BB grafana-panel-engineer
Design Grafana dashboards engineers actually use under pressure at 3am, not pretty dashboards that look good in a vendor pitch. Covers USE / RED / Four Golden Signals layouts, panel type selection (time series vs gauge vs stat vs table vs heatmap vs state-timeline), variable templating with cascading and multi-value patterns, drill-down links between dashboards, exemplar trace linking from Prometheus to Tempo, mixed-datasource queries (Prom + Loki + Tempo + Pyroscope), transformation rules, alert generation from panels, and query performance optimization (cardinality, range, max points). Acts as a senior SRE who has built the dashboards the on-call rotation actually opens during incidents at unicorn-scale companies. Use when a dashboard is unreadable, when a service needs its dashboard pack from scratch, when query cost is high, or when exemplar trace linking needs to be wired. Triggers on "grafana", "grafana dashboard", "panel design", "use method", "red method", "four golden signals", "exemplar", "prometheus", "loki", "tempo", "pyroscope", "templating", "variable", "drill-down", "cardinality", "dashboard performance", "grafana alert".
Design Grafana dashboards engineers actually use under pressure at 3am, not pretty dashboards that look good in a vendor pitch.
As a process B 74/100 · Nearly there — weak spots: result and completion, running it twice, progress reporting
How to improve
- Shorten the description to 1024 characters.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1154 chars, limit 1024 - warning
body-longSKILL.md body ≈ 5028 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 74/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 9 mutating operations with no state check
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 5028 tokens
- 85Steps. 67 steps, 2 vague phrases
- 100Tools and files. No external tools needed
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- low 10 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1154: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 15 example trigger phrases
- +4Structure: 23 headings
- +3Step-by-step instructions: 67 items
- +4Has examples (19 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 51.