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

Claude Skill

by feiskyer in feiskyer/codex-settings

Delegate a task to the Claude Code CLI, typically a headless claude -p run.

MITAuto-check passed

Install Claude Skill

skills CLI
$ npx skills add feiskyer/codex-settings --skill claude-skill -a claude-code

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

GitHub CLI
$ gh skill install feiskyer/codex-settings claude-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/feiskyer/codex-settings.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/claude-skill .claude/skills/claude-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
claude-skill
GitHub stars
244
Token cost
~742 tokens
SKILL.md length
365 words
Files
4 (incl. references)
Skills in repo
11
Repo updated
First seen
Licence
MIT

At a glance

Delegate a task to the Claude Code CLI, typically a headless claude -p run.

  • The user wants the work executed through Claude Code rather than answered inline
  • SKILL.md covers Core rules, Check what the task needs, Basic shape and When to pause, plus 1 more section
  • Calls claude

What it does

Claude Skill is an agent skill from feiskyer/codex-settings. Delegate a task to the Claude Code CLI, typically a headless claude -p run. Use when the user wants the work executed through Claude Code rather than answered inline.

Its SKILL.md is about 740 tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `agents/openai.yaml`, `references/examples.md` and `references/flags-and-permissions.md`).

The repository describes itself as: Curated skills, profiles, and config templates that supercharge Codex CLI — multi-model, deep research, image gen & browser automation. The licence is MIT.

When your agent uses it

  • The user wants the work executed through Claude Code rather than answered inline

Example prompts

  • “/claude-skill”

What it can do on your machine

Read from SKILL.md and the folder at commit d7f6570. 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:

    • claude

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

  • Network

    No URLs in SKILL.md.

    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

Claude Skill loads about 742 tokens when it runs, and up to ~2.6k if it reads all its reference files. Until then it costs about 45 tokens; SKILL.md has 365 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~45
When it runs · the whole SKILL.md, loaded when a task matches
~742
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.6k

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 feiskyer/codex-settings at commit d7f6570, republished under its MIT licence (© feiskyer). 365 words, ~742 tokens.

Download SKILL.mdSave it as .claude/skills/claude-skill/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
claude-skill
description
Delegate a task to the Claude Code CLI, typically a headless `claude -p` run. Use when the user wants the work executed through Claude Code rather than answered inline.

Claude Code Headless Mode

Build and run claude commands for work that should be executed through Claude Code itself.

ReferenceRead it when
references/flags-and-permissions.mdThe command needs more than -p — permission modes, tool scoping, output formats, flag inventory, installation
references/examples.mdYou want a worked command for a specific shape of task (read-only analysis, safe edit run, JSON report, resume, MCP, sandboxed unattended run)

Requires the claude CLI installed and authenticated on the target machine.

Core rules

  • claude --help on the target machine is the compatibility floor. CLI flags and permission-rule syntax move faster than docs and copied examples, and they differ between builds. Verify any uncommon flag there before emitting it.
  • Do not add --model unless the user asked for an override or the workflow must pin a model for reproducibility. The user's configured model is the right default.
  • Prefer --append-system-prompt over --system-prompt unless replacing Claude Code's default behavior is the point.
  • Choose the least-permissive mode that still fits the task. acceptEdits is the usual starting point for coding automation. For a truly unattended run, reach for explicit permission rules or dontAsk first; bypassPermissions is only for an already-isolated environment.

Check what the task needs

Before execution, confirm the CLI is available and authenticated. Consult claude --help for flags needed by this command; use version or diagnostic commands when compatibility or installation is in doubt. A request for a command example does not authorize running that task.

Show full SKILL.md (128 more words)Show less

Basic shape

bash
claude -p "summarize the repository architecture"
claude -p "review the auth layer for risks" --output-format json

Everything else is a matter of scoping tools and permissions around that — see the references.

When to pause

Pause for missing credentials, unavailable required capabilities, or a permission expansion. If an equivalent supported command stays within the request, use it without adding an approval step.

What to return

For execution requests, run the authorized command and inspect its result and relevant artifacts; do not stop at printing a command or treat exit code zero as proof that the requested work is complete. Continue bounded follow-up within the existing scope when work remains. For command-only requests, return the command without executing it.

Report the command, outcome, relevant checks, and any permission or validation gaps. Include a resume command only when the workflow is meant to continue later.

© feiskyer, 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 3 other files (references) in skills/claude-skill of feiskyer/codex-settings.

  • SKILL.md
  • agents/openai.yaml
  • references/examples.md
  • references/flags-and-permissions.md

Open the folder on GitHubat commit d7f6570

Compare with similar skills

Claude 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.

