Name: baseline
Rating: 76.8 (1 reviews)
Author: meshtastic

baseline

Run the mandatory pre-push baseline verification for Meshtastic-Android — bootstrap, then spotlessApply/spotlessCheck/detekt/assembleDebug/test/allTests (plus kmpSmokeCompile and sort-strings when relevant) via the gradle-runner subagent, restore the host-render screenshot diff, and report a single pass/fail. Use before every push. This is the check CI fails on when skipped.

Quality

96%

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

100%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.

This is a tightly written, fully executable runbook: a numbered five-step workflow with real commands, precise file paths, conditional task selection, and an explicit validation checkpoint plus feedback loop against a misbehaving subagent. It is lean with no filler, and its size and self-containment make external references unnecessary. No weaknesses identified against the rubric.

Dimension	Reasoning	Score
Conciseness	Every line instructs rather than explains ("Both `test` and `allTests` are required — `allTests` covers KMP modules (where bare `test` silently skips)") with no padding or concepts Claude already knows; the one piece of motivational context ("CI has failed repeatedly when it was skipped") is brief and load-bearing, matching the lean top anchor.	5 / 5
Actionability	Fully executable throughout: copy-paste bash for bootstrap and diff inspection, the exact gradle line "./gradlew spotlessApply spotlessCheck detekt assembleDebug test allTests", precise paths ("core/resources/.../values/strings.xml", ".github/workflows/pull-request.yml"), and conditional variants for strings/KMP changes, matching the copy-paste-ready top anchor.	5 / 5
Workflow Clarity	Five clearly sequenced steps with an explicit validation checkpoint ("After it returns, confirm the only changes are yours: git status --short") and a feedback loop for error recovery ("treat its PASS as suspect and re-run the failing task inline"; "Do not push on FAIL"), satisfying the batch-operation validation requirement and matching the top anchor.	5 / 5
Progressive Disclosure	The skill is under 50 lines, self-contained with no bundle files (references/, scripts/, assets/ are absent and nothing is referenced), and organized into five well-labeled sections, which per the rubric's simple-skill guideline earns the top score on structure alone.	5 / 5
	Total	20 / 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 highly effective description: it states the full concrete task list, the execution mechanism (gradle-runner subagent), and an explicit usage trigger tied to pushes and CI. Third-person, concise, and specific to one repo's gate, leaving virtually no conflict risk. The only minor gap is synonym coverage of natural trigger phrasings.

Dimension	Reasoning	Score
Specificity	The description enumerates concrete actions — "bootstrap, then spotlessApply/spotlessCheck/detekt/assembleDebug/test/allTests (plus kmpSmokeCompile and sort-strings when relevant)", "restore the host-render screenshot diff", "report a single pass/fail" — giving comprehensive coverage with no real gaps, matching the top anchor.	5 / 5
Completeness	It explicitly answers both questions: what (the full named task list executed via the gradle-runner subagent) and when ("Use before every push. This is the check CI fails on when skipped"), matching the anchor requiring clear what AND when with concrete triggers; not 4 because the when-clause is fully explicit rather than improvable.	5 / 5
Trigger Term Quality	Natural phrases like "pre-push", "Use before every push", "baseline", and "CI" are present and would be said by users, but a few common variations (e.g. "verify", "lint", "build check") are missing, matching "good keyword coverage; a few natural terms missing" rather than the comprehensive-synonyms anchor at 5.	4 / 5
Distinctiveness Conflict Risk	It occupies a clear niche — the pre-push verification gate for a specific repo with named gradle tasks — so the chance of triggering for the wrong skill is minimal, matching the "clear niche with distinct triggers" anchor.	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: meshtastic/Meshtastic-Android
Path: .claude/skills/baseline/SKILL.md
Commit: d003a21

Reviewed: 9 hours 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.