sees when deciding to trigger)
version: 1.0.0
invocation: both   # user = manual /skill only, agav = auto-trigger only, both = either
allowed-tools: read_file write_file run_command
tags:
  - topic
---

  5. Rules that matter:

    • description is the trigger — write it as "does X for Y situations", not marketing copy.
    • Allowed tools are validated against agav's known tools: read_file, write_file, edit_file, run_command, grep_search, find_files, list_directory, web_search, lsp_query, read_notebook, edit_notebook, fetch_url, update_plan, github, overview, run_tests, save_memory, subagent, activate_skill. An unknown name silently drops that tool.
    • The body is instructions to the agent. Number the steps. State what to do when inputs are missing, and what NOT to do (never invent data, never overwrite originals).
    • The body must not contain prompt-injection phrasing or destructive shell patterns (e.g. force-deleting from filesystem root, piping downloads into a shell) — validation rejects those patterns and such examples trip the scanner even in prose.
    • Keep the whole file under 64KB; a focused skill beats a sprawling one.

  6. After writing the file, verify it loads: run the skill with /skills in the session or restart agav and check it appears. If it does not load, check YAML indentation (two spaces, no tabs) and that name matches the directory.

  7. Skills bundled into the agav repo itself (source/skills/bundled/) additionally require running pnpm gen:skills so the manifest picks them up — for personal and project skills this is not needed.

  8. Suggest testing with one real task, then tightening the instructions wherever the agent guessed wrong.

© prapaa-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in source/skills/bundled/skill-creator of prapaa-ai/agav.

Open the folder on GitHubat commit 9e9582a

Compare with similar skills

Skill Creator 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 Creator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Skill Creator this skillprapaa-ai/agav147—~792Automated safety check: PassApache-2.0
Skill CreatorAzure/azqr79589 repos~8.2kAutomated safety check: PassApache-2.0
Claude Code Skill Developer Guidediet103/claude-code-infrastructure-showcase10k11 repos~3.5kAutomated safety check: PassMIT
Darwin Skill Optimizeralchaincyf/darwin-skill6.2k1 repos~4.7kAutomated safety check: PassMIT
Claude Code Command Developmentanthropics/claude-plugins-official38k10 repos~4.8kAutomated safety check: PassApache-2.0
Claude Code Plugin Structureanthropics/claude-plugins-official38k10 repos~3.4kAutomated safety check: PassApache-2.0

Similar skills

  • Skill Creator

    Azure/azqr

    Official

    Create new skills, modify and improve existing skills, and measure skill performance.

    795 GitHub starsUsed in 89 repos~8.2k tokens
    Agent WorkflowsAuto-check passed

  • Claude Code Skill Developer Guide

    diet103/claude-code-infrastructure-showcase

    A guide to creating and managing Claude Code skills with auto-activation: skill-rules.json triggers, hooks, enforcement levels, YAML frontmatter and progressive disclosure.

    10k GitHub starsUsed in 11 repos~3.5k tokens
    Agent WorkflowsAuto-check passed

  • Darwin Skill Optimizer

    alchaincyf/darwin-skill

    Scores SKILL.md files on a nine-dimension rubric, then improves them in a keep-or-revert loop with independent judge agents, test prompts, git history and human checkpoints.

    6.2k GitHub starsUsed in 1 repo~4.7k tokens
    Agent WorkflowsAuto-check passed

  • Claude Code Command Development

    anthropics/claude-plugins-official

    Official

    Explains how to write Claude Code slash commands: Markdown files with YAML frontmatter, arguments, file references, bash context and interactive prompts.

    38k GitHub starsUsed in 10 repos~4.8k tokens
    Agent WorkflowsAuto-check passed

  • Claude Code Plugin Structure

    anthropics/claude-plugins-official

    Official

    Explains the directory layout, plugin.json manifest and component organization of a Claude Code plugin, including auto-discovery and portable paths.

    38k GitHub starsUsed in 10 repos~3.4k tokens
    Agent WorkflowsAuto-check passed

  • Skill Release Gate

    rohitg00/ai-engineering-from-scratch

    Evaluates an Agent Skill bundle before release for structure, trigger quality, artifact improvement, script correctness, safety, installed-tree integrity and host portability.

    66k GitHub stars~1k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed

More from prapaa-ai/agav

All 12 skills in this repo

  • Git Commit

    prapaa-ai/agav

    Generate a commit message from staged changes. An agent skill from prapaa-ai/agav.

    147 GitHub stars~358 tokensUpdated today
    Auto-check passed

  • Data Clean

    prapaa-ai/agav

    Clean up and analyze CSV/Excel data for non-analysts. An agent skill from prapaa-ai/agav.

    147 GitHub stars~479 tokensUpdated today
    Auto-check passed

  • File Organizer

    prapaa-ai/agav

    Clean up a messy folder with a dry-run plan before moving anything

    147 GitHub stars~460 tokensUpdated today
    Auto-check passed

  • XLSX

    prapaa-ai/agav

    Create, read, and edit Excel .xlsx spreadsheets and CSV files

    147 GitHub stars~486 tokensUpdated today
    Auto-check passed

  • Code Review

    prapaa-ai/agav

    Review code changes for bugs, security issues, and improvements

    147 GitHub stars~384 tokensUpdated today
    Auto-check passed

  • Deep Research

    prapaa-ai/agav

    Multi-source research on a topic with citations. An agent skill from prapaa-ai/agav.

    147 GitHub stars~396 tokensUpdated today
    Auto-check passed

Categories

Questions about Skill Creator

What does Skill Creator do?

Guide for authoring a new agav skill (SKILL.md). An agent skill from prapaa-ai/agav. Skill Creator is an agent skill from prapaa-ai/agav.

When should I use Skill Creator?

Skill Creator fits situations like: tasks that involve Skill authoring.

How do I install Skill Creator in Claude Code?

Run `npx skills add prapaa-ai/agav --skill skill-creator -a claude-code`. Or copy the skill folder (source/skills/bundled/skill-creator in prapaa-ai/agav) into .claude/skills/skill-creator in your project. Claude Code loads it when a task matches its description.

How do I install Skill Creator in Codex?

Run `npx skills add prapaa-ai/agav --skill skill-creator -a codex`. Or copy the skill folder (source/skills/bundled/skill-creator in prapaa-ai/agav) into .agents/skills/skill-creator in your project. Codex loads it when a task matches its description.

Can I use Skill Creator 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 prapaa-ai/agav --skill skill-creator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skill-creator, .gemini/skills/skill-creator, .github/skills/skill-creator and .opencode/skills/skill-creator in your project.

What does Skill Creator need to run?

Going by SKILL.md and its folder, Skill Creator needs the command-line tools its instructions call (pnpm). Its frontmatter pre-approves these tools: read_file, write_file, edit_file, find_files, list_directory, run_command.

Does Skill Creator access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Skill Creator 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 Skill Creator use?

Skill Creator is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Skill Creator use?

About 792 tokens (SKILL.md is roughly 3.2k 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 Skill Creator?

Skills that share tags, products or a category with Skill Creator: Skill Creator (Azure/azqr, 795 stars), Claude Code Skill Developer Guide (diet103/claude-code-infrastructure-showcase, 10k stars), Darwin Skill Optimizer (alchaincyf/darwin-skill, 6.2k stars) and Claude Code Command Development (anthropics/claude-plugins-official, 38k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Skill Creator?

prapaa-ai (a GitHub organization) maintains it in prapaa-ai/agav, which has 147 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 8, 2026.

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