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

79%

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 ./benchmarks/runs/oma/.agents/skills/oma-observability/SKILL.md

Quality

Content

67%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 well-structured router skill with clear workflow sequencing and concrete routing/invocation guidance. Its main weaknesses are duplicated out-of-scope content and reference paths that point to bundle files not present in the package.

Suggestions

Collapse the 'When NOT to use' bullet list and the 'Out of Scope' table into a single section to remove the duplicated domain list and reduce token cost.

Provide the referenced resources/*.md bundle files (or note their absence), since the Routes table, How to Execute, and References all depend on paths that do not exist in the package.

Inline the key VERIFY/validation checks (e.g. the checklist.md §1 items) so the workflow's validation checkpoint is executable without loading an external file.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining basics Claude knows, but the 'When NOT to use' bullet list (lines 28-36) and the 'Out of Scope' table (lines 141-155) duplicate the same domains, and the large ASCII architecture diagram adds length that could be tightened.	3 / 5
Actionability	Concrete routing tables map each intent to a specific target file, invocation examples give exact `/oma-observability` commands, and guardrails cite specific thresholds (e.g. '< 100 ms drift'), though most executable detail is delegated to reference files.	4 / 5
Workflow Clarity	A clear Entry→Scenes→Transitions→Failure/Recovery→Exit sequence exists with a dedicated VERIFY scene and 'Failure and recovery' feedback loop, but validation is largely pointed at checklist.md rather than spelled inline, leaving minor checkpoint gaps.	4 / 5
Progressive Disclosure	The SKILL.md is a well-organized overview with a categorized References section and one-level-deep signaled paths, but no references/ bundle directory is actually present, so the referenced paths are dangling and navigation cannot complete.	4 / 5
	Total	15 / 20 Passed

Description

91%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, specific description that clearly states both capability and trigger conditions with rich natural-language keywords. Minor overlap risk with single-vendor observability skills is the only weakness.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('Routes to vendor-specific skills via category taxonomy; owns transport tuning, meta-observability, incident forensics'), with only minor abstraction in the action verbs keeping it below a 5.	4 / 5
Completeness	It explicitly answers both 'what' (intent-based router that routes/tunes/owns specific functions) and 'when' (a concrete 'Use for ...' trigger list), matching the top anchor.	5 / 5
Trigger Term Quality	The 'Use for observability, traceability, telemetry, APM, RUM, metrics, logs, traces, profiles, SLO, incident forensics, tracing architecture work' clause gives comprehensive natural-term coverage including synonyms and acronyms users actually say.	5 / 5
Distinctiveness Conflict Risk	It carves a clear routing/meta-observability niche with distinct triggers, but the broad observability vocabulary creates minor overlap risk with vendor-specific observability skills.	4 / 5
	Total	18 / 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: benchmarks/runs/oma/.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.