Name: survey-sdk-audit
Rating: 59.2 (1 reviews)
Author: PostHog

Blog Docs Log in Get started

survey-sdk-audit

Audit PostHog survey SDK features and version requirements

Quality

67%

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 ./.agents/skills/survey-sdk-audit/SKILL.md

Quality

Content

77%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with executable commands, a clear multi-step workflow, explicit validation checkpoints, and a completion checklist. Its main weaknesses are length/redundancy and a monolithic structure that could move large templates into referenced files.

Suggestions

Move the large settings.local.json example and/or the issue template and output-format blocks into reference files (e.g. references/issue-template.md) referenced one level deep to improve progressive disclosure.

Tighten redundant SDK path listings that repeat across the Setup Check, the paths table, and Step 5.

Consider a compact quick-start summary at the top so the detailed per-SDK file paths can be treated as a reference appendix.

Dimension	Reasoning	Score
Conciseness	The body is domain-specific and avoids explaining concepts Claude already knows, but at ~350 lines it includes some redundancy (repeated SDK path listings, a large settings.local.json JSON block) that could be tightened, matching the level-2 anchor of mostly efficient but could be tightened.	2 / 3
Actionability	It provides fully executable commands (e.g. "git log --oneline --all -S 'KEYWORD'", "gh issue create --repo ... --label 'Survey'"), exact file paths, copy-paste-ready issue and output templates, and per-SDK labels, matching the level-3 anchor of fully executable, copy-paste-ready guidance.	3 / 3
Workflow Clarity	Steps 1-5 are clearly sequenced with an explicit CRITICAL validation checkpoint ("Having a field in a data model does NOT mean the feature is implemented"), a completion checklist, and feedback loops (search existing issues before creating, backfill sibling links), matching the level-3 anchor of clear sequence with explicit validation and checklists.	3 / 3
Progressive Disclosure	No bundle files exist and the whole skill is a single ~350-line SKILL.md with well-organized sections, but substantial content that could be split (the settings.local.json example, issue template, output format) is inline rather than one-level-deep references, matching the level-2 anchor of some structure with content that should be separate kept inline.	2 / 3
	Total	10 / 12 Passed

Description

57%Weight 40%Scale 1-3

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 specific and distinct but stops short of full completeness because it omits an explicit 'Use when...' trigger clause and lists only a couple of concrete actions. Adding a trigger clause and a few more concrete actions would raise specificity and completeness.

Suggestions

Add an explicit trigger clause, e.g. "Use when auditing survey feature support across PostHog SDKs or updating surveyVersionRequirements.ts version requirements."

List more concrete actions in the description (e.g., search changelogs, trace git history for feature introductions, create GitHub issues for unsupported SDKs).

Include common natural variations a user might say (e.g., "survey feature support", "SDK parity", "changelog audit") to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	"Audit PostHog survey SDK features and version requirements" names the domain (PostHog survey SDKs) and two concrete actions (auditing features, version requirements), but does not list multiple specific concrete actions like the level-3 anchor, so it sits at level 2.	2 / 3
Completeness	It clearly states what the skill does but lacks any "Use when..." clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Terms like "audit", "PostHog", "survey SDK", and "version requirements" are natural and relevant, but coverage is narrow with no common variations (e.g., "survey feature support", "SDK parity", "changelog"), matching the level-2 anchor of some relevant keywords missing common variations.	2 / 3
Distinctiveness Conflict Risk	"PostHog survey SDK" is a clear, narrow niche with distinct triggers unlikely to overlap with unrelated skills, matching the level-3 anchor of a clear niche with distinct triggers.	3 / 3
	Total	9 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: PostHog/posthog
Path: .agents/skills/survey-sdk-audit/SKILL.md
Commit: 9bae056

Reviewed: 8 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.