beast-ui
Skill0 starsChanged 10 days agoMITView on GitHub
Improve an existing UI or generated document view through an ordered design and performance check. Use for a complete quality pass before handoff.
In this repository24 other files it gives its agents.
- AGENTS.mdAGENTS.md
- rules/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- babysit-prSkill
- cleanupSkill
- councilSkill
- doc-viewSkill
- featuremapSkill
- file-prSkill
- frontend-designSkill
- full-sendSkill
- full-stopSkill
- impeccableSkill
- leaving-pr-commentsSkill
- modernizeSkill
- no-commentsSkill
- patrolSkill
- sol-loopSkill
- statechartSkill
- technical-writingSkill
- tldrSkill
- untangleSkill
- verify-prSkill
- whySkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
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 8
Run Impeccable's audit, layout, typeset, polish and optimize playbooks in that order.
- Distinctive: line 12
Read the target and its project rules.
- Distinctive: line 22
Polish: Check alignment, interaction states, content and small inconsistencies.
- Distinctive: line 26
Use Impeccable's required context and craft guidance within the authorized scope.
- Distinctive: line 27
Do not turn a document view into product discovery, a redesign or maintenance work.
- Distinctive: line 29
Keep the running findings in the conversation unless a report was requested.
- Distinctive: line 31
Verify the final result with Playwright or an equivalent real browser.
≈ “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
Beast UI
Run Impeccable's audit, layout, typeset, polish and optimize playbooks in that order. Each stage sees the previous stage's result. A stage may find nothing that needs changing.
Read the target and its project rules. Preserve the chosen style, factual copy
and intended behavior. Resolve the installed Impeccable
skill and its base directory, then load the relevant playbook from its
reference/ folder for each stage. Use the host's actual skill mechanism or
read the files directly; do not invent a Skill tool or plugin command. Run every
engine command in these playbooks through Impeccable's bundled launcher.
- Audit. Find accessibility, responsive layout and rendering defects.
- Layout. Fix structure, spacing, hierarchy and any blocking layout defects.
- Typeset. Improve heading scale, line length, fonts and readability.
- Polish. Check alignment, interaction states, content and small inconsistencies.
- Optimize. Measure loading, asset weight or rendering costs. Fix demonstrated problems without changing the approved design or adding speculative machinery.
Use Impeccable's required context and craft guidance within the authorized scope. Do not turn a document view into product discovery, a redesign or maintenance work. Missing project context alone does not authorize creating new project rules. Keep the running findings in the conversation unless a report was requested.
Verify the final result with Playwright or an equivalent real browser. Inspect screenshots at desktop and narrow widths; exercise controls and keyboard access. Fix material defects and inspect the corrected result. A static source check or saved screenshot without inspection does not prove the UI works.
Hand back the changed result and any remaining limitation briefly. Do not claim a complete pass when a required playbook, engine or browser check did not run. This skill does not commit, publish or merge unless the task authorizes it.
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.

