observability-monitoring-monitor-setup

You are a monitoring and observability expert specializing in implementing comprehensive monitoring solutions. Set up metrics collection, distributed tracing, log aggregation, and create insightful da

Quality

26%

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/observability-monitoring-monitor-setup/SKILL.md

Quality

Content

11%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is a hollow template with no actionable content. It lists ambitious deliverables (Grafana dashboards, SLO definitions, alert runbooks) but provides zero concrete guidance, code, commands, or examples for producing any of them. The instructions are generic platitudes that could apply to any domain, and the sole referenced resource file does not exist in the bundle.

Suggestions

Add concrete, executable examples: include at least one Prometheus config snippet, a sample Grafana dashboard JSON, and example OpenTelemetry instrumentation code for a common language.

Replace the vague 'Instructions' bullets with a specific multi-step workflow including validation checkpoints (e.g., 'verify metrics endpoint responds', 'confirm traces appear in Jaeger').

Either provide the referenced 'resources/implementation-playbook.md' with real content or inline the essential patterns and examples directly in the SKILL.md.

Remove the generic 'Use this skill when' / 'Do not use this skill when' sections and the Context paragraph that restates common knowledge—use that space for actionable content instead.

Dimension	Reasoning	Score
Conciseness	The skill contains significant padding: the 'Use this skill when' / 'Do not use this skill when' sections are generic filler, the Context section restates what Claude already knows about observability pillars, and the Output Format section lists 8 deliverables without any concrete detail—it's verbose without being informative.	2 / 5
Actionability	There is no concrete code, no specific commands, no executable examples, and no tool-specific guidance. Instructions like 'Clarify goals, constraints, and required inputs' and 'Apply relevant best practices' are entirely vague. The Output Format lists deliverable names but provides zero concrete content for any of them.	1 / 5
Workflow Clarity	There is no clear sequence of steps, no validation checkpoints, and no feedback loops. The 'Instructions' section has four bullet points that are abstract platitudes rather than a workflow. The Output Format lists deliverables but not a process to produce them.	1 / 5
Progressive Disclosure	The skill references 'resources/implementation-playbook.md' but no bundle files exist, making the reference unverifiable and potentially broken. The SKILL.md itself is thin on content yet doesn't effectively use the referenced file to offload detail—it just defers everything to a file that may not exist.	2 / 5
	Total	6 / 20 Passed

Description

41%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 truncated mid-sentence, which severely undermines its effectiveness. It uses second-person voice ('You are') instead of the required third-person, and lacks any 'Use when...' trigger guidance. While it does name several concrete monitoring capabilities, the incomplete text and missing trigger clause significantly reduce its utility for skill selection.

Suggestions

Complete the truncated description and add an explicit 'Use when...' clause with trigger phrases like 'Use when the user asks about monitoring, observability, alerting, dashboards, or setting up metrics/tracing/logging.'

Switch from second-person voice ('You are a monitoring expert') to third-person voice ('Sets up monitoring and observability solutions including metrics collection, distributed tracing, and log aggregation').

Add common synonyms and tool names as trigger terms, such as 'Prometheus', 'Grafana', 'alerting', 'dashboards', 'APM', 'logging pipelines' to improve keyword coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain (monitoring and observability) and lists several concrete actions like 'metrics collection, distributed tracing, log aggregation,' but the description appears truncated ('create insightful da') so coverage is incomplete. It also uses second-person framing ('You are') which should penalize specificity by 1, bringing it from a potential 4 down to 3.	3 / 5
Completeness	The description provides a partial 'what' (set up metrics, tracing, log aggregation) but has no explicit 'when' clause or trigger guidance. Additionally, the description is truncated mid-word, making it incomplete. The missing 'Use when...' clause caps this at 3, and the truncation brings it further down to 2.	2 / 5
Trigger Term Quality	Includes relevant keywords like 'monitoring', 'observability', 'metrics collection', 'distributed tracing', 'log aggregation', but is missing common user-facing synonyms like 'alerting', 'dashboards', 'Prometheus', 'Grafana', 'logging', 'APM', or other natural terms users would say. The truncation also cuts off potential additional trigger terms.	3 / 5
Distinctiveness Conflict Risk	The monitoring/observability domain is somewhat specific, but terms like 'metrics collection' and 'log aggregation' could overlap with skills focused on logging, infrastructure, DevOps, or data pipelines. The lack of explicit boundaries or 'Use when' guidance increases conflict risk.	3 / 5
	Total	11 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/observability-monitoring-monitor-setup/SKILL.md
Commit: 57c135b

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.