understand-dashboard

Launch the interactive web dashboard to visualize a codebase's knowledge graph

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./understand-anything-plugin/skills/understand-dashboard/SKILL.md

Quality

Content

77%

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

The body is a highly actionable, well-sequenced launch workflow with executable bash, explicit validation checkpoints, and a fast-path-to-fallback feedback loop. Its main weaknesses are verbosity from repeated path listings and a lack of progressive disclosure, since all logic lives inline in one file with no referenced bundle materials.

Suggestions

Reduce redundancy in step 3 by defining the candidate paths once and reusing them for both the probe loop and the error message rather than listing them three times.

Move the lengthy plugin-root resolution logic into a script under scripts/ and reference it from SKILL.md, improving both conciseness and progressive disclosure.

Consider extracting the fallback build/dev-server steps into a referenced reference file so the main body can foreground the common fast-path flow.

Dimension	Reasoning	Score
Conciseness	The body is operational bash without concept explanations, but step 3 repeats the same candidate paths three times (prose list, the bash loop, and the error echo) and could be tightened, fitting 'mostly efficient but could be tightened'.	2 / 3
Actionability	Every step ships fully executable, copy-paste-ready bash with variable guards (e.g., ': "${PLUGIN_ROOT:?...}"', the candidate-path loop, 'npx --yes "$VIEWER_URL"'), matching the 'fully executable code/commands' anchor.	3 / 3
Workflow Clarity	A clear 8-step sequence with explicit validation checkpoints (project dir existence, knowledge-graph.json presence, plugin-root resolution) and a feedback loop (fast path -> fallback to build/dev server), matching the 'clear sequence with explicit validation and feedback loops' anchor.	3 / 3
Progressive Disclosure	Sections are well-organized (numbered steps, Notes) but the skill is a single ~155-line monolithic file with no bundle files or one-level-deep references, and the verbose path-resolution logic is inline content that could be split into a script, fitting 'content that should be separate is inline'.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 is concrete and specific about what the skill does, naming a clear domain (codebase knowledge-graph visualization via a web dashboard), but it omits any explicit 'when to use' trigger guidance and offers only a narrow action list. It is distinguishable but lacks the trigger-term coverage that would make it score higher.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should invoke this skill (e.g., when the user asks to view or explore a codebase's knowledge graph, code map, or dependencies).

Broaden trigger terms to include natural variations users might say, such as 'explore codebase', 'code map', 'dependency graph', or 'visualize project structure'.

Consider mentioning a second concrete capability (e.g., navigating or filtering the graph) to lift specificity from a narrow two-action list toward a comprehensive action set.

Dimension	Reasoning	Score
Specificity	Names the domain and two concrete actions ("Launch the interactive web dashboard", "visualize a codebase's knowledge graph") but the action list is narrow and not comprehensive, matching the 'names domain and some actions' anchor rather than the multi-action score-3 example.	2 / 3
Completeness	Clearly states what the skill does but provides no 'Use when...' clause or equivalent explicit trigger guidance, so per the judging guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	Includes relevant natural keywords ("dashboard", "visualize", "knowledge graph") a user might say, but misses common variations ("explore codebase", "code map", "dependencies"), fitting 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	The codebase knowledge-graph niche is somewhat specific, but generic verbs ('Launch', 'visualize') and the absence of explicit distinct triggers mean it could overlap with other code-visualization or dashboard skills.	2 / 3
	Total	8 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Egonex-AI/Understand-Anything
Path: understand-anything-plugin/skills/understand-dashboard/SKILL.md
Commit: 6ae7187

Reviewed: 4 days 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.