CtrlK
BlogDocsLog inGet started
Tessl Logo

observability

observability stuff

44

Quality

46%

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 ./observability/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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 content is a concise, well-organized overview that gives concrete, actionable guidance for logs, metrics, traces, and dashboards. Its weak spots are the vague Alerts section and the absence of any validation checkpoint, which cap actionability and workflow clarity.

Suggestions

Make the Alerts section actionable: name concrete conditions and thresholds (e.g., error rate > 1% for 5m, p99 latency > 500ms) and a routing default, replacing 'when stuff is bad'.

Add a verification checkpoint such as confirming all three signals are exposed (e.g., '/metrics returns 200, traces appear in the backend, logs are structured JSON') before declaring instrumentation done.

Consider a short code/config snippet for the metrics endpoint to lift actionability from concrete-but-incomplete to copy-paste ready.

DimensionReasoningScore

Conciseness

The body is lean with structured lists and no padding of concepts Claude already knows, matching 'Efficient; minor instances of over-explanation that could be trimmed'; it stops short of a 5 because the Alerts section is loose rather than maximally tight.

4 / 5

Actionability

Concrete guidance exists (JSON log levels, RED method, /metrics in Prometheus format, OTel spans, specific dashboard panels) but it is incomplete — the Alerts section ('set up some alerts that page the team when stuff is bad. Don't go overboard') is vague with no thresholds or concrete tooling, matching 'Some concrete guidance but incomplete; missing key details'.

3 / 5

Workflow Clarity

The 'Three signals to instrument' section gives a numbered checklist but there is no explicit validation/verification checkpoint and the remaining sections are not a sequenced process, matching 'Steps listed but validation gaps'; it does not reach 4 because no checkpoints are present.

3 / 5

Progressive Disclosure

The skill is under 50 lines, has no external bundle files, and is organized into clearly headed sections (Three signals, Common gotchas, Dashboards, Alerts), satisfying the simple-skill exception where well-organized sections score 5.

5 / 5

Total

15

/

20

Passed

Description

28%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 'observability stuff' is too vague to be effective: it names the domain but provides no concrete capabilities, no natural trigger terms, and no usage guidance. It would be a strong description if expanded to list concrete signals and trigger phrases.

Suggestions

Replace 'observability stuff' with concrete capabilities, e.g. 'Add structured logs, RED metrics, and OpenTelemetry traces to a service and build dashboards and alerts.'

Add a trigger clause such as 'Use when a user asks about adding logging, metrics, traces, dashboards, or alerts to a service.'

Include natural synonyms users say (logging, telemetry, Prometheus, Grafana, SLOs) to improve trigger matching and distinctiveness.

DimensionReasoningScore

Specificity

The phrase 'observability stuff' names the domain but the word 'stuff' is generic with no concrete actions, matching the anchor 'Names the domain but actions are minimal or generic'; it is above 1 (which requires no domain naming) but well below 3 (which requires 1-2 concrete actions).

2 / 5

Completeness

It offers only a vague 'what' ('observability stuff') and no 'when' / trigger clause, matching 'Has a vague what and no when'; the missing 'Use when...' guidance also caps completeness at 3, and this falls below that.

2 / 5

Trigger Term Quality

Only 'observability' appears as a keyword with no natural user phrasings like 'logging', 'metrics', 'dashboards', or 'traces' in the description, matching 'One or two generic keywords; missing the natural phrases users say'.

2 / 5

Distinctiveness Conflict Risk

'Observability' names a specific niche (somewhat distinct from adjacent skills) but the bare 'stuff' adds no distinguishing trigger, matching 'Somewhat specific but could still overlap with similar skills'; it is not as generic as the anchor-2 example 'Helps with document files'.

3 / 5

Total

9

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

description_field

'description' is very short (19 chars), consider making it more detailed

Warning

Total

15

/

16

Passed

Repository
fernandezbaptiste/skill-review-sandbox
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.