A guided workbench for creating new Claude Code skills or improving existing ones.

Use it to brainstorm and write skills, test them, check their consistency, and prepare them for use or refinement.

It organizes skill development into design, planning, building, testing, validation, and final checks.

skill-bench — Skill for Claude Code and Codex by Yiminnn: A guided workbench for creating new Claude Code skills…

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/yiminnn/skill-bench-plugin/skill-bench

Any agent

npx skills add Yiminnn/skill-bench-plugin --skill skill-bench

Clone the repo

git clone --depth 1 https://github.com/Yiminnn/skill-bench-plugin

Made for: Claude Code, Codex.

Or install skill-bench, the plugin that ships this one along with the rest of its 1 skill, 4 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/yiminnn/skill-bench-plugin/skill-bench.svg)](https://agentmods.dev/skills/yiminnn/skill-bench-plugin/skill-bench)

Your own site

<a href="https://agentmods.dev/skills/yiminnn/skill-bench-plugin/skill-bench"><img src="https://agentmods.dev/badge/skills/yiminnn/skill-bench-plugin/skill-bench.svg" alt="Measured on agentmods" height="20"></a>

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,686 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.

Model	Per session	Once invoked
Fable 5	$0.00050	$0.02686
Opus 5	$0.00025	$0.01343
Sonnet 5	$0.00010	$0.00537
Haiku 4.5	$0.00005	$0.00269

Measured 3d ago against content hash 6a4090da526b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-bench 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 3d 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.

skills/skill-bench/SKILL.md · 234 lines

How it starts

The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Bench

Interactive workbench for creating, testing, and refining Claude Code skills through structured conversation.

Five phases: Design (brainstorming) → Plan (writing-plans) → Build & Test (skill-creator) → Validate (consistency-tester) → Finalize (lint + promote).

Refining an existing skill? → Jump to Refine Mode — skips to validation and refinement.

Dependency Check

Before starting, verify required dependencies:

Superpowers (Phases 1-2)

Check if superpowers:brainstorming skill is available via the Skill tool
If not available, run: claude plugin install claude-plugins-official/superpowers
Verify installation succeeded
If fails: "Skill Bench requires the superpowers plugin. Install manually: claude plugin install claude-plugins-official/superpowers" — stop

Skill-Creator (Phase 3)

Check if the skill-creator skill is available
If not available: clone skills/skill-creator/ from https://github.com/anthropics/skills to ~/.claude/skills/skill-creator/
Verify ~/.claude/skills/skill-creator/SKILL.md and its internal agents are accessible
If fails: "Phase 3 requires skill-creator. Install from https://github.com/anthropics/skills" — stop

Phase 1: Design

REQUIRED SUB-SKILL: Use superpowers:brainstorming

Before invoking brainstorming:

Set spec location: Tell brainstorming: "Save the design spec to .skillbench/specs/{skill-name}-design.md"
Provide skill-authoring context: Read references/skill-format.md and summarize for brainstorming:
- A Claude Code skill is a SKILL.md file with YAML frontmatter (name, description) and markdown content
- name must be kebab-case: ^[a-z0-9]+(-[a-z0-9]+)*$
- description must start with "Use when", max 1024 chars, trigger-oriented (not workflow-summarizing)
- SKILL.md should stay under 200 lines; heavy content splits to references/
- Token estimate: lines * 6
- Skills can include companion agents (.md files in agents/)
Check for name collisions: Glob skills/**/SKILL.md and agents/**/*.md. Warn about shadowing.

Read the full file on GitHub · 234 lines

Files

What ships with it

5 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.

3d ago First seen · 234 lines · 50 tokens per session scan A 6a4090da526b

Subscribe to this mod's changes

skill-bench is a skill published in the GitHub repository Yiminnn/skill-bench-plugin (2 stars, last pushed 5mo ago), licensed MIT. It adds 50 tokens to every session and 2,686 once invoked, about $0.0003 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.

Planning Productivity

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