exploring-llm-clusters

Investigate AI observability clusters — understand usage patterns in AI/LLM traffic, compare cluster behavior, compute cost/latency metrics, and drill into individual traces within clusters.

Quality

83%

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

Quality

Content

100%

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 lean, executable playbook: complete SQL templates per clustering level, a clearly sequenced workflow, and well-signaled offloading of bulky output to a script. It assumes Claude's competence and avoids concept padding throughout.

Dimension	Reasoning	Score
Conciseness	The body is dense and actionable with no concept-over-explanation (no 'what is a cluster' padding); every SQL block and property listing earns its place, assuming Claude's competence.	3 / 3
Actionability	Provides fully executable, copy-paste-ready SQL and JSON tool-call examples with specific property names and placeholders, directly matching the executable-code anchor.	3 / 3
Workflow Clarity	A clear 4-step sequence (list runs → load clusters → compute metrics → drill into traces) with orientation-first ordering; the SQL operations are read-only SELECTs with explicit time bounds, so the destructive/batch-mutation validation cap does not apply.	3 / 3
Progressive Disclosure	Overview body is well-organized into sections and offloads large-result rendering to a real, one-level-deep script reference (print_clusters.py, verified to exist in ./scripts/), with a clearly signaled cross-skill reference for event details.	3 / 3
	Total	12 / 12 Passed

Description

67%

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 specific and clearly niche-scoped, naming multiple concrete investigative actions. Its main weakness is the missing explicit 'Use when...' trigger clause, which limits completeness and leaves trigger guidance only implied.

Suggestions

Add an explicit trigger clause, e.g. 'Use when investigating AI observability clusters, grouping or comparing LLM usage patterns, or drilling into clustered traces.'

Include more natural user-facing phrasings alongside the technical terms (e.g. 'group similar LLM traces', 'LLM usage clusters') to broaden trigger term coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'understand usage patterns in AI/LLM traffic', 'compare cluster behavior', 'compute cost/latency metrics', and 'drill into individual traces' — matching the multiple-specific-actions anchor.	3 / 3
Completeness	The 'what' is strong and detailed, but there is no explicit 'Use when...' clause or equivalent trigger guidance, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Relevant domain terms like 'AI observability clusters', 'AI/LLM traffic', and 'traces' are present but the phrasing is niche/technical and misses common natural variations a user might say (e.g. 'group similar traces', 'LLM usage clusters').	2 / 3
Distinctiveness Conflict Risk	Targets a clear niche (AI observability clustering) with distinct triggers unlikely to collide with sibling skills such as the LLM traces skill.	3 / 3
	Total	10 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: PostHog/posthog
Path: products/ai_observability/skills/exploring-llm-clusters/SKILL.md
Commit: a5d244e

Reviewed: about 14 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.