Claude Skill compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Claude Skill this skillfeiskyer/codex-settings244—~742Automated safety check: PassMIT
Delegate Workpaperclipai/paperclip99k—~372Automated safety check: PassMIT
Event Delegationthedaviddias/Front-End-Checklist74k—~500Automated safety check: PassMIT
Delegating To Agentssickn33/agentic-awesome-skills47k1 repos~1kAutomated safety check: PassMIT
Opencode Delegatesickn33/agentic-awesome-skills47k1 repos~2.8kAutomated safety check: PassMIT
Cline Delegatesickn33/agentic-awesome-skills47k1 repos~1.7kAutomated safety check: PassMIT

Similar skills

  • Delegate Work

    paperclipai/paperclip

    Delegate user-requested work to an existing Paperclip agent, with a durable task reference and clear execution expectations.

    99k GitHub stars~372 tokensUpdated today
    Auto-check passed

  • Event Delegation

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing scripts, client components, bundles, or runtime behavior related to Use event delegation for dynamic content.

    74k GitHub stars~500 tokensUpdated 3 days ago
    Auto-check passed

  • Delegating To Agents

    sickn33/agentic-awesome-skills

    Delegate bounded work to other AI agents while preserving context, ownership, and progress checks.

    47k GitHub starsUsed in 1 repo~1k tokens
    Auto-check passed

  • Opencode Delegate

    sickn33/agentic-awesome-skills

    Delegate coding tasks to the OpenCode CLI only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.

    47k GitHub starsUsed in 1 repo~2.8k tokens
    Auto-check passed

  • Cline Delegate

    sickn33/agentic-awesome-skills

    Delegate coding tasks to the Cline CLI (cline) only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.

    47k GitHub starsUsed in 1 repo~1.7k tokens
    Auto-check passed

  • Grok Delegate

    sickn33/agentic-awesome-skills

    Delegate coding tasks to the Grok Build CLI only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.

    47k GitHub starsUsed in 1 repo~2.6k tokens
    Auto-check passed

More from feiskyer/codex-settings

All 11 skills in this repo

  • Youtube Transcribe Skill

    feiskyer/codex-settings

    Extract subtitles or a transcript from a YouTube URL and save normalized timestamped text locally.

    244 GitHub stars~745 tokensUpdated 12 days ago
    Auto-check passed

  • Gpt Image Skill

    feiskyer/codex-settings

    Generate or edit images when the user names OpenAI, GPT Image, or a gpt-image model.

    244 GitHub stars~572 tokensUpdated 12 days ago
    Auto-check passed

  • Minimax Image Skill

    feiskyer/codex-settings

    Generate images when the user names MiniMax or image-01/image-01-live.

    244 GitHub stars~495 tokensUpdated 12 days ago
    Auto-check passed

  • Code Simplifier

    feiskyer/codex-settings

    Simplify existing code for clarity and maintainability without changing behavior.

    244 GitHub stars~521 tokensUpdated 12 days ago
    Auto-check passed

  • Deep Research

    feiskyer/codex-settings

    用 Codex CLI 子任务完成多来源深度调研并综合成带出处的报告。用于确实需要分头取证的研究，不用于单次查证或已给定材料的总结。

    244 GitHub stars~302 tokensUpdated 12 days ago
    Auto-check passed

  • Nanobanana Skill

    feiskyer/codex-settings

    Generate, edit, or composite images with Gemini/Nanobanana. An agent skill from feiskyer/codex-settings.

    244 GitHub stars~1.2k tokensUpdated 12 days ago
    Auto-check passed

Questions about Claude Skill

What does Claude Skill do?

Delegate a task to the Claude Code CLI, typically a headless claude -p run. Claude Skill is an agent skill from feiskyer/codex-settings. Delegate a task to the Claude Code CLI, typically a headless claude -p run.

When should I use Claude Skill?

Claude Skill fits situations like: the user wants the work executed through Claude Code rather than answered inline.

How do I install Claude Skill in Claude Code?

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

How do I install Claude Skill in Codex?

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

Can I use Claude 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 feiskyer/codex-settings --skill claude-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/claude-skill, .gemini/skills/claude-skill, .github/skills/claude-skill and .opencode/skills/claude-skill in your project.

What does Claude Skill need to run?

Going by SKILL.md and its folder, Claude Skill needs the command-line tools its instructions call (claude).

Does Claude Skill 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 Claude 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 Claude Skill use?

Claude 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 Claude Skill use?

About 742 tokens (SKILL.md is roughly 3k 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 1.9k tokens, read only when the agent opens those files.

What are the alternatives to Claude Skill?

Skills that share tags, products or a category with Claude Skill: Delegate Work (paperclipai/paperclip, 99k stars), Event Delegation (thedaviddias/Front-End-Checklist, 74k stars), Delegating To Agents (sickn33/agentic-awesome-skills, 47k stars) and Opencode Delegate (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Claude Skill?

feiskyer (a GitHub user) maintains it in feiskyer/codex-settings, which has 244 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on September 27, 2026.

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