oma-observability

Intent-based observability + traceability router across layers, boundaries, and signals. Routes to vendor-specific skills via category taxonomy; owns transport tuning, meta-observability, incident forensics. Use for observability, traceability, telemetry, APM, RUM, metrics, logs, traces, profiles, SLO, incident forensics, tracing architecture work.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/oma-observability/SKILL.md

Quality

Content

56%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.

A thoughtfully structured router skill with clear workflow sequencing, routing tables, and guardrails, but the body repeats intent classification across sections, inlines time-sensitive facts, and—most importantly—references ~30 resource files that are absent from the bundle, breaking progressive disclosure.

Suggestions

Materialize the referenced resource files (resources/, transport/, layers/, boundaries/, signals/) or remove the dangling references so progressive disclosure resolves to real content.

De-duplicate intent classification: state the setup/migrate/investigate/alert/trace/tune/route taxonomy once and reference it from Entry, Scenes, and the Routes table instead of restating it.

Consolidate time-sensitive facts ('as of 2026-Q2', CNCF 2025-10, graduation dates) into the Versioning & Deprecation section rather than scattering them through guardrails and prose.

Dimension	Reasoning	Score
Conciseness	Mostly efficient routing metadata, but intent classification is restated across Entry, Scenes, Canonical workflow path, and the Routes table, and time-sensitive facts ('as of 2026-Q2', 'CNCF 2025-10', 'OpenFeature Graduated 2024-11') sit inline rather than isolated in the deprecation section.	3 / 5
Actionability	The Routes table maps each intent to concrete primary/fallback resource files and invocation examples are copy-paste ready, but the actual executable detail is deferred to resource files that are not present in the bundle, leaving the body mostly routing metadata.	3 / 5
Workflow Clarity	Clear sequenced flow (Entry → Scenes PREPARE/ACQUIRE/REASON/ACT/VERIFY/FINALIZE → Exit) with a VERIFY checkpoint, a failure-and-recovery section, and a pre-submit checklist reference; checkpoints are somewhat high-level and delegate to external files.	4 / 5
Progressive Disclosure	The body is well-organized as a hub with clearly signaled one-level-deep references and a full References list, but the referenced bundle (resources/, transport/, layers/, boundaries/, signals/) does not exist, so navigation leads to dead ends and the disclosure is not realized.	3 / 5
	Total	13 / 20 Passed

Description

83%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 well-constructed description that uses third-person voice, clearly states both purpose and trigger conditions, and enumerates a broad set of natural observability keywords. Minor gaps in synonym coverage and slightly abstract action framing keep it just short of perfect.

Dimension	Reasoning	Score
Specificity	Lists several concrete routing/ownership actions ('Routes to vendor-specific skills via category taxonomy', 'owns transport tuning, meta-observability, incident forensics') rather than vague language, though the actions are router-framed and somewhat abstract.	4 / 5
Completeness	Explicitly answers both what ('Intent-based observability + traceability router... owns transport tuning, meta-observability, incident forensics') and when ('Use for observability, traceability, telemetry...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural keyword coverage ('observability, traceability, telemetry, APM, RUM, metrics, logs, traces, profiles, SLO, incident forensics'), but common synonyms like 'monitoring' and 'OpenTelemetry/OTel' are absent.	4 / 5
Distinctiveness Conflict Risk	The category-taxonomy router framing across layers/boundaries/signals carves a clear niche with minimal conflict risk, though it overlaps slightly with the vendor-specific observability skills it routes to.	4 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: first-fluke/oh-my-agent
Path: .agents/skills/oma-observability/SKILL.md
Commit: 032c988

Reviewed: 2 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.