create_skill

Instructions for creating a new command-line skill as a directory with a required instruction file and optional supporting files. A command-line skill is a reusable set of instructions and resources for an agent.

In plain words
What is it for?
Use them when scaffolding a new skill in a project or user-level skill directory.
Why use it?
They define the information that must be agreed on before creating files, including the skill's scope, name, and description.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/aliasjeff/aclix/create_skill
Any agent
npx skills add AliasJeff/ACLIx --skill create_skill
Clone the repo
git clone --depth 1 https://github.com/AliasJeff/ACLIx

Made for: Claude Code, Codex.

Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 813 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00021 $0.00813
Opus 5 $0.00010 $0.00407
Sonnet 5 $0.00004 $0.00163
Haiku 4.5 $0.00002 $0.00081

Measured 2d ago against content hash 28c88ba6653c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create_skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

src/builtin-skills/create_skill/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

This skill defines how to scaffold a new Anthropic-style skill for ACLIx: one directory per skill, SKILL.md as the entry file, and optional scripts/ and reference/ assets. Follow these steps in order; do not skip user confirmation of scope and naming.

Standard Operating Procedure

Step 1 — Confirm scope, name, and description

Use the ask_user tool to agree with the human on all of the following before creating any files:

  1. Target scope

    • Project scope: ./.aclix/skills/ (relative to the current working directory / project root).
    • User global scope: ~/.aclix/skills/ (home directory, portable across projects).
  2. Skill name — Must be a single filesystem-safe identifier (no spaces; use lowercase letters, digits, and underscores if needed). This name becomes the folder name under the chosen scope.

  3. Short description — One or two sentences that will appear in skill listings and may be mirrored in the new skill’s frontmatter description field.

If anything is ambiguous, ask follow-up questions via ask_user until all three are explicit.

Step 2 — Create directory layout

Use the shell tool to create the directory tree (adjust <scope> and <skill_name> to the values from Step 1):

  • <scope>/<skill_name>/scripts/
  • <scope>/<skill_name>/reference/

Example pattern (conceptual):

  • mkdir -p "<scope>/<skill_name>/scripts" "<scope>/<skill_name>/reference"

Use absolute paths when the human prefers them, or resolve paths relative to the confirmed project root. Ensure mkdir -p so existing parents are not an error.

Step 3 — Author SKILL.md

Use the file_write tool to create:

<scope>/<skill_name>/SKILL.md

The file must include:

  1. YAML frontmatter at the very top, with at least:
    • name: — Should match the folder name (<skill_name>) unless the user explicitly requests otherwise.
    • description: — The agreed short description from Step 1.

Read the full file on GitHub · 70 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 70 lines · 21 tokens per session scan A 28c88ba6653c

Subscribe to this mod's changes

create_skill is a skill published in the GitHub repository AliasJeff/ACLIx (23 stars, last pushed 4mo ago), licensed MIT. It adds 21 tokens to every session and 813 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens