Name: release-sample-sweep
Rating: 72 (1 reviews)
Author: Atmosphere

release-sample-sweep

Run the pre-release end-to-end sweep of every user-facing surface — the 33 samples under samples/ (booted from their packaged artifacts and driven in a real browser via chrome-devtools MCP), the Expo/React Native client, and the atmosphere CLI. Use before cutting a release, and after any change to the Console bundle, a shared module, atmosphere.js, the CLI, or several samples at once. Covers preconditions, the keyless Ollama backend, the per-sample launch/drive/collect/teardown loop, the evidence ledger, the fix phase (every issue gets a biting regression test in the right suite), the re-test subset, and the report.

Quality

88%

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

85%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 procedure body with a clear multi-step workflow, explicit validation, and excellent progressive disclosure through real referenced files. Minor conciseness and inline-completeness gains are available by trimming narrative prose and inlining a touch more of the Expo/CLI procedures.

Suggestions

Trim the narrative opener and the 2026-06/2026-07 historical-bug table down to the lesson each teaches, since the non-negotiables already encode those lessons.

Inline one or two of the most common Expo/CLI probe commands before the 'Full procedure: references/...' pointer so the body stands alone for the typical case.

Consider moving the dated sweep-log anecdotes (e.g. 2026-08-07 shakedown) into references/troubleshooting.md to keep time-sensitive detail out of the overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with tables and code blocks that earn their place, but the narrative intro ('This skill is that procedure written down') and the historical-bug storytelling add prose that could be trimmed without losing the actionable guidance.	4 / 5
Actionability	Provides concrete, copy-paste-ready commands (./mvnw install -DskipTests -Pfastinstall, the full sweep-sample.sh invocation, grep 'AI config:') for the main loop, but defers the full Expo and CLI procedures to references, leaving minor gaps in inline executable guidance.	4 / 5
Workflow Clarity	Clear Step 0–5 sequence with explicit validation checkpoints (git status clean, port-release verification, resolved-endpoint grep), a COLLECT-ONLY gate, and a 'repeat triage → fix → re-test' feedback loop backed by a non-negotiables checklist.	5 / 5
Progressive Disclosure	SKILL.md is a clear overview with a 'Files in this skill' table; all seven references, the ledger template asset, and the sweep script are one level deep, clearly signaled, and verified to exist, so detail is appropriately split for easy navigation.	5 / 5
	Total	18 / 20 Passed

Description

92%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, third-person description that clearly states both what the skill does and when to invoke it, with concrete actions and a distinct niche. Trigger terms are natural for the target maintainer audience though somewhat jargon-bound.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions with comprehensive coverage: 'sweep of every user-facing surface', 'booted from their packaged artifacts and driven in a real browser', 'per-sample launch/drive/collect/teardown loop', 'evidence ledger', 'fix phase', 're-test subset', and 'report'.	5 / 5
Completeness	Explicitly answers both 'what' (the end-to-end sweep across samples, Expo client, and CLI) and 'when' ('Use before cutting a release, and after any change to the Console bundle, a shared module, atmosphere.js, the CLI, or several samples at once').	5 / 5
Trigger Term Quality	Natural maintainer trigger phrases like 'before cutting a release' and 'after any change to the Console bundle, a shared module' are present, but the language is domain-jargon-heavy (atmosphere CLI, chrome-devtools MCP) and a few common synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	Targets a narrow, repo-specific release-gate niche (33 samples + Expo RN client + atmosphere CLI via chrome-devtools MCP) with distinct triggers and minimal conflict risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: Atmosphere/atmosphere
Path: .claude/skills/release-sample-sweep/SKILL.md
Commit: 468f0ea

Reviewed: 3 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.