gpt
Skill1 starsChanged 50 days agoMITView on GitHub
Send web research, a code review, UI mockups or a UI critique to GPT. Use as /yah:gpt research <q>.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- runapi-ai/gpttheir own version, first seen Oct 13, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- runapi-ai/gpt★ 0same 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.
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 25
If codex.py says yah:gpt is off, reply that /yah:setup (or setup.py --codex) turns it on, and stop.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Request:
$ARGUMENTS
The forked agent cannot see the conversation that sent this, so the request above must stand alone: the question or what to review, the files or links involved, and what a good answer holds.
The first word is the mode: review reviews this repo, mockup draws UI mockups, critique judges UI screenshots, anything else is research (drop a leading research). The rest is the brief. For critique, take --url <page> or the .png paths out of the brief; they go on the command line, not in the heredoc. A --url must already be reachable (start the dev server first); it is shot at 375x812 and 1440x900.
Run codex.py with Bash as PY "${CLAUDE_SKILL_DIR}/../../scripts/codex.py". PY is python on Windows and python3 elsewhere; use py -3 only if both fail. The brief goes on stdin (-) through a quoted heredoc, so quotes and $ in it stay as written and no temp file is needed. After the command line comes the brief, then YAH_BRIEF on a line of its own:
- research:
PY "<codex.py>" research --timeout 570 - <<'YAH_BRIEF' - review:
PY "<codex.py>" review --timeout 570 "$(git rev-parse --show-toplevel)" - <<'YAH_BRIEF' - mockup:
PY "<codex.py>" mockup --timeout 570 - <<'YAH_BRIEF' - critique:
PY "<codex.py>" critique --timeout 570 --url "<page>" - <<'YAH_BRIEF', or with PNGsPY "<codex.py>" critique --timeout 570 - "<a.png>" "<b.png>" <<'YAH_BRIEF'
If codex.py says yah:gpt is off, reply that /yah:setup (or setup.py --codex) turns it on, and stop.
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.