CtrlK
BlogDocsLog inGet started
Tessl Logo

diagnosing-sdk-health

Diagnoses the health of a project's PostHog SDK integrations — which SDKs are out of date and how to fix them. Use when a user asks about PostHog SDK versions, outdated SDKs, upgrade recommendations, "SDK health", "SDK doctor" (the former name), or when events or features seem off and it might be due to an old SDK.

76

Quality

93%

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 content is a tight, executable playbook: exact tool calls, an explicit triage-then-stop validation gate, and security guardrails (the trusted/untrusted trust boundary) that act as feedback loops. It loses only a point on conciseness due to a few passages that could be trimmed without losing meaning.

Suggestions

Tighten the Step 4 delay-expectations paragraph and the "Interpreting severity" rules block — several sentences can be compressed into bullet fragments without losing the actionable detail.

Consider moving the canonical "Keeping SDKs current" deferral language into a short reference block so the main workflow stays scannable while the full suggested reply is preserved verbatim.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — it never explains what PostHog, an SDK, or semver is — but a few passages (e.g. the multi-sentence delay-expectations paragraph and the severity-rules block) could be tightened, so it sits just below the "every token earns its place" 5 anchor.

4 / 5

Actionability

Concrete tool invocations with exact parameters (e.g. `posthog:health-issues-list { "kind": "sdk_outdated", "status": "active" }`), a canonical SQL query referenced from remediation text, and copy-paste-ready reply snippets fully cover the common cases, matching the executable 5 anchor.

5 / 5

Workflow Clarity

A clear 5-step sequence (triage → list → drill in → act → link to UI) is paired with an explicit validation checkpoint in Step 1 (zero sdk_outdated issues ⇒ healthy, stop) and trust-boundary guardrails that function as error-prevention feedback; this matches the "explicit validation steps; feedback loops" anchor rather than the "minor validation gaps" 4.

5 / 5

Progressive Disclosure

No bundle files are present and the skill is a single, well-sectioned SKILL.md with clear headers and one clearly-signaled external docs URL; under the simple-skill guidance, a self-contained well-organized file scores 5 without external references.

5 / 5

Total

19

/

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.

The description is well-crafted: it pairs a precise statement of what the skill does with an explicit, trigger-rich "Use when" clause and distinctive terminology including a deprecated alias. The only minor gap is that the fix actions are summarized rather than enumerated, which slightly limits specificity.

DimensionReasoningScore

Specificity

"Diagnoses the health of a project's PostHog SDK integrations — which SDKs are out of date and how to fix them" names the domain and concrete actions (diagnose, identify outdated, fix), but the description stops short of enumerating the full set of fix actions, leaving minor coverage gaps — closer to "several specific actions; minor gaps" than the comprehensive 5.

4 / 5

Completeness

It clearly states the "what" (diagnoses SDK health, identifies outdated SDKs, how to fix them) and an explicit "Use when..." clause with concrete trigger phrases, matching the anchor for clearly and explicitly answering both what AND when.

5 / 5

Trigger Term Quality

"PostHog SDK versions, outdated SDKs, upgrade recommendations, 'SDK health', 'SDK doctor' (the former name)" gives comprehensive coverage of natural terms including synonyms and the deprecated alias; it is not the lower anchor ("a few natural terms missing") because every common variation a user would say is present.

5 / 5

Distinctiveness Conflict Risk

The PostHog-SDK-health niche is narrow and carries distinct triggers ("SDK health", "SDK doctor", "outdated SDKs") that are unlikely to fire for unrelated skills, giving minimal conflict risk.

5 / 5

Total

19

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.