agent-analytics

Analytics your AI agent can actually use. Track, analyze, run A/B experiments, and optimize across all your projects via CLI. Includes a growth playbook so your agent knows HOW to grow, not just what to track.

Quality

74%

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 ./plugins/all-skills/skills/agent-analytics/SKILL.md

Quality

Content

82%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 highly actionable and well-structured, with copy-paste commands and an excellent question-to-endpoint map. Minor conciseness padding in the intro and the absence of an explicit error-recovery feedback loop are the only things keeping it from top marks.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with command tables and code blocks earning their place, but the opening marketing line ('the analytics platform your AI agent can actually use ... Built for developers who ship lots of projects') and the 'You are NOT Mixpanel' philosophy paragraph are mild padding that could be trimmed.	4 / 5
Actionability	Fully executable guidance throughout: copy-paste npx commands, an HTML snippet, JS track() examples, and a 'Which endpoint for which question' table that maps user questions to exact commands, covering the common cases comprehensively.	5 / 5
Workflow Clarity	First-time setup and Steps 1-3 are clearly sequenced with an explicit 'Test immediately' verification checkpoint and a significance threshold for experiments, but there is no error-recovery feedback loop (what to do if events do not appear), keeping it just below 5.	4 / 5
Progressive Disclosure	Well-organized with clear section headers and a strong question-to-command navigation table; the inlined CLI reference is the one block that could live in a separate file, but as a self-contained single-file skill with no bundle files this is a minor gap rather than a structural problem.	4 / 5
	Total	17 / 20 Passed

Description

66%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 clearly communicates capabilities with several concrete actions and a clear niche, but it omits an explicit 'Use when...' trigger clause, which caps its completeness. Slightly generic verbs ('analyze', 'optimize') keep specificity just below the top anchor.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers (e.g., 'Use when the user wants to add analytics, check traffic/conversions, or run A/B experiments on a site or app').

Replace generic verbs ('analyze', 'optimize') with more concrete actions (e.g., 'view funnels and retention cohorts', 'compare variants') to lift specificity toward 5.

Include common user phrasings like 'how's my site doing' or 'are people visiting' as trigger terms to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Track, analyze, run A/B experiments, and optimize ... via CLI') plus a distinct deliverable (growth playbook), but 'analyze' and 'optimize' are somewhat generic compared to the fully-fleshed anchor 5 example.	4 / 5
Completeness	The 'what' is clearly stated (track/analyze/experiment/optimize via CLI), but there is no explicit 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural terms a user would say ('analytics', 'A/B experiments', 'track', 'projects') with good coverage, but is missing common phrasings like 'how's my site doing', 'traffic', or 'conversions' that appear only in the body.	4 / 5
Distinctiveness Conflict Risk	The agent-focused analytics niche plus A/B experimentation and CLI access is a fairly distinct trigger space with minimal overlap risk, though 'analytics' alone is a broad category that could collide with general analytics skills.	4 / 5
	Total	15 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: davepoon/buildwithclaude
Path: plugins/all-skills/skills/agent-analytics/SKILL.md
Commit: c9856ea

Reviewed: 6 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.