field-agent-visualization

Professional Plotly visualization best practices for Field Agents including chart specifications, color palettes, formatting standards, and JSON structure requirements for executive-ready data visualizations

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./field-agent-skills/visualization/SKILL.md

Quality

Content

63%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill is highly actionable with copy-paste-ready Plotly JSON examples and useful verification checklists, but it suffers from severe redundancy across repeated examples and checklists, and keeps everything in a single monolithic file instead of splitting reference material into bundle files.

Suggestions

Deduplicate the repeated bar/heatmap/pie JSON examples and consolidate the three overlapping checklists (Common Issues Fix Checklist, Quality Checklist, Forbidden Patterns) into a single verification checklist to cut the body roughly in half.

Move the color palette, the hex_to_rgb/hex_to_rgba helper functions, and the complete worked examples into separate reference files under ./references/, keeping SKILL.md as a concise overview that links one level deep.

Add a single explicit numbered workflow with a validation checkpoint (e.g. 1. pick chart type → 2. apply TD palette → 3. verify against checklist → 4. validate JSON is not stringified) to lift workflow clarity toward 5.

Dimension	Reasoning	Score
Conciseness	The ~970-line body is noticeably verbose with heavy redundancy — bar/heatmap JSON appears in 'Missing Elements Fixes', 'Chart-Specific Guidelines', and 'Complete Examples', 'NO SUBPLOTS' is stated three times, and three overlapping checklists (Common Issues Fix Checklist, Quality Checklist, Forbidden Patterns) restate the same rules.	2 / 5
Actionability	Provides fully executable, copy-paste-ready Plotly JSON for every common chart type (bar, pie, heatmap, line, sankey, KPI indicator) with concrete property values and formatting, covering the common cases comprehensively.	5 / 5
Workflow Clarity	Verification checkpoints are present via 'Before generating any chart, verify' checklists, a 'Common Issues Fix Checklist', and a 'Success Criteria' section; this is not a destructive/batch workflow so the cap does not apply, though there is no explicit multi-step sequence with error-recovery feedback loops.	4 / 5
Progressive Disclosure	No bundle files exist and all content is inlined in a ~970-line monolithic SKILL.md; while it is well-sectioned with headers, content that clearly belongs in separate files (the color palette reference, the helper functions, the full examples library) is inlined rather than split into one-level-deep references.	3 / 5
	Total	14 / 20 Passed

Description

66%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description clearly conveys what the skill covers with several specific capability areas, but it omits any 'when to use' trigger guidance, which caps completeness. Trigger keywords are good but lack common synonyms.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when creating Plotly charts, dashboards, or executive-ready visualizations for Field Agent outputs.'

Include common synonyms users might say such as 'graphs', 'plots', or 'dashboards' to broaden trigger coverage.

Reframe the listed areas as concrete actions (e.g. 'Specify charts, apply the TD color palette, format axes and legends, structure valid Plotly JSON') to lift specificity toward 5.

Dimension	Reasoning	Score
Specificity	Names the domain and lists several concrete areas — 'chart specifications, color palettes, formatting standards, and JSON structure requirements' — giving specific coverage, though these are topic nouns rather than verb-based actions, keeping it just below a 5.	4 / 5
Completeness	Provides a clear 'what' (best practices including specific areas) but has no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Includes natural terms a user would say ('Plotly visualization', 'chart', 'data visualizations') with good coverage, but misses common synonyms like 'graphs', 'plots', or 'dashboards'.	4 / 5
Distinctiveness Conflict Risk	The niche — 'Plotly visualization best practices for Field Agents ... executive-ready data visualizations' — is mostly distinct with a clear target, with only minor overlap risk against a generic data-visualization skill.	4 / 5
	Total	15 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (976 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: treasure-data/td-skills
Path: field-agent-skills/visualization/SKILL.md
Commit: 1a0845f

Reviewed: 3 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.