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

82%

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

65%

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

A thorough, highly actionable reference for agent observability with strong executable examples and precise file paths. Its weakness is token efficiency and structure: it is a dense monolith whose exhaustive API/tracking detail belongs in split-out reference files, and its risky workflows lack explicit validation checkpoints.

Suggestions

Move the full API endpoint table and the $ai_generation / $ai_sentiment tracking-event property schemas into a separate references/ file, leaving only a concise overview and a clearly signaled link in SKILL.md.

Add explicit validation checkpoints to the experiment and eval-gate workflows (e.g. 'verify status is running before reading assignment config', 'confirm the eval exited non-zero on failure before blocking the deploy').

Trim the inferred-sentiment deployment override and env-var details into a short summary or a referenced doc to reduce low-value inline token cost.

Dimension	Reasoning	Score
Conciseness	The body is dense and reference-grade (full API tables, exhaustive tracking-event property lists, deployment env-var overrides) — mostly efficient but several sections expand low-value detail (e.g. the long $ai_generation property enumeration and inferred-sentiment deployment knobs) that could be tightened or offloaded to a referenced doc.	2 / 3
Actionability	Provides complete, copy-paste-ready code blocks with real imports (insertExperiment, defineEval, putSetting) and concrete commands ('agent-native eval [pattern] [--threshold N]'), plus exact file paths — fully executable rather than pseudocode.	3 / 3
Workflow Clarity	Sequences for experiments and evals are listed, but the destructive/batch-adjacent operations (experiment status transitions, CI-gate eval runs) lack explicit validation checkpoints or error-recovery loops, which the rubric notes should cap this dimension at 2.	2 / 3
Progressive Disclosure	Well-sectioned overview, but it is a monolithic ~290-line document with no bundle files present (references/scripts/assets absent) and prose pointers like 'See the Evals doc' that point to external docs rather than real one-level-deep reference files; content that should be split out (full API table, tracking event schema) is inline.	2 / 3
	Total	9 / 12 Passed

Description

100%

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 a strong activation driver: third-person voice, concrete actions, natural trigger terms, and an explicit 'Use when' clause covering both what and when. It is concise yet specific and unlikely to fire for the wrong skill.

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' — matching the score-3 anchor that asks for several specific concrete actions.	3 / 3
Completeness	Explicitly answers both what ('Agent observability, evals, feedback, and experiments') and when ('Use when adding observability dashboards, configuring trace capture, setting up evals, creating A/B experiments, or collecting user feedback'), satisfying the score-3 anchor requiring explicit triggers for both halves.	3 / 3
Trigger Term Quality	Uses natural phrasing a user would actually say — 'observability dashboards', 'trace capture', 'setting up evals', 'A/B experiments', 'user feedback' — with good coverage of common variations rather than jargon.	3 / 3
Distinctiveness Conflict Risk	The agent-observability/evals/experiments niche has distinct triggers unlikely to collide with unrelated skills; the named scenarios are specific enough to disambiguate from generic monitoring or analytics skills.	3 / 3
	Total	12 / 12 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: c1ee18b

Reviewed: 4 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.