understand-dashboard

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

Quality

60%

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

67%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 content is a well-sequenced, highly actionable procedure with real validation and fallback handling; its main weaknesses are minor verbosity in path handling and the lack of any external reference split despite exceeding 50 lines.

Suggestions

Factor the duplicated eight-path candidate list into a shell array so the search loop and the error echo share one source of truth, trimming ~15 lines.

Consider extracting the long path-resolution block (step 3) into a bundled script under scripts/ to shorten SKILL.md and improve progressive disclosure.

Add a one-line 'Prerequisites' note up front (knowledge graph must exist from /understand) so the validation in step 2 is anticipated.

Dimension	Reasoning	Score
Conciseness	The body is mostly executable bash with little concept-explanation fluff, but the eight-path candidate enumeration is duplicated in the error echo and the fast-path/fallback split adds length that could be tightened, matching 'mostly efficient but could be tightened'.	3 / 5
Actionability	Each step ships copy-paste-ready bash with explicit `${VAR:?...}` guards and concrete fallback commands, but snippets rely on shell state carried between steps and a couple of details (npx viewer download, build filter) are context-dependent, fitting 'mostly executable, minor gaps'.	4 / 5
Workflow Clarity	Steps 1-8 are clearly numbered with explicit validation checkpoints (knowledge-graph.json existence, plugin-root resolution) and a fast-path->fallback recovery branch; it lacks a true fix-and-revalidate loop, so it sits just below the 5 anchor.	4 / 5
Progressive Disclosure	The skill is self-contained with clear ## Instructions and ## Notes sections and numbered steps, and none of the bash clearly belongs in a separate file; it is well-structured for a linear procedure, though at ~155 lines with no references it does not reach the one-level-deep reference ideal of a 5.	4 / 5
	Total	15 / 20 Passed

Description

53%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 is concrete and distinctive, naming a clear purpose and niche, but it omits any 'Use when...' trigger guidance and lacks keyword variations, which caps completeness and trigger-term quality at the midpoint.

Suggestions

Append a 'Use when...' clause with concrete triggers, e.g. 'Use when the user asks to view, explore, or visualize a codebase's knowledge graph or dashboard.'

Add natural synonym terms users might say ('explore', 'browse', 'graph view') to broaden trigger coverage.

Optionally mention the prerequisite (run /understand first) in the description so the trigger context is self-contained.

Dimension	Reasoning	Score
Specificity	Names the domain ('web dashboard', 'knowledge graph') and two concrete actions ('Launch', 'visualize'), matching the anchor for 1-2 concrete actions; it does not list several actions, so it is not a 4.	3 / 5
Completeness	It clearly states what the skill does but provides no 'Use when...' clause or equivalent trigger guidance; per the judging guidelines a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	Includes relevant natural terms ('dashboard', 'visualize', 'knowledge graph') a user might say, but offers no synonyms or variations (e.g. 'explore', 'browse', 'graph'), keeping it at 'some relevant keywords, missing common variations'.	3 / 5
Distinctiveness Conflict Risk	The phrase carves a clear niche (a knowledge-graph visualization dashboard) with low conflict risk, but the absence of explicit trigger phrasing leaves minor overlap with generic dashboard skills, so it sits at 'mostly distinct' rather than a 5.	4 / 5
	Total	13 / 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
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: ba450c4

Reviewed: ~16 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.