build-run-debug

Build, run, and debug local macOS apps and desktop executables using shell-first Xcode and Swift workflows. Use when asked to build a Mac app, launch it, diagnose compiler or linker failures, inspect startup problems, or debug desktop-only runtime issues.

Quality

89%

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

78%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, operational skill body that delegates the full script to a single canonical reference and provides concrete commands and a clear multi-step workflow. Main weaknesses are repeated guidance that could be consolidated and verification being optional rather than default.

Suggestions

Consolidate the 'raw executable launch only for true CLI tools' guidance — it appears in Quick Start, Workflow steps 2 and 3, and Guardrails; state it once in Guardrails and reference it elsewhere.

Make launch verification a default checkpoint in the main build/run flow (e.g., always confirm the process with pgrep -x after launch) rather than only via the optional --verify flag.

Inline a minimal copy-paste build_and_run.sh skeleton in the body so the common CLI case is executable without first opening references/build-script.md.

Dimension	Reasoning	Score
Conciseness	The body is lean and operational without explaining concepts Claude already knows, but the 'raw executable launch only for CLI tools' guidance is repeated across Quick Start, Workflow steps 2 and 3, and Guardrails and could be consolidated.	4 / 5
Actionability	Concrete commands are present (xcodebuild -list, pgrep -x, /usr/bin/open -n, swift build) with a defined flag set and Info.plist key list, but the full copy-paste script lives in the reference rather than inline.	4 / 5
Workflow Clarity	A clear 7-step sequence with a --verify checkpoint and failure-classification feedback loop (steps 5-6), though launch verification is optional rather than a default checkpoint in the main flow.	4 / 5
Progressive Disclosure	Well-sectioned overview (Quick Start, Workflow, Preferred Commands, References, Guardrails, Output Expectations) with a single one-level-deep canonical reference (references/build-script.md, confirmed present) that is clearly signaled and explicitly designated as the authoritative source.	5 / 5
	Total	17 / 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 strong, specific description that clearly states concrete capabilities and provides explicit trigger guidance with natural phrasing. Third-person voice is used correctly throughout with no vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — build, run, debug, launch, diagnose compiler/linker failures, inspect startup problems, debug runtime issues — with comprehensive coverage of the domain.	5 / 5
Completeness	Explicitly answers both what ('Build, run, and debug local macOS apps...using shell-first Xcode and Swift workflows') and when ('Use when asked to build a Mac app...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger phrases users would say ('build a Mac app', 'launch it', 'compiler or linker failures', 'startup problems', 'runtime issues') with good synonym coverage.	5 / 5
Distinctiveness Conflict Risk	Clear macOS-desktop niche ('local macOS apps and desktop executables', 'desktop-only runtime issues') that explicitly excludes mobile/simulator workflows, minimizing conflict risk.	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: robinebers/openusage
Path: .agents/skills/build-run-debug/SKILL.md
Commit: 2270d5f

Reviewed: 1 day 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.