Name: algolia-release-qa
Rating: 77.60000000000001 (1 reviews)
Author: algolia

algolia-release-qa

Algolia launch, regression, and implementation QA. Use when auditing an Algolia build before release, validating relevance changes, checking search UI behavior, verifying event instrumentation, diagnosing analytics gaps, reviewing secured keys, or creating a smoke test plan for search, browse, autocomplete, indexing, and configuration changes. Do NOT use to make live account changes or inspect live account data; use algolia-mcp or algolia-cli first. Do NOT use as the primary implementation skill when the task is clearly data modeling, events setup, InstantSearch, Autocomplete, NeuralSearch, or Agent Studio; use the focused skill first and this skill for final QA.

Quality

97%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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.

A well-structured, highly actionable QA skill body with explicit validation gates, real one-level-deep references, and concrete executable checks. Its only weakness is mild verbosity from war-story anecdotes and repeated source-reading warnings.

Suggestions

Trim the anecdote in the Finish Gates intro ('agents that had read this section still reported…') to a single clause; the 'executed, never asserted' rule already conveys the point.

Consolidate the repeated 'reading source is not executing the gate' warning — it currently appears in Finish Gates, Anti-Patterns, and Source-Of-Truth Rules — into one canonical statement referenced from the others.

Consider moving the readiness signposts list into references/release-qa-checklist.md to keep SKILL.md as a tighter overview, since the checklist reference already exists.

Dimension	Reasoning	Score
Conciseness	Mostly lean and directive, assuming Claude's competence, but carries anecdotal padding ('agents that had read this section still reported "no console errors ✓"…') and repeats the source-reading-is-not-execution warning across Finish Gates, Anti-Patterns, and Source-Of-Truth Rules.	4 / 5
Actionability	Provides copy-paste-ready guidance: the smoke command 'node scripts/page-smoke.mjs --dir <folder> --query "<a real product word>" --click --mobile', 'curl -sI' for CDN 200 checks, and concrete loader verification via a callback from aa('getVersion', cb) rather than the misleading typeof check.	5 / 5
Workflow Clarity	A 10-step sequenced Workflow pairs with Finish Gates framed as 'executed, never asserted' validation checkpoints, plus Signposts and Anti-Patterns acting as checklists with feedback loops (re-validate before claiming launch-ready).	5 / 5
Progressive Disclosure	The body is an overview that points one level deep to real, clearly signaled files — references/release-qa-checklist.md, references/example-output.md, references/verified-cdn-urls.md, and scripts/page-smoke.mjs (all verified present) — with bulk detail appropriately split out.	5 / 5
	Total	19 / 20 Passed

Description

100%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 high-quality description: concrete actions, natural trigger phrasing, explicit what/when, and strong boundary guidance against sibling Algolia skills. Third-person imperative voice throughout with no first/second-person drift.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'auditing an Algolia build before release, validating relevance changes, checking search UI behavior, verifying event instrumentation, diagnosing analytics gaps, reviewing secured keys' and 'creating a smoke test plan' — giving comprehensive coverage of the QA surface.	5 / 5
Completeness	Explicitly answers both 'what' ('Algolia launch, regression, and implementation QA') and 'when' via a concrete 'Use when' clause, and adds negative 'Do NOT use' boundaries — a textbook what+when with triggers.	5 / 5
Trigger Term Quality	Natural QA/release phrasing a user would say ('audit an Algolia build before release', 'smoke test plan', 'relevance changes') plus synonyms across surfaces (search, browse, autocomplete, indexing, configuration).	5 / 5
Distinctiveness Conflict Risk	Carves a clear release-QA niche and explicitly hands off to algolia-mcp, algolia-cli, instantsearch, and focused skills (InstantSearch, NeuralSearch, Agent Studio), minimizing wrong-skill triggering.	5 / 5
	Total	20 / 20 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: algolia/skills
Path: skills/algolia-release-qa/SKILL.md
Commit: 0953d1b

Reviewed: 5 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.