CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

seo-posthog

PostHog MCP extension. PostHog analytics as a GA4 alternative or complement. Organic traffic, landing pages, device / country breakdowns, referrers, via the PostHog MCP server. Triggers on "PostHog", "posthog analytics", "GA4 alternative", "product analytics SEO".

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/seo-posthog/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 compact, well-sectioned router for six subcommands with concrete defaults, explicit error-handling and output rules, and unusually strong security guidance (untrusted-data treatment and read-only credential scoping). It falls short of top marks mainly on actionability (no example invocations or sample HogQL) and mild redundancy in the Security section.

Suggestions

Add one example invocation with options (e.g., `/seo posthog organic --days 90`) and a sample HogQL query or MCP exec call so the guidance is copy-paste ready.

Dedupe the Security section: state the read-only rule and the no-credential rule once each instead of twice.

State an explicit sequence, e.g., "Run `/seo posthog check` before any data command", to add a validation checkpoint to the workflow.

DimensionReasoningScore

Conciseness

The body is tight and operational (routing table, defaults, error handling, output format) with no explanations of concepts Claude already knows. Minor redundancy could be trimmed: "this extension ships no script and stores no token" (intro) repeats "This extension stores no credential" (Security), and the read-only rule appears in both the second and third Security bullets.

4 / 5

Actionability

Concrete guidance dominates: six named commands in the routing table, "Options: days (default 28) and limit (default 50)", and the delegation mechanism "runs HogQL queries through the MCP `exec` tool (`call execute-sql`)". It stops short of anchor 5 because there is no example invocation with options and no sample HogQL query or MCP call to copy.

4 / 5

Workflow Clarity

Sections sequence logically from Prerequisites to Routing to Error Handling, and validation is present: "/seo posthog check" verifies connectivity, and empty results trigger a verification step ("verify project, window, and that $referring_domain is captured before reporting zero organic traffic"). It misses anchor 5 because no explicit end-to-end ordering (e.g., run check before data commands) or re-check loop is stated.

4 / 5

Progressive Disclosure

Good structure with clear, flat section headers and no nested references; no bundle files exist, so nothing is over-inlined. The minor gap is that referenced paths such as "extensions/posthog/install.sh" and "extensions/posthog/docs/POSTHOG-SETUP.md" point outside the skill bundle and cannot be resolved from the skill itself.

4 / 5

Total

16

/

20

Passed

Description

75%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 identifies a niche (PostHog analytics via MCP as a GA4 alternative or complement), lists concrete data deliverables, and includes an explicit "Triggers on" clause that answers both what and when. It falls short of top marks for its verb-free fragment style, a few missing natural synonyms, and minor trigger overlap with sibling analytics skills via "GA4 alternative".

Suggestions

Rewrite the capability statement with action verbs, e.g., "Pull organic traffic, top landing pages, device/country breakdowns, and referrers from PostHog via the PostHog MCP server", to sharpen the what.

Add missing natural trigger synonyms such as "web analytics", "traffic sources", or "organic search traffic" to broaden keyword coverage.

Qualify the "GA4 alternative" trigger (e.g., "GA4 alternative (when the site already tracks with PostHog)") to reduce overlap with sibling analytics skills.

DimensionReasoningScore

Specificity

"Organic traffic, landing pages, device / country breakdowns, referrers" lists several concrete deliverables that cover the skill's domain, but the fragment style ("PostHog MCP extension", "PostHog analytics as a GA4 alternative") names no action verbs, placing it between anchor 3 and anchor 4.

4 / 5

Completeness

Both parts are explicitly present: the what ("Organic traffic, landing pages, device / country breakdowns, referrers, via the PostHog MCP server") and an explicit when ("Triggers on 'PostHog', 'posthog analytics', 'GA4 alternative', 'product analytics SEO'"). It falls below anchor 5 because the what is a noun-fragment list rather than a clearly stated set of capabilities.

4 / 5

Trigger Term Quality

The explicit triggers "PostHog", "posthog analytics", "GA4 alternative", and "product analytics SEO" are phrases a user would naturally say, but common variations such as "web analytics", "traffic sources", or "organic search traffic" are missing, so coverage is good rather than comprehensive.

4 / 5

Distinctiveness Conflict Risk

The PostHog-specific triggers establish a clear niche with minimal conflict risk, but "GA4 alternative" and "product analytics SEO" could also plausibly match closely related sibling analytics skills (e.g., a Matomo or product-analytics skill), which is exactly anchor 4's "minor overlap risk with closely related skills".

4 / 5

Total

16

/

20

Passed

Validation

100%

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

AgriciDaniel/claude-seo

Path

skills/seo-posthog/SKILL.md

Reviewed

Table of Contents

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.