New: 97,000+ 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

Create Agent Skill

by oocx in oocx/tfplan2md

Create a new Agent Skill following project standards and templates.

MITAuto-check passedAI & LLM Engineering

Install Create Agent Skill

skills CLI
$ npx skills add oocx/tfplan2md --skill create-agent-skill -a claude-code

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

GitHub CLI
$ gh skill install oocx/tfplan2md create-agent-skill --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/oocx/tfplan2md.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/create-agent-skill .claude/skills/create-agent-skill && 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
create-agent-skill
GitHub stars
174
Token cost
~1.5k tokens
SKILL.md length
618 words
Files
2
Skills in repo
28
Repo updated
First seen
Licence
MIT

At a glance

Create a new Agent Skill following project standards and templates.

  • Works in 5 steps: Gather Information → Create Directory Structure → Create SKILL.md → …
  • Tasks that involve Building AI agents
  • SKILL.md covers Purpose, When to Create a Skill, Hard Rules and Best Practices, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Create Agent Skill is an agent skill from oocx/tfplan2md. Create a new Agent Skill following project standards and templates. Use this when you need to encapsulate a new capability or workflow.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `templates/SKILL.md`).

It sits in AI & LLM Engineering, covering Building AI agents. The repository describes itself as: Convert terraform plans (json) into human readable markdown for easier review of changes in pull requests. The licence is MIT.

When your agent uses it

  • Tasks that involve Building AI agents

Example prompts

  • “/create-agent-skill”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Gather Information
  2. Create Directory Structure
  3. Create SKILL.md
  4. Update Documentation
  5. Verify

What it can do on your machine

Read from SKILL.md and the folder at commit 3fa4b5a. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

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

  • Network

    Links to these hosts (documentation or services it may open):

    • agentskills.io
    • github.com
    • code.visualstudio.com
    • dev.to
    • github.blog

    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

Create Agent Skill loads about 1.5k tokens when it runs. Until then it costs about 39 tokens; SKILL.md has 618 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~39
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

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 oocx/tfplan2md at commit 3fa4b5a, republished under its MIT licence (© oocx). 618 words, ~1,457 tokens.

Download SKILL.mdSave it as .claude/skills/create-agent-skill/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
create-agent-skill
description
Create a new Agent Skill following project standards and templates. Use this when you need to encapsulate a new capability or workflow.

Create Agent Skill

Purpose

Standardize the creation of new Agent Skills to ensure they are consistent, discoverable, and follow best practices.

When to Create a Skill

  • Complex Tooling: When an agent needs to run a sequence of scripts or commands that are too long for the main agent prompt.
  • Shared Capabilities: When multiple agents need the same capability (e.g., "Run UAT" used by UAT Tester and Quality Engineer).
  • Strict Procedures: When a process requires exact adherence to a checklist or script (e.g., Release process).

Hard Rules

Must
  • Create the skill in .agents/skills/<skill-name>/.
  • Use kebab-case for the skill name.
  • Ensure the skill name matches the parent directory name exactly.
  • Ensure name is 1–64 characters, lowercase letters/numbers/hyphens only.
  • Ensure name does not start or end with - and does not contain consecutive hyphens (--).
  • Include a SKILL.md with valid YAML frontmatter.
  • Include a description in the frontmatter (max 1024 chars).
  • Create scripts/ and templates/ subdirectories only if needed.
  • Use the provided template for SKILL.md.
  • Update docs/workflow.md to register the new skill in the "Available Skills" table.
Must Not
  • Create skills in the root .github/ directory.
  • Use spaces or special characters in the skill name.
  • Leave the description empty.

Best Practices

  • Self-Contained: A skill should include all necessary scripts and templates within its folder.
  • Progressive Disclosure: the harness only loads the skill body when the description matches the user's intent. Keep descriptions specific.
  • Verification: Confirm the skill loads by asking for the task it covers in a fresh session and checking that the skill is invoked.
  • Approval Minimization: Design skills to reduce the number of Maintainer approval prompts (terminal command approvals) so agents can execute workflows with minimal interruptions.
    • Prefer a small number of stable wrapper commands over many one-off commands.
    • Batch related operations into a single command where practical (and safe).
    • Prefer tool-based reads (editor tools) over shell commands for read-only actions when available.
    • Reuse existing repo scripts (e.g., scripts/uat-*.sh) instead of duplicating multi-step command sequences.
    • If a workflow is inherently risky (force-push, merge, deleting branches), keep it explicit and gated, but still consolidate the surrounding steps.

