visual-review
Skill10 starsChanged 19 days agoMITView on GitHub
Use before a paneline task that changes what the pane, status row or chat draws is called done: screenshot every state of the feature, then adversarial visual-reviewer rounds and fixes until a round finds nothing blocking.
14 other projects use a version of this.
Adopted by
Most recently taken up by
- colinhacks/frizztheir own version, first seen Nov 10, 2026
- dsifry/metaswarmtheir own version, first seen Nov 8, 2026
- usecompai/compound-operations-modeltheir own version, first seen Nov 8, 2026
- davojta/skillstheir own version, first seen Nov 1, 2026
- robritacca-dotcom/rift-dstheir own version, first seen Nov 1, 2026
- robritacca-dotcom/design-systemtheir own version, first seen Oct 28, 2026
Other versions14 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 14
- ai-dynamo/dynamo★ 8.5ksame name
- nubjs/nub★ 4.4ksame name
- dsifry/metaswarm★ 432same name
- ethanplusai/astro-conversion-kit★ 114same name
- usecompai/compound-operations-model★ 31same name
- colinhacks/frizz★ 29same name
- helderberto/agent-skills★ 19same name
- robritacca-dotcom/rift-ds★ 9same name
- malinskibeniamin/skills★ 4same name
- Naoray/skills★ 2same name
4 more not listed
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.
- AGENTS.mdAGENTS.md
- .claude/CLAUDE.mdCLAUDE.md
- add-pane-tabSkill
- live-checkSkill
- write-testSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 13 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
States: Write visual-review.md with the list of states to shoot: every tab, button and window the change adds or touches, each opened and …
- Very specific: line 13
Fix: Every blocking finding with a quote is fixed in the part that draws it, then reshoot every state that part draws.
“Common” is measured: kept by at least 6 in 10 of the 13 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
Visual review
Record dir: backlog/work/task-<id>/ in the main checkout. Screenshots go to shots/ there (git ignores it).
- States. Write
visual-review.mdwith the list of states to shoot: every tab, button and window the change adds or touches, each opened and clicked; empty state; long names; widths 60 and 120 columns; themes dark and light;/color red. - Shoot. Start a session as in skill
live-check(own tmux socket, plugin from your worktree, session namemain). Per state: drive it withtmux -L <socket> send-keysorpython3 .claude/skills/visual-review/click.py <socket> "<label>" [nth], wait for it to settle, thenpython3 .claude/skills/visual-review/shot.py <socket> <record dir>/shots/r<round>-<state> [light](passlightfor the light themes). That writes.png,.txtand.ansi. Crop nothing. - Review. Dispatch two fresh
visual-revieweragents in one message. Give each only the PNG paths and the ticket's user-visible acceptance criteria. Never the diff, your reasoning or the last round's verdict. - Fix. Every
blockingfinding with a quote is fixed in the part that draws it, then reshoot every state that part draws. Anitgoes to the ticket notes, not into a fix. A finding you think is wrong goes to the owner. - Repeat 3-4 with new reviewers until one round has
blocking: 0from both. After round 5 with blocking findings left, stop and give the owner the list with its PNGs. - Record. Append each round to
visual-review.md: findings, what fixed them. Under the last round list the final PNG paths (relative,shots/...), and end the file with the lineverdict: clean. A change that draws nothing different ends withverdict: no-ui - <why>instead. - Report. The done report to the owner names the final PNGs.
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.

