observability-dashboard-creator

Create and manage Grafana dashboards for Claude Code observability. Use when importing pre-built dashboards or creating custom visualizations.

Quality

58%

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 ./skills/observability-dashboard-creator/SKILL.md

Quality

Content

46%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 body is well-organized into operations, a dashboard catalog, features, references, and scripts, but its actionable guidance is skill-syntax rather than executable commands and its reference/script paths are largely inaccurate or missing. Fixing the broken bundle references is the highest-impact improvement.

Suggestions

Correct the References list to the actual filenames (01-claude-code-overview.json, 02-tool-performance.json, 05-session-analytics.json, etc.) and remove or create the missing references/grafana-api-guide.md.

Replace bare operation names in Usage blocks with executable invocations (e.g., "bash scripts/import-all-dashboards.sh") and only list scripts that actually exist.

Add an explicit validation step for export-dashboards (e.g., verify the backup JSON files are valid/importable) to satisfy the batch-operation feedback-loop requirement.

Dimension	Reasoning	Score
Conciseness	The body is lean without padding concepts Claude already knows, but the per-dashboard panel/use-case listings duplicate definitions already held in the reference JSON files and could be tightened.	3 / 5
Actionability	Usage blocks show bare skill-syntax ("import-all", "import-dashboard --name overview") rather than executable shell, and the real script scripts/import-all-dashboards.sh is never shown how to invoke.	3 / 5
Workflow Clarity	import-all has a clear 5-step "What Happens" sequence with a verify step, but export-dashboards is a batch operation with no validation/feedback loop, capping this dimension at 3 per the rubric.	3 / 5
Progressive Disclosure	Dedicated References and Scripts sections show good structure intent, but the listed paths do not match the actual bundle (e.g. claude-code-overview.json vs the real 01-claude-code-overview.json; grafana-api-guide.md and two of three scripts do not exist), so navigation breaks.	2 / 5
	Total	11 / 20 Passed

Description

70%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 third-person, concise, and answers both what and when with a clear trigger clause. It is strong but not comprehensive: actions are generic and the "when" omits the export/backup use cases the skill supports.

Suggestions

Add a more specific action list (e.g., "import pre-built dashboards, build custom panels, export/backup dashboards as JSON") to lift specificity.

Extend the "Use when" clause to cover export/backup triggers (e.g., "or when backing up existing dashboards").

Include natural synonyms/extensions like "Grafana", ".json dashboard files", "observability dashboards" for fuller trigger coverage.

Dimension	Reasoning	Score
Specificity	"Create and manage Grafana dashboards" names the domain and two concrete actions (create, manage), but the actions are generic and not comprehensive enough for a 4.	3 / 5
Completeness	Both "what" (create and manage Grafana dashboards for Claude Code observability) and "when" ("Use when importing pre-built dashboards or creating custom visualizations") are present, but the "when" omits export/backup scenarios the skill also covers.	4 / 5
Trigger Term Quality	Includes natural terms a user would say ("Grafana dashboards", "importing pre-built dashboards", "custom visualizations", "Claude Code observability"); a few synonyms and file extensions are missing.	4 / 5
Distinctiveness Conflict Risk	The "Claude Code observability" + "Grafana dashboards" niche is mostly distinct with minor overlap risk against generic Grafana skills.	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
referenced_paths_exist	Referenced path issues: 8 missing, 5 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skills/observability-dashboard-creator/SKILL.md
Commit: 93ed392

Reviewed: 1 day 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.