CtrlK
BlogDocsLog inGet started
Tessl Logo

ship-desktop

Build the Agent Native desktop app locally, kill the running copy, install the fresh DMG to /Applications, and launch it. Use when the user says "rebuild/reinstall the desktop app", "ship desktop", "install the desktop app", or similar.

78

Quality

100%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Medium

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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

The content is a tightly written, fully executable end-to-end procedure with a clear numbered workflow, explicit validation checkpoints before destructive steps, and clean sectioning. It avoids teaching concepts Claude already knows and keeps all genuinely non-obvious local-environment detail inline where it belongs.

DimensionReasoningScore

Conciseness

The body is dense and operational, assuming Claude's competence with no generic concept explanations; explanatory prose (universal-build stalls, signing fallback, icon-cache flushing) addresses non-obvious local-environment quirks Claude would not already know, so tokens earn their place rather than padding.

3 / 3

Actionability

Provides fully executable, copy-paste-ready bash commands with specific flag values (e.g. electron-builder --mac dmg --arm64 -c.mac.notarize=false, PlistBuddy, codesign --verify --deep --strict), matching the score-3 anchor for complete executable code rather than pseudocode.

3 / 3

Workflow Clarity

A clear numbered 1–5 sequence (Build, Quit, Verify, Install, Launch) with explicit validation checkpoints — build-failure log grep in step 1 and Assets.car/PlistBuddy/codesign verification in step 3 — before the destructive install, so the destructive-operation cap does not apply.

3 / 3

Progressive Disclosure

A single-file, single-purpose linear procedure with well-organized sections (When to use, Pre-flight, Steps, Notes) and no external references needed; per the simple-skills note, clean organization without nested or missing references supports a score of 3.

3 / 3

Total

12

/

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.

The description is specific, complete, and uses natural trigger terms with an explicit "Use when..." clause, all in appropriate imperative (third-person-style) voice. It clearly communicates both the capability and the triggering contexts with no over-claims or padding.

DimensionReasoningScore

Specificity

Enumerates multiple concrete actions — "Build the Agent Native desktop app locally, kill the running copy, install the fresh DMG to /Applications, and launch it" — matching the score-3 anchor for listing several specific actions rather than naming only a domain and a couple of actions.

3 / 3

Completeness

Explicitly answers both what (build/kill/install/launch) and when via a clear "Use when the user says..." clause, matching the score-3 anchor for clearly answering what AND when with explicit triggers; not score 2 because the when is explicit, not merely implied.

3 / 3

Trigger Term Quality

Provides natural user phrasings — "rebuild/reinstall the desktop app", "ship desktop", "install the desktop app" — that a user would genuinely say, aligning with good natural-keyword coverage rather than the score-2 "some relevant keywords but missing common variations."

3 / 3

Distinctiveness Conflict Risk

Targets a single named app ("Agent Native desktop app") with distinct triggers like "ship desktop", giving it a clear niche unlikely to conflict with other skills, matching the score-3 anchor.

3 / 3

Total

12

/

12

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.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

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

Warning

Total

13

/

16

Passed

Repository
BuilderIO/agent-native
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.