dashboard-builder

Build monitoring dashboards that answer real operator questions for Grafana, SigNoz, and similar platforms. Use when turning metrics into a working dashboard instead of a vanity board.

Quality

70%

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/dashboard-builder/SKILL.md

The canonical home for this skill is tdg-personal/dashboard-builder

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 body is a well-structured, concise instruction-only skill with a clear workflow and end-of-process checklist. Its main gaps are the absence of concrete executable artifacts (query/JSON examples or templates) and no explicit validate-and-retry feedback loop.

Suggestions

Add a small executable example for one platform, such as a minimal Grafana panel JSON snippet or a sample PromQL/LogQL query, to lift actionability toward 4-5.

Insert an explicit validation feedback loop, e.g. 'Validate dashboard JSON (grafana-cli dashboards validate or jq .); if errors, fix and re-validate before shipping', to push workflow_clarity to 5.

Consider moving the per-platform Example Panel Sets into a references/ file (e.g. panel-sets.md) referenced one level deep, so SKILL.md stays a lean overview and progressive_disclosure can reach 5.

Dimension	Reasoning	Score
Conciseness	The body is lean, uses tight bullet lists, and never explains concepts Claude already knows (no 'what is Grafana' padding), but the intro philosophy ('The goal is not show every metric') is slightly restated by the Guardrails ('do not include every available metric just because it exists'), keeping it at 'efficient; minor instances that could be trimmed' rather than the perfectly lean level 5.	4 / 5
Actionability	It gives a useful framework (operating questions, section structure, per-platform panel sets like 'under-replicated partitions' and 'p50/p95/p99 latency') but no executable code, queries, JSON templates, or commands, fitting 'some concrete guidance but incomplete; missing key details' rather than the mostly-executable level 4.	3 / 5
Workflow Clarity	A clear four-step sequence (define questions, study schema, build minimum board, cut vanity panels) is present and a Quality Checklist acts as a validation checkpoint, but there is no explicit error-recovery feedback loop (e.g., validate JSON -> fix -> retry), matching 'clear sequence with most checkpoints; minor validation gaps' rather than the feedback-loop level 5.	4 / 5
Progressive Disclosure	The single file is well-organized into clearly signaled sections (When to Use, Guardrails, Workflow, Example Panel Sets, Quality Checklist) with no nested references and no bundle files present, but at ~100 lines with all content inline it is slightly more than a minimal overview, fitting 'good structure; minor organization gaps' rather than the well-split level 5.	4 / 5
	Total	15 / 20 Passed

Description

73%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 well-constructed in third person with explicit what/when structure, named platforms, and natural trigger terms. Its main weakness is a single core action and a 'when' clause that is conceptual rather than packed with concrete user trigger phrases.

Suggestions

Expand the action list beyond 'Build' to name concrete sub-actions (e.g., 'Define operator questions, lay out sections, write panel queries, set thresholds') to lift specificity toward 5.

Add concrete user trigger phrases to the 'when' clause (e.g., 'Use when the user asks to build a Grafana/SigNoz dashboard or turn a metrics list into an operational board') to push completeness to 5.

Include a couple more natural synonyms/extensions (e.g., 'observability', 'panels', 'Datadog') to round out trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('monitoring dashboards') and concrete platforms (Grafana, SigNoz) with one core action ('Build monitoring dashboards that answer real operator questions'), but does not enumerate several distinct actions, matching the '1-2 concrete actions, not comprehensive' anchor rather than the 'several specific actions' level 4.	3 / 5
Completeness	Explicitly states both what ('Build monitoring dashboards that answer real operator questions for Grafana, SigNoz, and similar platforms') and when ('Use when turning metrics into a working dashboard instead of a vanity board'), but the 'when' clause is conceptual rather than listing concrete user trigger phrases, matching level 4 rather than the concrete-trigger-phrase level 5.	4 / 5
Trigger Term Quality	Includes natural terms users say ('monitoring dashboards', 'Grafana', 'SigNoz', 'metrics', 'dashboard') with concrete platform names, but misses common synonyms/extensions like 'observability', 'panels', or 'Datadog', fitting 'good keyword coverage; a few natural terms missing' rather than the comprehensive level 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (building operator-focused monitoring dashboards) with distinct platform-named triggers (Grafana, SigNoz) and minimal realistic conflict with other skills, matching the 'clear niche with distinct triggers; minimal conflict risk' anchor.	5 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: affaan-m/ECC
Path: skills/dashboard-builder/SKILL.md
Commit: 06c5e11

Reviewed: 3 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.