BC grafana-lens
Grafana tools for data visualization, monitoring, alerting, security, SRE investigation, and data collection pipeline management via Alloy. Use grafana_query, grafana_query_logs, grafana_query_traces, grafana_create_dashboard, grafana_update_dashboard, grafana_create_alert, grafana_share_dashboard, grafana_annotate, grafana_explore_datasources, grafana_list_metrics, grafana_search, grafana_get_dashboard, grafana_check_alerts, grafana_push_metrics, grafana_explain_metric, grafana_security_check, grafana_investigate, and alloy_pipeline. Trigger when asked about metrics, dashboards, monitoring, alerts, costs, token usage, data visualization, PromQL, Prometheus, LogQL, Loki, log queries, error logs, log search, TraceQL, Tempo, traces, distributed tracing, span search, find slow traces, debug session traces, annotations, deployments, sharing charts, investigating alert notifications, pushing custom data (calendar, git, fitness, finance) to Grafana for visualization, pushing historical data, backfilling metrics, recording past data with timestamps, modifying dashboards, adding panels, removing panels, changing dashboard settings, updating dashboard time range, explain metric, metric trend, what is this metric, how has this changed, is this metric normal, why did my bill spike, cost visibility, security monitoring, security check, security audit, am I being attacked, is my agent compromised, suspicious activity, threat detection, prompt injection detection, set up security alerts, investigate, debug, triage, root cause, what's wrong, why is X broken, anomaly detection, RED method, USE method, alert fatigue, postmortem, incident summary, collect metrics from, monitor my database, monitor my app, scrape endpoint, set up log collection, collect Docker logs, tail log files, collect Kubernetes logs, receive OTLP, set up trace collection, data collection pipeline, Alloy pipeline, pipeline status, pipeline health, node exporter, system metrics, postgres exporter, mysql exporter,
As a process C 60/100 · Has gaps — weak spots: result and completion, inputs and preconditions, execution cost
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: 80. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 2038 chars, limit 1024 - warning
body-longSKILL.md body ≈ 23354 tokens (recommended < 5000); move details to references/ - note
description-budgetdescription takes 2038 of the ~15000-char shared budget for all skills
Process rating: all ten parameters 60/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 10Execution cost. Instruction body is 23354 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 85Steps. 331 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 10 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 2038: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Structure: 33 headings
- +3Step-by-step instructions: 331 items
- +4Reference files are cited in the instructions (6 of 6)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 43.