Personal Dashboard Style
Skill1 starsChanged 4 months agoMITView on GitHub
Apply a consistent dark-theme HTML report/dashboard convention (background, accent colors, save path, open command) to any generated standalone report instead of re-deriving a visual style from scratch each time. Use whenever generating a self-contained HTML report, dashboard, or comparison view for personal review.
In this repository25 other files it gives its agents.
- templates/AGENTS.mdAGENTS.md
- braindump-autoSkill
- braindumpSkill
- Capability Claim GroundingSkill
- Derived Figure AuditSkill
- design-review-loopSkill
- Dictation Garble CatcherSkill
- Discord Todo OpsSkill
- Full Account Security AuditSkill
- Large Task Session SplitSkill
- Pre-Push Secret ScanSkill
- Project Design DocSkill
- Public Repo Leak RetractionSkill
- repo-hygieneSkill
- Repo Index Drift CheckSkill
- Safe Section DeletionSkill
- Session HandoffSkill
- Skill Overlap AuditSkill
- superbraindumpSkill
- ui-change-visual-verifySkill
- Verify, Don't TrustSkill
- Windows Process Restart (Safe)Skill
- Windows Shell Tool SelectionSkill
- Worktree Task-Pack VerificationSkill
- Zombie Process SweepSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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 23
Before finalizing a report, confirm: same three colors, same semantic role for each, saved to the right path with a sortable filename, …
≈ “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
Personal Dashboard Style
Visual/data-heavy output (reports, dashboards, comparisons, anything with 10+ rows of data) gets a self-contained HTML file rather than a wall of text, and it should look like the same system every time, not a new visual style invented per request.
The convention
- Dark theme, fixed palette: navy background (
#0a0d18), teal accent (#22d3ee), purple accent (#7c3aed). Use these consistently for the same semantic role every time (e.g. teal for primary metrics/links, purple for secondary/highlight elements) rather than swapping which color means what per report. - Save location: a dedicated
ui/folder, filename pattern<date>-<topic>.htmlso reports are chronologically sortable and self-describing without opening them. - Open command: launch it directly (e.g.
Start-Process "<path>"on Windows) rather than just stating the path and leaving it to the user to open manually. - Always pair with a short text summary (2-3 lines) alongside the HTML. The file is the detailed view; the chat response is the at-a-glance takeaway. Never let the HTML be the only thing delivered.
When to reach for this vs. plain text
Use the styled HTML report when: there's a real dataset (10+ rows), a comparison across multiple items, or a dashboard-shaped request. Don't reach for it for a simple one-off answer that reads fine as prose. The convention is for when structure and visual scanning genuinely help, not a default for every response.
Consistency check before shipping
Before finalizing a report, confirm: same three colors, same semantic role for each, saved to the right path with a sortable filename, opened automatically, and a short accompanying summary written, not just the file dropped with no context.
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.

