CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

posthog

Analyze product data and manage product tooling in PostHog. Use when the user wants product analytics or insights, HogQL/SQL queries, feature flags, experiments and A/B tests, error tracking, session replay, surveys, LLM analytics, dashboards, data warehouse, or PostHog documentation.

66

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

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.

A well-structured, instruction-only skill body with a clear ordered workflow, identifier-resolution checkpoints, destructive-change confirmation, and a troubleshooting feedback loop, appropriately deferring detail to runtime tool and docs discovery. The main weaknesses are mild redundancy between the tips sections and the workflow, and the lack of any example HogQL query or post-write verification step.

Suggestions

Fold "Tips for Maximum Productivity" into the workflow steps and HogQL section — "batch related reads before writes" and "confirm identifiers up front" already appear in Steps 2–3, and the final troubleshooting bullet repeats the docs-search advice from the Overview.

Add one short example HogQL query (e.g., a narrow date-ranged events count) to anchor the querying guidance and make the "read the schema, confirm event/property names" advice concrete.

Add an explicit post-write verification step to the workflow (e.g., re-fetch the created flag, experiment, or dashboard to confirm it was created with the intended fields) to close the validation loop for write operations.

DimensionReasoningScore

Conciseness

The body is efficient and assumes competence (e.g., "Don't build workarounds for 'query-time' person properties"), but "Tips for Maximum Productivity" restates Step 2/3 guidance ("Batch related reads before writes; confirm identifiers up front") and the closing troubleshooting bullet repeats the docs-search advice from the Overview and Step 2. Not a 5 because of this duplicated material; not a 3 because the rest is lean with no concept explanations Claude already knows.

4 / 5

Actionability

Guidance is specific and executable in context: Step 2 names the exact identifiers to resolve (project ID, flag key, experiment ID, insight/dashboard ID, error issue ID), Step 3 gives a concrete read-first batching order with a destructive-change checkpoint, and natural-language examples are quoted ("signups by week this quarter"). Not a 5 because there is no sample HogQL query or example tool invocation to anchor the querying guidance; as an instruction-only skill relying on runtime-discovered tools, the absence of code is otherwise justified.

4 / 5

Workflow Clarity

Steps 0–4 are explicitly ordered ("Follow these steps in order. Do not skip steps.") with checkpoints (resolve identifiers before calling tools; state impact and confirm before destructive or broad changes) and a troubleshooting feedback loop (empty results → re-check names, date range, filters, timezone; confirm via a small query). Not a 5 because there is no explicit post-write verification step (e.g., re-fetch the created flag/experiment to confirm). The destructive/batch cap at 3 does not apply since validation and confirmation steps are present.

4 / 5

Progressive Disclosure

A single-file skill with no bundle files and well-organized sections, a routing capability-map table, and correct deferral of syntax/product detail to the runtime docs-search tool rather than inlined reference material. Not a 5 because the ~85-line body is slightly more than a pure overview — the HogQL tips and productivity tips could fold into the workflow sections — though nothing here warrants separate files.

4 / 5

Total

16

/

20

Passed

Description

83%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.

A strong description that states what the skill does and when to use it with an explicit, third-person trigger clause covering the full PostHog surface. Trigger coverage is near-comprehensive with only a few natural synonyms missing and some minor generic-term overlap risk.

DimensionReasoningScore

Specificity

"Analyze product data and manage product tooling in PostHog" plus the enumerated surfaces (HogQL/SQL queries, feature flags, experiments, error tracking, session replay, surveys, dashboards, data warehouse) lists several specific capabilities with only minor gaps. It is not a 5 because the leading verbs "analyze" and "manage" are more generic than concrete actions like extract/fill/merge.

4 / 5

Completeness

Explicitly answers both: what ("Analyze product data and manage product tooling in PostHog") and when ("Use when the user wants product analytics or insights, HogQL/SQL queries, feature flags...") with concrete trigger phrases in third person.

5 / 5

Trigger Term Quality

Strong natural-term coverage including a synonym pair ("experiments and A/B tests") and technical-but-spoken terms like "feature flags", "session replay", "HogQL/SQL queries". A few phrases users commonly say are missing (funnel, retention, churn, rollout), keeping it just below comprehensive.

4 / 5

Distinctiveness Conflict Risk

PostHog-specific terms (HogQL, session replay, PostHog documentation) create a clear niche, but broadly generic words like "surveys", "dashboards", "error tracking", and "data warehouse" carry minor overlap risk with adjacent analytics/observability skills.

4 / 5

Total

17

/

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

openai/plugins

Path

plugins/posthog/skills/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.