observability

Agent observability, evals, feedback, and experiments. Use when adding observability dashboards, configuring trace capture, setting up evals, creating A/B experiments, or collecting user feedback on agent responses.

Quality

81%

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

Quality

Content

71%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 dense, highly actionable reference with excellent executable examples and clear pillar-based structure. Its weaknesses are verbosity in the tracking-bridge prose and a monolithic layout with no bundled reference files to offload detail.

Suggestions

Move the long 'Tracking Bridge' constraint list and the API endpoint table into dedicated reference files (e.g. references/tracking-bridge.md, references/api.md) and link to them one level deep to improve progressive disclosure.

Tighten the prose in the constraint bullets — several explain the same PostHog $ai_* quirk across multiple sentences and could be condensed to one line each.

Add brief validation/guardrail callouts (e.g. confirm captureToolResults is off before relying on 'withheld' markers) at the points where destructive or batch observability actions are configured.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and focused on non-obvious framework-specific gotchas rather than general concepts, but the long 'Tracking Bridge' constraint list and prose-heavy sections have padding that could be tightened.	3 / 5
Actionability	Provides fully executable, copy-paste-ready code (config blocks, defineEval, insertExperiment, dashboard route), a concrete CLI command, and a complete API endpoint table covering the common cases.	5 / 5
Workflow Clarity	Clear structure via the Rule + Five Pillars, with sequenced flows for the eval CI gate and experiment lifecycle (draft→running→results); not a destructive/batch workflow so the validation cap does not apply.	4 / 5
Progressive Disclosure	A single ~390-line monolithic file with good headers but no bundled reference files; large blocks like the tracking-bridge constraint list and API table are inlined rather than split into separate one-level-deep references.	3 / 5
	Total	15 / 20 Passed

Description

92%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 is third-person, concrete, and explicitly pairs a 'what' with an explicit 'Use when...' trigger clause covering five distinct actions. Strong across all dimensions, with only minor gaps in synonym coverage for trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('adding observability dashboards, configuring trace capture, setting up evals, creating A/B experiments, or collecting user feedback') with comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what ('Agent observability, evals, feedback, and experiments') and when ('Use when adding... configuring... setting up... creating... or collecting...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural keyword coverage ('observability dashboards', 'trace capture', 'evals', 'A/B experiments', 'user feedback') but missing common synonyms like 'monitoring', 'analytics', or 'logging'.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (agent observability/evals) with distinct triggers unlikely to fire for unrelated skills.	5 / 5
	Total	19 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: BuilderIO/agent-native
Path: .agents/skills/observability/SKILL.md
Commit: a06e0ac

Reviewed: 13 hours 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.