CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

observability-alert-manager

Configure Grafana alerts for Claude Code anomalies and thresholds. Use when setting up monitoring alerts for sessions, errors, context usage, or subagents.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/observability-alert-manager/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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-sectioned, actionable reference of LogQL alert templates with executable examples, weakened by duplicated example configurations, absent validation/test loops around alert creation and batch import, and a Scripts section pointing at four script files that are missing from the bundle.

Suggestions

Add the four cited script files to a `scripts/` directory (or remove the Scripts section), and have the example invocations call them by path (e.g. `scripts/create-alert.sh --name ...`) so the references resolve.

Add a validation loop to the alert lifecycle: create an alert, run `test-alert` to confirm it fires on simulated conditions, and fix/adjust the query before considering it done — this also covers the batch `import-alert-templates.sh` flow.

Cut the three 'Example Alert Configurations' down to one (the syntax is identical across them; only the flags differ) since the LogQL queries are already given verbatim in the template section.

DimensionReasoningScore

Conciseness

The body is mostly lean LogQL templates with no concept explanations Claude already knows, but the three 'Example Alert Configurations' restate queries verbatim from the template section and could be trimmed to one, matching 'efficient; minor instances of over-explanation that could be trimmed'. Not 3 because the bulk of the content is genuinely non-redundant reference material.

4 / 5

Actionability

Provides copy-paste-ready LogQL queries, bash invocations, and a complete curl API example covering common cases. Not 5 because the `create-alert` examples don't use the actual script path (`scripts/create-alert.sh`) and the curl example hardcodes `admin:admin`, leaving minor gaps to execute literally.

4 / 5

Workflow Clarity

The Grafana UI setup lists a rough 4-step sequence but has no validation checkpoints, and although a `test-alert` operation exists there is no create-then-test feedback loop; `import-alert-templates.sh` is a batch import with no verification step, which caps this at 3 per the batch-operations guideline.

3 / 5

Progressive Disclosure

The Scripts section cites `scripts/create-alert.sh`, `scripts/list-alerts.sh`, `scripts/test-alerts.sh`, and `scripts/import-alert-templates.sh`, but no `scripts/` directory exists in the bundle — these are dangling references that break navigation. In-doc section structure is good, which keeps it above anchor 1, but broken referenced paths match 'minimal structure; references buried/nonexistent' better than the organized-structure anchors 3-4.

2 / 5

Total

13

/

20

Passed

Description

78%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.

A strong description with an explicit 'Use when...' clause and concrete trigger terms, written in third-person imperative style. Its main weakness is a thin 'what' — it states one action (configure alerts) while the body supports create/list/test/delete operations.

DimensionReasoningScore

Specificity

The description names a specific domain ("Configure Grafana alerts for Claude Code") with one concrete action, but "anomalies and thresholds" is abstract and the list/create/test/delete operations the skill actually supports are not mentioned, matching the 'domain and 1-2 concrete actions, but not comprehensive' anchor.

3 / 5

Completeness

It explicitly answers both what ("Configure Grafana alerts for Claude Code anomalies and thresholds") and when ("Use when setting up monitoring alerts for sessions, errors, context usage, or subagents") with concrete trigger phrases, mirroring the anchor-5 example structure. Not 4 because the when-clause is more explicit and specific than the anchor-4 example.

5 / 5

Trigger Term Quality

Natural phrases like "monitoring alerts", "sessions, errors, context usage, or subagents" would be said by a user needing this skill, but common variations such as "alerting", "notifications", or "Loki" are missing, matching 'good keyword coverage; a few natural terms missing'.

4 / 5

Distinctiveness Conflict Risk

Grafana alerting for Claude Code telemetry is a clear niche with distinct triggers, but the generic "monitoring" framing has minor overlap risk with closely related observability/dashboard skills, matching 'mostly distinct; minor overlap risk'.

4 / 5

Total

16

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 4 missing

Warning

Total

15

/

16

Passed

Repository

fernandezbaptiste/Skrillz

Path

skills/observability-alert-manager/SKILL.md

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.