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

92%

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%

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 macOS build/run/debug skill with a clear sequenced workflow, explicit verification, and proper one-level-deep reference disclosure. Its main weakness is redundancy: the mode-flag set and bundle metadata are repeated across sections.

Suggestions

State the `--debug`/`--logs`/`--telemetry`/`--verify` flag set once (e.g. in Workflow step 3) and have Quick Start and Preferred Commands point to it, instead of repeating the full list in three places.

Replace the inline Info.plist key enumeration in Workflow step 3 with a one-line pointer to `references/build-script.md`, which already contains the canonical bundle shape.

Consider folding the standalone 'Preferred Commands' section into the relevant Workflow steps so each command appears once in its operational context.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence (no primers on Xcode/SwiftPM), but the `--debug`/`--logs`/`--telemetry`/`--verify` flag set is restated in Quick Start, Workflow step 3, and Preferred Commands, and the Info.plist key list at step 3 duplicates the reference; not level 3 because not every token earns its place.	2 / 3
Actionability	Gives concrete executable commands (`git rev-parse --is-inside-work-tree`, `xcodebuild -list -workspace`, `find . -name '*.xcworkspace' ...`, `pgrep -x <AppName>`, `/usr/bin/open -n`) and a specific script path with copy-paste-ready flags, plus a canonical full script in the reference; not level 2 because guidance is complete and executable rather than pseudocode.	3 / 3
Workflow Clarity	A clear 7-step sequence with an explicit validation checkpoint (`--verify` / `pgrep -x`), failure classification in step 5, and a debug-recovery loop in step 6, plus guardrails on the risky `git init` operation; not level 2 because validation and feedback loops are explicit rather than implicit.	3 / 3
Progressive Disclosure	Well-organized sections (Quick Start, Workflow, Preferred Commands, References, Guardrails, Output Expectations) with a single one-level-deep, clearly signaled reference to `references/build-script.md`, which exists and holds the canonical full script; not level 2 because the split is appropriate and navigation is easy.	3 / 3
	Total	11 / 12 Passed

Description

100%

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 states concrete capabilities and pairs them with an explicit 'Use when' trigger clause scoped to macOS desktop development. It is specific, complete, and clearly distinguishable from adjacent skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Build, run, and debug local macOS apps and desktop executables' plus 'diagnose compiler or linker failures, inspect startup problems, or debug desktop-only runtime issues' — matching the multiple-specific-actions anchor; not the level below because it is comprehensive rather than naming only some actions.	3 / 3
Completeness	Explicitly answers both what ('Build, run, and debug local macOS apps and desktop executables using shell-first Xcode and Swift workflows') and when ('Use when asked to build a Mac app, launch it, diagnose...'); the explicit 'Use when' clause clears the cap that would limit this to 2.	3 / 3
Trigger Term Quality	Natural user phrases like 'build a Mac app', 'launch it', 'diagnose compiler or linker failures', and 'debug desktop-only runtime issues' give good coverage of terms users would actually say; not level 2 because common variations are present rather than partially missing.	3 / 3
Distinctiveness Conflict Risk	A clear niche — 'local macOS apps and desktop executables' with 'desktop-only runtime issues' — is unlikely to conflict with mobile/web/simulator skills; not level 2 because the triggers are sharply scoped to macOS desktop rather than merely 'somewhat specific'.	3 / 3
	Total	12 / 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: robinebers/openusage
Path: .agents/skills/build-run-debug/SKILL.md
Commit: 9d2bf09

Reviewed: about 13 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.