CtrlK
BlogDocsLog inGet started
Tessl Logo

review-hog-authoring

How to author custom PostHog Review skills: the review perspectives, blind-spot checks, validation criteria, and resolution criteria that drive PostHog Review's automated PR reviews. Use when a user wants a new review perspective (a specialist lens on their PRs), a custom blind-spot sweep, their own validation bar for which findings get published, or their own bar for which review comments get implemented. Trigger on "create a PostHog Review perspective", "custom review perspective", "my own blind-spot check", "custom validation criteria", "custom resolution criteria", "tune what PostHog Review publishes", "tune what PostHog Review implements".

69

Quality

85%

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, actionable authoring guide that names the exact MCP tools, name contracts, and activation steps for each of the four skill kinds. It is concise and clearly sequenced; the main room for improvement is adding a concrete example skill-create invocation and trimming the opening overview.

Suggestions

Add one full `posthog:skill-create` example call with concrete name, description, and body arguments so the create step is copy-paste ready.

Tighten the opening pipeline overview — the per-kind sections already convey what each kind does, so the chunk/parallel/dedup mechanics can be shortened.

Include an explicit validation/retry checkpoint in the authoring flow (e.g. re-read the created skill and confirm the name prefix and body landed correctly before telling the user to activate it).

DimensionReasoningScore

Conciseness

The body is largely lean and assumes Claude's competence (e.g. 'restating harness rules dilutes it'), but the opening pipeline overview and a few explanatory asides could be tightened slightly without losing clarity.

4 / 5

Actionability

Gives concrete executable guidance — specific MCP tool names (skill-list, skill-get, posthog:skill-create, posthog:skill-update), exact name contracts, and activation locations — but stops short of a full copy-paste example invocation with parameters, leaving minor gaps.

4 / 5

Workflow Clarity

The five-step authoring flow is clearly sequenced with explicit gating checkpoints ('Don't start writing until the direction is picked', 'actually create the team LLMSkill row; never hand the user a body to copy-paste'), though it lacks an explicit error-recovery feedback loop.

4 / 5

Progressive Disclosure

Content is well organized into a kind table plus dedicated per-kind sections with clear headers; no external bundle files are needed or referenced, and structure is good, though the guide runs over 50 lines so it does not qualify for the simple-skill 5.

4 / 5

Total

16

/

20

Passed

Description

95%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: it states the skill's purpose, lists the four concrete skill kinds it covers, and provides both a 'Use when' clause and explicit 'Trigger on' phrases in third-person voice. The only mild weakness is that the action verb ('author') is broad relative to the well-specified deliverables.

DimensionReasoningScore

Specificity

Names the domain ('author custom PostHog Review skills') and enumerates the four concrete deliverable kinds (perspectives, blind-spot checks, validation criteria, resolution criteria), but the action itself stays at the generic 'author' level rather than listing multiple distinct concrete actions, leaving minor coverage gaps.

4 / 5

Completeness

Explicitly answers both what ('How to author custom PostHog Review skills: the review perspectives, blind-spot checks, validation criteria, and resolution criteria') and when ('Use when a user wants... Trigger on...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Supplies a comprehensive set of natural trigger phrases users would actually say — 'create a PostHog Review perspective', 'custom review perspective', 'my own blind-spot check', 'tune what PostHog Review publishes', etc. — covering synonyms and variations.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (authoring PostHog Review skills) with PostHog-specific trigger phrases, making it unlikely to fire for unrelated skills.

5 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
PostHog/posthog
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.