skill-creator

skill-creator is a skill for Claude Code, Codex from anymouschina/TapCanvas. It costs 64 tokens per session (8,084 once invoked), scanned A, a copy of skill-creator, MIT.

A workflow for creating, improving, and testing instructions that teach coding agents how to perform a task. It focuses on reliable triggering, clear boundaries, practical steps, and measuring results.

In plain words
What is it for?
Use it to create a new skill, revise an existing one, optimize when it activates, run evaluations, or compare its performance.
Why use it?
It helps turn vague or inconsistent agent instructions into guidance that works across different requests. Testing can expose missing rules, weak checks, and cases where the skill is used incorrectly.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions Claude Code.

Good fit Use it to create a new skill, revise an existing one, optimize when it activates, run evaluations, or compare its performance.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/anymouschina/tapcanvas/skill-creator
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.

Any agent
npx skills add anymouschina/TapCanvas --skill skill-creator
Clone the repo
git clone --depth 1 https://github.com/anymouschina/TapCanvas

Made for: Claude Code, Codex.

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 skill-creator

README.md
[![agentmods](https://agentmods.dev/badge/skills/anymouschina/tapcanvas/skill-creator.svg)](https://agentmods.dev/skills/anymouschina/tapcanvas/skill-creator)
Your own site
<a href="https://agentmods.dev/skills/anymouschina/tapcanvas/skill-creator"><img src="https://agentmods.dev/badge/skills/anymouschina/tapcanvas/skill-creator.svg" alt="Measured on agentmods" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,084 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 83% copy Near-identical to another mod 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 5.1 $0.00064 $0.08084
Opus 5 $0.00032 $0.04042
Sonnet 5 $0.00013 $0.01617
Haiku 4.5 $0.00006 $0.00808

Measured 8d ago against content hash 5d7761f90dbd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

skill-creator 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 8d ago.

The scan reads SKILL.md. This mod also ships 10 executable files (eval-viewer/generate_review.py, scripts/__init__.py, scripts/aggregate_benchmark.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.

Origin

This is a copy

83% identical to skill-creator — 125 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

apps/agents-cli/skills/skill-creator/SKILL.md · 564 lines

How it starts

The opening of the file, as written. The whole thing — 564 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Creator

A skill for creating new skills and iteratively improving them.

Your job is not just to produce a valid SKILL.md. Produce a skill that triggers reliably, resists misuse, has clear boundaries, and stays coherent across many prompts. Treat "technically works" as the floor.

What High-Quality Skills Actually Have

Weak skills usually look polished but miss one of these layers:

  • Role
  • Outcome
  • Workflow
  • Decision rules
  • Boundaries
  • Quality bar
  • Resource strategy

If one is missing, the skill is probably underspecified.

Use Exemplars Properly

When the user gives you a strong skill as reference, reverse-engineer it. Extract what it optimizes for, what it treats as non-negotiable, how it separates core instructions from references, where it draws boundaries, how it names failure modes, and whether it includes a review loop.

Transfer the pattern, not the prose. Useful pattern names include:

  • "identity + workflow + anti-patterns + quality gate"
  • "domain worldview first, execution steps second"
  • "teach the taste, not just the format"
  • "bundle the nuance into references, keep the operating loop in SKILL.md"

If you need a concrete comparison rubric for strong versus weak skills, read references/quality_bar.md.

At a high level, the process of creating a skill goes like this:

  • Decide what you want the skill to do and roughly how it should do it
  • Write a draft of the skill
  • Create a few test prompts and run claude-with-access-to-the-skill on them
  • Help the user evaluate the results both qualitatively and quantitatively
    • While the runs happen in the background, draft some quantitative evals if there aren't any (if there are some, you can either use as is or modify if you feel something needs to change about them). Then explain them to the user (or if they already existed, explain the ones that already exist)
    • Use the eval-viewer/generate_review.py script to show the user the results for them to look at, and also let them look at the quantitative metrics
  • Rewrite the skill based on feedback from the user's evaluation of the results (and also if there are any glaring flaws that become apparent from the quantitative benchmarks)
  • Repeat until you're satisfied
  • Expand the test set and try again at larger scale

Read the full file on GitHub · 564 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. 8d ago First seen · 564 lines · 64 tokens per session scan A 5d7761f90dbd

Subscribe to this mod's changes

skill-creator is a skill published in the GitHub repository anymouschina/TapCanvas (600 stars, last pushed 2d ago), licensed MIT. It adds 64 tokens to every session and 8,084 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 83% identical to skill-creator, differing in 125 lines, and is treated as a copy.

Related

Other skills, from other repositories

dramake

A production workflow for turning an idea, story, script, storyboard, or existing footage into a short AI drama or film. It covers planning, generation, voice, editing, and quality checks for formats such as vertical and horizontal video.

xixihhhh/ai-short-drama-skill · 279 tokens

last30Days

Resolve "last30Days" to a concrete ISO date range relative to your run time — a rolling 30-day window ending today. Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a "last 30 days" / trailing-month task…

chaitanyagiri/munder-difflin · 83 tokens

thisWeek

Resolve "thisWeek" to a concrete ISO date range relative to your run time — this week so far (Monday → today). Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a week-to-date task (this week's activity…

chaitanyagiri/munder-difflin · 77 tokens

short-drama-storyboard

A workflow for turning a Chinese short-drama script and its visual facts into a shot-by-shot storyboard with frozen starting-frame prompts.

zenstory-ai/drama-skills · 102 tokens

md-fetch-summarize

Fetch a URL and return a concise markdown summary of its content. Read-only: no files are written; the summary is returned as output only. Use when asked to "fetch and summarize", "summarize this URL", "what does this page say", or "get the content of ". Proactively suggest when the user pastes a URL and asks what it…

chaitanyagiri/munder-difflin · 93 tokens

vchart-development-assistant

A coding assistant for VChart, a JavaScript chart library used to build visualizations such as bar, line, and pie charts.

VisActor/VChart · 144 tokens