create-skill

A generator for creating Claude Code skills that ask focused questions using a concrete source of information, then produce one finished output. A skill is a reusable set of instructions for an AI coding assistant.

In plain words
What is it for?
Use it to design and scaffold interview-style skills, including the instruction file, an output template, and optional helper scripts.
Why use it?
It avoids generic interview questions by first grounding the process in material such as a codebase, document collection, website, or transcript archive.

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/alteredcraft/claude-code-plugins/create-skill
Any agent
npx skills add AlteredCraft/claude-code-plugins --skill create-skill
Clone the repo
git clone --depth 1 https://github.com/AlteredCraft/claude-code-plugins

Made for: Claude Code, Codex.

Per session 201 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,510 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 $0.00201 $0.04510
Opus 5 $0.00101 $0.02255
Sonnet 5 $0.00040 $0.00902
Haiku 4.5 $0.00020 $0.00451

Measured yesterday against content hash 1e0816e0ff0b, 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 yesterday.

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.

plugins/anchored-interview/skills/create-skill/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Anchored Interview Skill Creator

Interview the user to produce a new Claude Code skill that follows the Anchored Interview pattern: grounded in a CORPUS, run an interview sharpened by that grounding, then produce a single ARTIFACT. The output is a complete skill directory (SKILL.md + references/<artifact>-template.md, optional scripts) the user can drop into their project, user-global skills, or a plugin.

Why this skill exists

The Anchored Interview is a recurring shape: skills that ground in something concrete (a codebase, a notes folder, a docs site, a transcript archive) and then run a short, adaptive interview whose questions reference what was found in the grounding. The questions get sharper because something concrete preceded them. Done well, the pattern recovers a lot of the value lost to vague or generic skill interviews.

This meta-skill is itself an instance of that pattern — its CORPUS is two bundled worked-example skills (one code-corpus, one docs-corpus) plus a parameterized blueprint; its ARTIFACT is a new skill directory. The recursion is intentional. The most reliable way to teach someone (human or model) to produce something is to walk them through producing it, anchored in real exemplars.

The pattern's invariant: ground before you interview; interview before you act. Anything that breaks that invariant doesn't belong in this skill's output.

Workflow

The sequence matters. Do not jump ahead.

1. Confirm the seed intent in one sentence

Before reading any source material, get the user's intent in one sentence: what type of Anchored Interview skill do you want to create?

If they already said it clearly in the prompt, paraphrase it back and ask "is that right?" — don't make them repeat themselves. If their seed is vague ("I want a skill for my writing"), ask one or more clarifying questions to narrow it before grounding. Grounding the wrong area is wasted work. DO NOT go too deep at this point — just enough to shape the grounding step.

Read the full file on GitHub · 161 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday First seen · 161 lines · 0 tokens per session scan A 1e0816e0ff0b

Subscribe to this mod's changes

create-skill is a skill published in the GitHub repository AlteredCraft/claude-code-plugins (13 stars, last pushed 3mo ago), licensed MIT. It adds 201 tokens to every session and 4,510 once invoked, about $0.0010 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