Actions

Show full SKILL.md (274 more words)Show less
1. Gather Information

Ask the user for:

  • Skill Name: Short, descriptive, kebab-case (e.g., run-uat, deploy-docs).
  • Description: One sentence explaining what the skill does and when an agent should load it.
  • Purpose: Detailed explanation of the skill's goal.
  • Approval Plan: Which commands will run, and how to structure them to minimize approvals (prefer a small number of stable wrappers).
2. Create Directory Structure

Run the following command to create the skill directory:

bash
mkdir -p .agents/skills/`<skill-name>`

If your skill includes scripts or templates, add those directories explicitly:

bash
mkdir -p .agents/skills/`<skill-name>`/scripts
mkdir -p .agents/skills/`<skill-name>`/templates
3. Create SKILL.md

Read the template from .agents/skills/create-agent-skill/templates/SKILL.md and create the new SKILL.md file:

bash
cp .agents/skills/create-agent-skill/templates/SKILL.md .agents/skills/`<skill-name>`/SKILL.md

Then, edit the file to replace the placeholders ({{skill-name}}, {{description}}, {{purpose}}) with the gathered information.

4. Update Documentation

Add the new skill to the "Available Skills" table in docs/workflow.md.

5. Verify

Check that the file structure looks like this:

.agents/skills/`<skill-name>`/
├── SKILL.md
├── scripts/
└── templates/

References

Specifications & Documentation
ResourceWhat You'll Find
VS Code Agent SkillsOfficial documentation: SKILL.md format, YAML frontmatter fields, progressive disclosure architecture, and complete examples.
Agent Skills StandardThe open specification: formal schema, interoperability with other AI tools (Claude, Cursor, OpenAI Codex), and integration guides.
Agent Skills SpecificationDetailed field definitions, validation rules, and edge cases for SKILL.md files.
Example Repositories
RepositoryWhat You'll Find
anthropics/skillsReference skills from Anthropic: well-structured examples covering common patterns like debugging, documentation, and code review.
github/awesome-copilotCommunity collection of skills, custom agents, instructions, and prompts. Good source of real-world patterns.
Practical Guides
ResourceWhat You'll Find
Teaching AI Your Repository PatternsHands-on tutorial: real-world example (Selenium testing), key components that work (Clear Rules, Golden Examples, Templates), and verification tips.
GitHub Changelog AnnouncementFeature overview, availability across VS Code/CLI/coding agent, and links to community resources.

© oocx, 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 1 other file in .agents/skills/create-agent-skill of oocx/tfplan2md.

  • SKILL.md
  • templates/SKILL.md

Open the folder on GitHubat commit 3fa4b5a

Compare with similar skills

Create Agent Skill 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.

Create Agent Skill compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Create Agent Skill this skilloocx/tfplan2md174—~1.5kAutomated safety check: PassMIT
Apex Agent Authoringjonathan-vella/apex217—~1.8kAutomated safety check: PassMIT
New Resource WorkflowGoogleCloudPlatform/magic-modules973—~512Automated safety check: PassCustom licence
Hcp Create Agentopenshift-eng/ai-helpers120—~3.7kAutomated safety check: PassApache-2.0
Autogpt AgentsOrchestra-Research/AI-Research-SKILLs13k3 repos~2.3kAutomated safety check: NotesMIT
Agent BuildershareAI-lab/learn-claude-code78k6 repos~1.2kAutomated safety check: PassMIT

Similar skills

  • Apex Agent Authoring

    jonathan-vella/apex

    WORKFLOW SKILL — Creates, restructures, and audits GitHub Copilot .agent.md and .prompt.md files with correct frontmatter, handoffs, model policy, context budgets, and validation.

    217 GitHub stars~1.8k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • New Resource Workflow

    GoogleCloudPlatform/magic-modules

    Workflow specifically for creating a new resource, supporting both autogen and manual generation.

    973 GitHub stars~512 tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Hcp Create Agent

    openshift-eng/ai-helpers

    A skill your agent uses when you need to deploy HyperShift clusters on bare metal, edge environments, or disconnected infrastructures using pre-provisioned agents

    120 GitHub stars~3.7k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Autogpt Agents

    Orchestra-Research/AI-Research-SKILLs

    Autonomous AI agent platform for building and deploying continuous agents.

    13k GitHub starsUsed in 3 repos~2.3k tokens
    AI & LLM EngineeringAuto-check: notes

  • Agent Builder

    shareAI-lab/learn-claude-code

    Design and build AI agents for any domain. An agent skill from shareAI-lab/learn-claude-code.

    78k GitHub starsUsed in 6 repos~1.2k tokens
    AI & LLM EngineeringAuto-check passed

  • Azure AI Projects Python SDK

    microsoft/skills

    Official

    Reference for building on Microsoft Foundry with the azure-ai-projects Python SDK: project clients, versioned agents, evaluations, connections, datasets and indexes.

    3.1k GitHub starsUsed in 6 repos~2.8k tokens
    AI & LLM EngineeringAuto-check passed

More from oocx/tfplan2md

All 28 skills in this repo

  • Detect Diagram Crossings

    oocx/tfplan2md

    Detect and analyze edge crossings and overlaps in SVG workflow diagrams using geometric intersection algorithms and visual analysis.

    174 GitHub stars~4.3k tokensUpdated yesterday
    Auto-check passed

  • Generate Release Screenshots

    oocx/tfplan2md

    Generate PNG screenshots for release notes using the repository's HtmlRenderer and ScreenshotGenerator tools.

    174 GitHub stars~3.7k tokensUpdated yesterday
    Auto-check passed

  • Git Rebase Main

    oocx/tfplan2md

    Safely rebase the current feature branch on top of the latest origin/main.

    174 GitHub stars~456 tokensUpdated yesterday
    Auto-check passed

  • Next Issue Number

    oocx/tfplan2md

    Determine the next available issue number across all change types (feature, fix, workflow, website) by checking both local docs and remote branches, then reserve it by pushing an empty branch.

    174 GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed

  • Run Uat

    oocx/tfplan2md

    Run User Acceptance Testing by creating a PR with rendered markdown on GitHub or Azure DevOps.

    174 GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

  • Update Workflow Diagram

    oocx/tfplan2md

    Convert the mermaid diagram in docs/workflow.md to a blueprint-styled SVG for the website.

    174 GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Create Agent Skill

What does Create Agent Skill do?

Create a new Agent Skill following project standards and templates. Create Agent Skill is an agent skill from oocx/tfplan2md. Create a new Agent Skill following project standards and templates.

When should I use Create Agent Skill?

Create Agent Skill fits situations like: tasks that involve Building AI agents.

How do I install Create Agent Skill in Claude Code?

Run `npx skills add oocx/tfplan2md --skill create-agent-skill -a claude-code`. Or copy the skill folder (.agents/skills/create-agent-skill in oocx/tfplan2md) into .claude/skills/create-agent-skill in your project. Claude Code loads it when a task matches its description.

How do I install Create Agent Skill in Codex?

Run `npx skills add oocx/tfplan2md --skill create-agent-skill -a codex`. Or copy the skill folder (.agents/skills/create-agent-skill in oocx/tfplan2md) into .agents/skills/create-agent-skill in your project. Codex loads it when a task matches its description.

Can I use Create Agent Skill 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 oocx/tfplan2md --skill create-agent-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/create-agent-skill, .gemini/skills/create-agent-skill, .github/skills/create-agent-skill and .opencode/skills/create-agent-skill in your project.

What does Create Agent Skill need to run?

SKILL.md names no scripts, command-line tools or credentials: Create Agent Skill is instructions for the agent only.

Does Create Agent Skill access the network?

SKILL.md names 5 domains. As links in the text: agentskills.io, github.com, code.visualstudio.com, dev.to and github.blog. This is read from the text; nothing was executed.

Is Create Agent Skill 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 Create Agent Skill use?

Create Agent Skill is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Create Agent Skill use?

About 1.5k tokens (SKILL.md is roughly 5.8k 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 Create Agent Skill?

Skills that share tags, products or a category with Create Agent Skill: Apex Agent Authoring (jonathan-vella/apex, 217 stars), New Resource Workflow (GoogleCloudPlatform/magic-modules, 973 stars), Hcp Create Agent (openshift-eng/ai-helpers, 120 stars) and Autogpt Agents (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Create Agent Skill?

oocx (a GitHub user) maintains it in oocx/tfplan2md, which has 174 GitHub stars. The repository holds 28 skills in this directory. The repository was last updated on October 6, 2026.

Source: oocx/tfplan2md on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.