build-and-run-macos-app

Slash command that creates or updates the project-local macOS `script/build_and_run.sh` and uses it as the default build/run entrypoint. Invoke explicitly with /build-and-run-macos-app — this skill never self-triggers.

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/build-and-run-macos-app/SKILL.md

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise and well-structured with a clear sequenced workflow and guardrails. Its main weaknesses are the missing inline script content (deferred to a non-local reference) and the absence of explicit build/launch validation checkpoints.

Suggestions

Inline or bundle the actual `build_and_run.sh` template (or place it in ./scripts/) instead of relying on an external sibling-skill reference, so the core executable artifact is self-contained and verifiable.

Add an explicit validation step between build and launch (e.g., 'Verify the build succeeded before launching; on failure, report the error and do not relaunch the stale app').

Turn step 7 into a feedback loop: on build/launch failure, surface the error, suggest a fix, and re-run the script rather than only summarizing.

Dimension	Reasoning	Score
Conciseness	The body is lean (~35 lines), assumes Claude knows Xcode/SwiftPM/git, and avoids concept explanations; every line is actionable guidance, matching 'Lean and efficient; assumes Claude's competence; every token earns its place'.	3 / 3
Actionability	Concrete commands and flags appear (`git init`, `/usr/bin/open -n`, `--debug`/`--logs`/`--telemetry`/`--verify`, `script/build_and_run.sh`), but the central executable artifact — the script's actual content — is deferred to an external reference (`../build-run-debug/references/build-script.md`) not present in this skill's bundle, leaving key details missing.	2 / 3
Workflow Clarity	Seven steps are clearly sequenced, but there is no explicit validation checkpoint (e.g., verify the build succeeded before launching) and step 7 only summarizes failure rather than providing a validate→fix→retry loop; for an operation that stops/relaunches an app this matches 'Steps listed but validation gaps'.	2 / 3
Progressive Disclosure	A compact, well-sectioned skill (Arguments / Workflow / Guardrails) with a single clearly-signaled one-level reference for the detailed script shape, matching the simple-skill guidance that well-organized sections score 3 without local bundle files.	3 / 3
	Total	10 / 12 Passed

Description

75%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concise, third-person, and gives explicit trigger guidance suited to a slash command, with a clear niche and low conflict risk. It is slightly under-comprehensive on the full action set and on natural trigger-term variations.

Suggestions

Expand the action list in the description to cover the full scope (stop/kill the running app, build, launch, debug/logs/telemetry/verify modes) so it reads as comprehensive rather than two actions.

Add natural trigger terms a user would say, e.g. 'Use when building or running a macOS Xcode or SwiftPM app', to broaden keyword coverage beyond the slash-command name.

Consider an explicit 'Use when...' phrasing in addition to the invocation instruction to strengthen the natural-trigger signal.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('creates or updates the project-local macOS `script/build_and_run.sh`', 'uses it as the default build/run entrypoint') but only two actions and not the full scope (stop, build, launch, debug) the body reveals, matching 'Names domain and some actions, but not comprehensive'.	2 / 3
Completeness	Clearly answers what ('creates or updates ... build_and_run.sh and uses it as the default build/run entrypoint') and provides equivalent explicit trigger guidance ('Invoke explicitly with /build-and-run-macos-app — this skill never self-triggers'), appropriate for a slash-command skill.	3 / 3
Trigger Term Quality	Relevant keywords are present ('macOS', 'build/run', 'build_and_run.sh') but coverage is invocation-focused and misses common variations a user would naturally say ('Xcode', 'Swift', 'launch app', 'debug'), matching 'Some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	A clear niche (project-local macOS build/run script via a named slash command) with 'never self-triggers' making accidental invocation very unlikely, matching 'Clear niche with distinct triggers; unlikely to conflict'.	3 / 3
	Total	10 / 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-and-run-macos-app/SKILL.md
Commit: 9d2bf09

Reviewed: about 12 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.