CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

platform-seams

Apply Epicenter's one-build rule, where a capability package decides at run time whether the page is in a Tauri window and loads its desktop implementation when it connects or first acts, and apps branch on what a capability offers. Use when adding or changing a desktop implementation, a capability only some surfaces have, a view only they show, or the desktop shell's build.

Quality

86%

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

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 dense, high-quality body: no wasted tokens, concrete code and file paths throughout, an explicit test-based validation gate, and a well-signaled anti-patterns section. The only real gap is the absence of a worked example for authoring a capability package's runtime choice.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — it never explains what Tauri, localStorage, or export conditions are, and compresses per-package behavior into a six-row table instead of prose. Every token carries project-specific fact, matching the 5 anchor; there is no over-explanation to trim as the 4 anchor would require.

5 / 5

Actionability

Concrete and executable throughout: real code ("{#if folder.reveal === null}<RepositoryChrome />{:else}<FolderChrome />{/if}"), real APIs ("isTauri() from @tauri-apps/api/core", "mock.module('@tauri-apps/api/core', ...)"), and real paths ("scripts/first-load.test.ts", "src-tauri/tauri.conf.json" with exact config keys). It falls short of 5 only because the core task of authoring a new capability's two-step choice has no copy-paste code example inside a package.

4 / 5

Workflow Clarity

The two-step sequence ("Presence, synchronously" then "The desktop implementation, in its asynchronous step") is explicit, and "scripts/first-load.test.ts" serves as a validation gate with a fix loop ("Add a new desktop module's name to its DESKTOP patterns"). It sits below 5 because this is a conventions skill rather than a multi-step procedure, and the checkpoints for adding a new capability remain implicit.

4 / 5

Progressive Disclosure

Well-organized sections with clearly signaled, one-level-deep links to ADRs (0778, 0780, 0781, 0787) and no nested reference chains. At ~95 lines with inlined test-condition and shell-build detail, some material could arguably live in bundle reference files, which is the minor organization gap that keeps it at the 4 anchor rather than 5.

4 / 5

Total

17

/

20

Passed

Description

87%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 description: it states the rule concretely, uses third person, and carries an explicit and specific "Use when" trigger clause covering the main entry points. The only weakness is that trigger coverage, while good, misses a few natural synonyms.

DimensionReasoningScore

Specificity

Names several concrete actions — "decides at run time whether the page is in a Tauri window", "loads its desktop implementation when it connects or first acts", "apps branch on what a capability offers" — with only minor coverage gaps. It stops short of the 5 anchor because it frames a single rule rather than comprehensively enumerating the skill's concrete actions.

4 / 5

Completeness

Explicitly answers both questions: the "what" ("a capability package decides at run time... and apps branch on what a capability offers") and a concrete "Use when adding or changing a desktop implementation, a capability only some surfaces have, a view only they show, or the desktop shell's build". Written in third-person imperative voice, matching the 5 anchor exactly.

5 / 5

Trigger Term Quality

Includes natural developer phrasing such as "adding or changing a desktop implementation", "the desktop shell's build", and "Tauri window" that a user on this project would plausibly say. A few natural variants (e.g. "desktop app", "native") are missing, keeping it below the comprehensive-synonym coverage of the 5 anchor.

4 / 5

Distinctiveness Conflict Risk

"Epicenter's one-build rule" and the Tauri/capability-package framing carve out a clear niche with distinct triggers, making conflict with other skills unlikely. The overly generic language of the lower anchors is entirely absent.

5 / 5

Total

18

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 4 suspicious

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

16

Passed

Repository

EpicenterHQ/epicenter

Path

.agents/skills/platform-seams/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.