understand-dashboard
Launch the interactive web dashboard to visualize a codebase's knowledge graph
44
45%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./understand-anything-plugin/skills/understand-dashboard/SKILL.mdQuality
Discovery
40%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 identifies a specific and distinctive capability—launching a web dashboard for codebase knowledge graph visualization—but it lacks a 'Use when...' clause, which is critical for Claude to know when to select this skill. The description is also thin on concrete actions and natural trigger terms users might use.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to visualize, explore, or browse the codebase knowledge graph, or requests a dashboard or graph view.'
Include additional natural trigger terms users might say, such as 'graph view', 'code map', 'dependency visualization', 'explore codebase structure'.
List more specific capabilities of the dashboard beyond just 'visualize', e.g., 'navigate nodes and edges, filter by module, inspect relationships between code entities'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names a specific action ('launch the interactive web dashboard') and a domain ('codebase's knowledge graph'), but only describes one action rather than listing multiple concrete capabilities of the dashboard. | 2 / 3 |
Completeness | Describes what the skill does (launches a dashboard to visualize a knowledge graph) but has no 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill, which per the rubric caps completeness at 2, and the 'what' is also thin enough to warrant a 1. | 1 / 3 |
Trigger Term Quality | Contains some relevant keywords like 'dashboard', 'visualize', 'knowledge graph', and 'codebase', but misses common user variations such as 'graph view', 'code map', 'dependency graph', 'explore', or 'browse'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'interactive web dashboard', 'knowledge graph', and 'codebase' is quite distinctive and unlikely to conflict with other skills. This is a clear niche. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides highly actionable, executable guidance for launching a dashboard but suffers significantly from verbosity — particularly the exhaustive path resolution logic in step 3 which dominates the file. The workflow is clearly sequenced but lacks validation after critical steps like dependency installation and building. The content would benefit greatly from extracting the path resolution into a helper script and adding error handling for build/install failures.
Suggestions
Extract the path resolution bash script (step 3) into a separate helper script file (e.g., `resolve-plugin-root.sh`) and reference it from the skill, dramatically reducing inline verbosity.
Add validation checkpoints after step 4 (dependency install and build) — e.g., check exit codes and provide error recovery guidance if pnpm install or build fails.
Condense the error message in the path resolution script — Claude can generate helpful error messages without being given the exact template for every checked path.
Add a brief troubleshooting section or reference for common failures (port conflicts, missing pnpm, build errors) rather than scattering notes at the bottom.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose, especially the path resolution logic in step 3 which lists 8+ candidate paths with a massive bash script. Much of this could be condensed. The error messages and fallback paths are exhaustively enumerated when Claude could handle this more concisely. The skill is well over 100 lines for what is essentially: check for knowledge graph, find dashboard, install deps, start server, report URL. | 1 / 3 |
Actionability | The skill provides fully executable bash commands for every step — path resolution, dependency installation, building, and starting the server. The commands are copy-paste ready with clear variable substitution patterns and concrete environment variable usage. | 3 / 3 |
Workflow Clarity | The steps are clearly sequenced (1-7) and include a validation check for the knowledge graph existence in step 2. However, there are no validation checkpoints after dependency installation or build steps (step 4), which could fail silently. There's no feedback loop for handling build failures or port conflicts beyond a brief note. | 2 / 3 |
Progressive Disclosure | The content is monolithic — all detail is inline in a single file with no references to supporting documentation. The massive path resolution bash script in step 3 could be extracted to a separate script or reference file. However, the section headers provide reasonable organization within the single file. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- Lum1104/Understand-Anything
- Commit
26edf61
- Reviewed
Table of Contents
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.