CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

xcode-run

Load to install or dispatch a macOS GitHub Actions build, test or simulator screenshot run for an Xcode project.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/xcode-run/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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 concise, well-sectioned body with genuinely executable dispatch commands and honest limitation notes. Its weaknesses are the missing verification/observation steps in the install-configure-dispatch workflow and a broken reference to templates/mac-run.yml, which forces the reader to trust prose descriptions of the workflow instead of reading it.

Suggestions

Add post-dispatch verification commands, e.g. `gh run watch` / `gh run list --workflow mac-run.yml` and `gh run download` for the `mac-run` artifact, to close the validation-loop gap.

Ensure templates/mac-run.yml ships in the bundle (it is referenced by both the body and scripts/install.sh but is absent), or inline the key workflow snippet so the payload is inspectable.

Provide a concrete example XCODE_DESTINATION value (a specific simulator identifier) alongside the 'Replace the example' guidance.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence: terse tables for env values and dispatch steps, copy-paste `gh` commands, and honest scope/failure notes ("does not archive, export or deploy an app") with zero padding or explanation of concepts Claude already knows. It matches the 'every token earns its place' anchor; the only near-noise is the small kendex instruction comment block, which is structural rather than over-explanation.

5 / 5

Actionability

Guidance is mostly executable: exact `gh workflow run mac-run.yml -f step=...` commands for all three operations, a table of env values to edit, and a named installer script (scripts/install.sh, which exists). It falls short of the 5 anchor because the body's central reference, templates/mac-run.yml, is not present in the bundle, and configuration advice is prose ('Replace the example with a simulator supported by the selected Xcode') without a concrete example destination.

4 / 5

Workflow Clarity

The sequence (install → configure env → commit to default branch → dispatch → retrieve artifact) is present and coherent via section ordering, but verification checkpoints are missing or implicit: no commands to confirm dispatch (e.g. `gh run watch/list`) or download the `mac-run` artifact, and no pre-dispatch check that XCODE_SCHEME/XCODE_DESTINATION are valid. This matches the 'sequence present but checkpoints missing' anchor; it is above the 2 anchor because steps are well defined, but below 4, which requires most checkpoints present.

3 / 5

Progressive Disclosure

Sections are well organized and references are clearly signaled (a markdown link to templates/mac-run.yml, and the installer declared in frontmatter pointing to the real scripts/install.sh). However, scoring against the actual bundle structure, the referenced templates/mac-run.yml does not exist in the bundle, so navigation to the skill's core payload is broken — the workflow's behavior must be inferred from prose. This places it between 'references present but not clearly signaled' (3) and 'minor organization gaps' (4), landing at 3 due to the unresolvable reference.

3 / 5

Total

15

/

20

Passed

Description

70%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 tight, domain-specific description that clearly states what the skill does with concrete operation names. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness and leaves activation guidance only weakly implied.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to build, test, or capture simulator screenshots for an Xcode project in GitHub Actions or CI.'

Include natural trigger variations such as 'xcodebuild', 'CI', or 'continuous integration' to broaden keyword coverage.

Optionally mention artifact/log retrieval (e.g. downloading run logs and screenshots) to round out capability coverage.

DimensionReasoningScore

Specificity

The description lists several concrete actions — "install or dispatch a macOS GitHub Actions build, test or simulator screenshot run" — covering the skill's main operations (install, dispatch, build, test, screenshots). It falls just short of the 5 anchor because artifact/log retrieval and the xcodebuild mechanism go unmentioned, leaving minor coverage gaps.

4 / 5

Completeness

The 'what' is clear (installs and dispatches a macOS GitHub Actions build/test/screenshot workflow), but there is no 'Use when...' clause or equivalent explicit trigger guidance; the leading "Load to install or dispatch" only weakly implies when to load the skill. Per the judging guideline, a missing explicit trigger clause caps completeness at 3 — not 4, which requires both what and when with the when at least explicit.

3 / 5

Trigger Term Quality

Natural terms users would say are present: "Xcode project", "GitHub Actions", "build", "test", "simulator screenshot", "macOS". A few common variations are missing ("xcodebuild", "CI", "run tests in CI"), which fits the 'good keyword coverage; a few natural terms missing' anchor rather than the comprehensive 5 anchor.

4 / 5

Distinctiveness Conflict Risk

The niche is unmistakable — Xcode projects built/tested/screenshot on macOS GitHub Actions runners with simulator screenshots — and would not plausibly trigger for unrelated skills. It clearly matches the 'clear niche with distinct triggers; minimal conflict risk' anchor; even the 4 anchor's 'minor overlap risk with closely related skills' is not implicated.

5 / 5

Total

16

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 1 missing

Warning

Total

13

/

16

Passed

Repository

vanillagreencom/kendex

Path

.agents/skills/xcode-run/SKILL.md

Reviewed

Table of Contents

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.