unslop
AGENTS.md17 starsChanged 5 months agoMITView on GitHub
You rescue ugly vibe-coded React + Tailwind sites. The workflow has three stages; each is fully specified in a skill file. Follow them exactly — they are the product, not suggestions. Where a skill references ${CLAUDE_PLUGIN_ROOT}, substitute the path to this repository. - rules/anti-slop-checklist.md — every design claim needs evidence; this is the scoring rubric and exit bar. - rules/lane-synthesis.md — how to derive a custom design lane; the four files in examples/lanes/ are calibration examples, never a menu to…
1 other project uses a version of this.
Adopted by
Most recently taken up by
- authrain-cloud-abdullahformuli/unslopword for word, first seen Nov 15, 2026
Other versions1 project uses a version of this.
Word for word · 1
- authrain-cloud-abdullahformuli/unslop★ 1100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
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
Files
Unslop — agent instructions (Codex / any AGENTS.md-aware tool)
You rescue ugly vibe-coded React + Tailwind sites. The workflow has three stages; each is fully specified in a skill file. Follow them exactly — they are the product, not suggestions.
| Stage | When | Spec |
| Audit | Site "looks AI-generated / generic / off" | skills/audit/SKILL.md |
| Interview → Lane | Before any restyling | skills/interview/SKILL.md |
| Retheme | Only after LANE.md is approved | skills/retheme/SKILL.md |
Where a skill references ${CLAUDE_PLUGIN_ROOT}, substitute the path to this
repository.
Shared rules (binding for all stages)
- rules/anti-slop-checklist.md — every design claim needs evidence; this is the scoring rubric and exit bar.
- rules/lane-synthesis.md — how to derive a custom design lane; the four files in examples/lanes/ are calibration examples, never a menu to copy from.
- rules/client-report.md — format for the
client-facing
CLIENT-REPORT.htmlthe retheme stage produces at the end. - Scripts in scripts/ provide deterministic checks (screenshots + overflow, WCAG AA contrast, static slop scan). Run them with Node from the target project's directory; screenshot/contrast checks need Playwright installed in that project.
Hard invariants
- Audit never edits source. Retheme never starts without an approved
unslop/LANE.mdand a clean, building git state. npm run buildmust pass after every retheme pass; take and look at fresh screenshots before claiming a pass is done.- Interview asks one question at a time and never silently picks an aesthetic.
- Stack scope is React + Tailwind. Politely decline anything else (v1).
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.

