new-tool
Skill59 starsChanged 2 days agoMITView on GitHub
Design and ship a brand-new tool on gptgames.dev that beats the best existing version - pick an idea from IDEAS.md (or take the one given), design thesis, mockup critique, tested core, user tests, register it, PR.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- jamesmccomish/mp-mcptheir own version, first seen Oct 20, 2026
- OpenC3/cosmostheir own version, first seen Oct 8, 2026
- ShenSeanChen/waku-agenttheir own version, first seen Oct 8, 2026
- wnkinc/claude-custom-connector-servertheir own version, first seen Jul 16, 2026
- QBT-Labs/openmm-mcptheir own version, first seen Mar 28, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- ShenSeanChen/waku-agent★ 2.2ksame name
- OpenC3/cosmos★ 261same name
- QBT-Labs/openmm-mcp★ 3same name
- jamesmccomish/mp-mcp★ 2same name
- wnkinc/claude-custom-connector-server★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository5 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- improve-gameSkill
- improve-toolSkill
- new-gameSkill
- next-boxSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 67
No layout jumps when a result or error appears, readable contrast, reduced motion respected, no console errors, no network request that …
- Distinctive: line 69
TEST IT ON SOMEONE, IN ROUNDS.
- Distinctive: line 95
Every visual choice is deliberate: if you cannot say why this font, this colour and this shape belong to this tool and not to any other, …
“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Build one new tool for gptgames.dev, as good as it can be built today. Make every decision yourself and explain the important ones in the PR. Do not stop to ask me.
Tool requested (may be empty): $ARGUMENTS
THE BAR Measure it against the best version of this tool that exists anywhere, paid or free. Name that product in your thesis. Not against other pages on this site. A stranger who arrives from a search in the middle of some other task should get a correct result within seconds, trust it without checking it elsewhere, and bookmark the page.
- CHOOSE THE TOOL. If a tool is requested above, that is the tool. If nothing is requested,
read IDEAS.md (starting with Read this first, then Axes, not categories, the gap
lists and Tried and rejected) and pick the idea that best fills a gap the file names.
Either way, check
tools/anddata/tools.jsonso it does not duplicate an existing tool (if it would, stop building a new one and say so: that is a job for /improve-tool). Name it plainly, in the words people search for, and pick a file id that is not taken. In the PR, say in two lines why this tool and why now. - UNDERSTAND THE JOB. In a few lines: who arrives and what they have in hand (a pasted text, a file, a number, a vague question), what they want to leave with, what the best versions of this tool do well and where they annoy, and what a phone user needs. Name the one moment that matters: the result is there and the person believes it. That is your design thesis.
- THE FIRST TEN SECONDS. Before anything visual, write out step by step what a new visitor on a phone sees on arrival, what they touch first, when the result appears, and how they take it away (copy, download, link). The tool is usable without scrolling and shows a worked example, so nobody faces an empty box. Results update as the input changes; a button only where the work is slow or cannot be undone. Then: what happens on bad input, on input a thousand times larger than expected, and when they come back tomorrow. List every state (example, empty, valid, partly valid, invalid, working, done, failed) and what is on screen in each.
- CHOOSE THE LOOK. Derive it from the thesis and from the material the tool handles: palette, typography, shapes, and one motion idea whose only job is to show what just changed. The result is the most prominent thing on the page, the person's input the second. Type must suit the data: aligned figures for numbers, a real monospace for code. Write down why each choice belongs to this tool; a reason that would fit any tool is not a reason. Quiet beats striking. Build a static mockup in your scratchpad, not in the repo, in two states: filled with realistic, awkward content and its result, and the error state. Screenshot both at desktop and phone size. Show the screenshots, one sentence about the tool and the principles below to a critic: a subagent that has not seen your reasoning. It reviews as a harsh critic: what looks cheap, what is confusing, what would make a stranger doubt the result? It must name the three worst defects and give scores from 1 to 10 for first impression, clarity, trust and phone. Do not tell it the pass mark or which round it is. Revise until every score is at least 8, for at most three rounds.
- BUILD IT as CLAUDE.md describes a page:
tools/<id>.html, one self-contained file. Correctness: the logic lives in a DOM-free core with a suite in test/. Derive it from the authoritative source (the spec, the standard, the published formula). Test it with published test vectors or independently checked values, and with the inputs that break tools: empty, whitespace, huge, malformed, non-ASCII, zero and negative, decimal comma, and the boundaries of the domain (leap days, time zones, rounding). Keep the suite in proportion: a text reformatter needs a dozen cases, anything that calculates money, dates or units needs many more. Input: accept what people actually paste, with stray spaces, units and either decimal separator. Never lose it: not on error, not on reload, and undo works. Errors appear next to the field that caused them, in plain words, saying what would be accepted. Speed: typing never stutters. Heavy work runs off the main thread, shows progress and can be cancelled. Access: every control is labelled and reachable by keyboard, the phone shows the right keyboard for each field, and result changes are announced to screen readers. No layout jumps when a result or error appears, readable contrast, reduced motion respected, no console errors, no network request that carries the person's data. - TEST IT ON SOMEONE, IN ROUNDS. Write three tasks in a visitor's words, not the tool's ("I have this and need that"), one of them with messy input. Give each to a fresh subagent that knows nothing but the local URL and the task. It works in headless Chromium at phone size from screenshots and clicks alone, without reading the source, and reports what it tried, where it hesitated, how many actions it took and the result it got. Check that result yourself. Then give a fresh critic, as in step 4, screenshots of every state on desktop and phone and the testers' reports. It also scores speed to result. Fix the biggest issues and repeat until every score is at least 8 and no tester got stuck, for at most three rounds. If you disagree with the critic, show why in the next round instead of arguing. If a score is still below 8 after the last round, say so in the PR with the open defects.
- REGISTER AND COMMIT as "Adding a game or tool" in CLAUDE.md describes (JSON entry with
featuredoff unless it truly earns the shelf, sidebar, sitemap, screenshot). The commit message says what the tool does and why it looks and works the way it does. Push, open a PR, and give me screenshots, the testers' action counts and the critic's last scores.
PRINCIPLES
- Correct before beautiful. A wrong result is a failure at any level of polish.
- The result is the page. Everything else is on screen only while it helps someone reach it.
- The tool explains itself through labels, a worked example and a live result. A paragraph of instructions means the design has not done its job. The exception is trust: where the result depends on a method or assumption (which standard, which rounding), say so in one line near the result.
- The default is right for most people. An option exists only where real needs differ, and rare ones are folded away.
- Every visual choice is deliberate: if you cannot say why this font, this colour and this shape belong to this tool and not to any other, choose again.
- Take nothing from the person: no sign-up, nothing sent anywhere, nothing stored that would surprise them, and no content of theirs in a link they did not ask for.
One tool per session.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

