create-skill

create-skill is a skill for Claude Code, Codex from fledgeling-co/fledgeling-plugins. It costs 235 tokens per session (3,124 once invoked), scanned A, original, MIT.

A guided process for creating a new coding-agent skill from an initial idea. It clarifies the goal, uses evidence to shape the design, tests the result, and prepares it for delivery.

In plain words
What is it for?
Use it to interview a requester, define a skill’s requirements, design its instructions, test its behavior, and prepare the resulting files for another model or user.
Why use it?
It helps prevent a skill from being built around an unclear or incomplete request. It also checks whether the finished skill works better than having no skill at all.

Skill for Claude CodeCodex

Part of the create-skill plugin — 1 skill shipped together

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/fledgeling-co/fledgeling-plugins/create-skill
Any agent
npx skills add fledgeling-co/fledgeling-plugins --skill create-skill
Clone the repo
git clone --depth 1 https://github.com/fledgeling-co/fledgeling-plugins

Made for: Claude Code, Codex.

Or install create-skill, the plugin that ships this one along with the rest of its 1 skill.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for create-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/create-skill.svg)](https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/create-skill)
Your own site
<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/create-skill"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/create-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 235 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,124 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 $0.00235 $0.03124
Opus 5 $0.00118 $0.01562
Sonnet 5 $0.00047 $0.00625
Haiku 4.5 $0.00023 $0.00312

Measured 4d ago against content hash 510f6472e3f1, 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 4d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/banner_sheet.py, scripts/render_banner.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/create-skill/skills/create-skill/SKILL.md · 250 lines

How it starts

The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.

create-skill

Build a skill that does not exist yet, properly: understand what the user actually wants before writing anything, ground the design in evidence rather than instinct, prove it works against the honest baseline of not having it, and ship it like a product.

The sibling of improve-skill. That one starts from an artifact and its failures; this one starts from an intention, which is harder, because an unstated intention is the most common reason a new skill misses. So this pipeline front-loads the interview and treats a vague answer as a defect to fix rather than a constraint to work around.

Running as a Gemini model? Read gemini.md in this directory first, then follow this file with the overrides it names. Turns Phase 2's traceability rule and Phase 5's banner-through-design-craft into a filled ledger and file-gated phases, restores the verification scaffolding the Opus brief file strips, and names the four deliverables to hand to another model. Other models skip it.

Phase 0 — Discovery (the phase that decides everything)

A new skill has no predecessor to argue with, so the brief is the only specification. Get it right before anything else runs. Full protocol: references/discovery.md.

The short version:

  • Answer what you can from what you already have. The conversation, the repo, sibling skills, an earlier subagent's findings, a failed workflow's output. A question whose answer is already on disk wastes the user's attention and makes the rest look less considered.
  • Then ask, with recommendations. Use AskUserQuestion, multi-choice where the options are genuinely discrete, each option carrying what it means and what it costs. Lead with the one you would pick and say why. Users answer a recommendation faster than an open question, and a recommendation they reject is itself information.
  • Cover the axes a skill actually turns on: what triggers it, what it produces, who reads the output, what "done" looks like, what it must never do, whether outputs are objectively checkable, and what existing tools or skills it should route to rather than reimplement.
  • Leave room for notes. Every question invites free text alongside the choice; the notes are where the real constraint usually appears.

Read the full file on GitHub · 250 lines

Files

What ships with it

8 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. 4d ago First seen · 250 lines · 235 tokens per session scan A 510f6472e3f1

Subscribe to this mod's changes

create-skill is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed today), licensed MIT. It adds 235 tokens to every session and 3,124 once invoked, about $0.0012 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 2026-08-31.

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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 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