config/agents/skills/tufte-test/SKILL.md
Review charts with a simple Tufte-style rubric. Use when judging whether a chart is clean, honest, readable, and insight-forward, or when iterating on a visualization until it passes a concise quality bar.
npx skillsauth add edmundmiller/dotfiles tufte-testInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use this skill to review a chart locally with a lightweight Tufte-style rubric.
This skill is intentionally simple:
This skill works with either:
Prefer reviewing the rendered chart when available. If only code is available, infer the likely output and call out uncertainty.
Evaluate the chart against these 7 checks:
Data-ink ratio
No 3D effects
Direct labeling
Axis readability
Muted, purposeful color
Integrated annotations
Graphical integrity
The chart passes only if all 7 core checks pass.
If one or more checks fail, the overall result is pass: false.
Use this exact structure when possible:
pass: false
checks:
data_ink_ratio: pass
no_3d_effects: pass
direct_labeling: fail
axis_readability: pass
muted_purposeful_color: pass
integrated_annotations: fail
graphical_integrity: pass
summary: "Clear and honest overall, but it still relies on a legend and lacks an integrated takeaway annotation."
failed_checks:
- direct labeling
- integrated annotations
fixes:
- "Replace the legend with direct labels on the marks or line endpoints."
- "Add a subtitle or annotation that states the main takeaway."
uncertainty: "Low"
If reviewing from code rather than an image, include an uncertainty note such as
Medium or High when the rendered result cannot be confirmed.
When suggesting fixes, prefer minimal edits:
If the chart type itself is the problem, say so directly and recommend a better alternative.
For the expanded checklist, see:
references/rubric.mdreferences/rules/01-data-ink-ratio.mdreferences/rules/02-no-3d-effects.mdreferences/rules/03-direct-labeling.mdreferences/rules/04-axis-readability.mdreferences/rules/05-muted-purposeful-color.mdreferences/rules/06-integrated-annotations.mdreferences/rules/07-graphical-integrity.mddevelopment
Read-only Linear issue access via the Linear GraphQL API.
data-ai
## <!-- Purpose: Teach agents fast day-to-day memory browse/search/read/sync workflows in pi-context-repo. --> name: searching-memory description: > Search, browse, and inspect memory quickly in pi-context-repo. Use when asked to find prior notes, inspect memory files, locate preferences, or sync recent memory updates. Trigger phrases: "search memory", "list memory files", "find in memory", "read memory file", "memory status", "sync memory". --- # Searching Memory Use this workflow for fast
development
Comprehensive guide for initializing or reorganizing agent memory into a deeply hierarchical file structure. Use when running /init, when user asks to set up memory, or when memory needs a major reorganization. Trigger phrases: "initialize memory", "set up memory", "populate memory", "build my memory", "memory init".
data-ai
Decomposes and reorganizes agent memory files into focused, single-purpose components. Use when memory has large multi-topic blocks, redundancy, or poor organization. Trigger phrases: "defrag memory", "reorganize memory", "clean up memory files", "split memory blocks".