CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

iced-rs

Load whenever building or debugging an Iced UI.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/iced-rs/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

90%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.

The body is an exceptionally lean, highly actionable rulebook: every section carries concrete API names, file paths, or code, and the reference structure is well designed around a real index. The only notable weaknesses are the absence of an explicit compile/run validation step in the workflow and the examples/iced_wgpu paths referenced in the body being missing from the actual bundle.

DimensionReasoningScore

Conciseness

The body is dense rules and pointers with no explanation of concepts Claude already knows ("Read the canonical example in `examples/`, never generate 0.14 code from memory"); even the tables are functional indexes rather than padding. This matches anchor 5 — lean, assumes competence, every token earns its place; it is not 4 because there are no identifiable instances of over-explanation to trim.

5 / 5

Actionability

Concrete, executable guidance throughout: exact file paths per need ("examples/custom_widget/src/main.rs"), a runnable lookup command ("ctx7 docs /websites/iced_rs \"<query>\""), a copy-paste theming snippet ("Theme::custom_with_fn(\"My Dark\", palette, |p| theme::palette::Extended::generate(p))"), and a WRONG/RIGHT code pair for the common tree-consistency mistake. This matches anchor 5 — copy-paste ready material covering the common cases.

5 / 5

Workflow Clarity

The 4-step workflow (classify surface → read canonical example → read guide → check failure modes when debugging) is clearly sequenced, with an error-recovery feedback loop ("If geometry updates on a second click, check that the first state change invalidates layout") and a symptom→cause checklist reference. It is not 5 because no explicit build/run verification step (e.g. compile or run against the pinned upstream workspace) appears within the workflow sequence itself; it is not 3 because checkpoints and error-recovery guidance are clearly present, not merely implicit.

4 / 5

Progressive Disclosure

The body is a clear overview with a verified references/INDEX.md hub, well-signaled one-level-deep links (all referenced references/*.md files and section anchors exist), and lookup tables routing each need to a specific file. It is not 5 because the examples/ and iced_wgpu/ paths prominently referenced in the tables do not exist in the bundle, breaking navigation for a large part of the advertised material; it is not 3 because the structure that is present is clearly organized and clearly signaled.

4 / 5

Total

18

/

20

Passed

Description

48%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.

The description has a clear, explicit trigger ('whenever building or debugging an Iced UI') and a well-defined niche, but it never states what the skill actually provides. Its brevity is efficient but leaves both capability coverage and trigger-term synonyms thin.

Suggestions

Add a 'what' clause enumerating concrete capabilities, e.g. "Provides Iced 0.14 API references, surface-selection guides, and canonical examples for building, styling, animating, and debugging Iced UIs. Load whenever building or debugging an Iced UI."

Include natural trigger variations users would say, such as "Rust GUI", "iced-rs", or "iced widgets", to broaden retrieval without adding vagueness.

Mention the pinned version (Iced 0.14) in the description to set expectations and further sharpen distinctiveness against general Rust or GUI skills.

DimensionReasoningScore

Specificity

"building or debugging an Iced UI" names the domain and two concrete actions, but coverage is not comprehensive — styling, animation, custom widgets, and subscriptions are all unmentioned. It matches anchor 3 (domain plus 1-2 concrete actions); it is not 4 because only two generic verbs are listed, and not 2 because the actions named are concrete rather than minimal or generic.

3 / 5

Completeness

"Load whenever building or debugging an Iced UI" provides an explicit 'when' but states no 'what' — the skill's capabilities (API references, guides, examples, 0.14 patterns) are never described. This is structurally identical to anchor 2's "Use when working with documents" (only 'when' present without 'what'); it is not 3 because anchor 3 requires a clear 'what', which is the inverse of what is here.

2 / 5

Trigger Term Quality

The core natural phrase a user would say ("Iced UI", "building", "debugging") is present, but common variations and synonyms such as "Rust GUI", "iced-rs", or "iced widgets" are missing. This fits anchor 3 (some relevant keywords, missing variations); not 4 because keyword coverage is thin, not 2 because the primary natural trigger term is included.

3 / 5

Distinctiveness Conflict Risk

"an Iced UI" targets a specific named Rust GUI framework, giving a clear niche with distinct triggers and minimal conflict risk with other skills. This matches anchor 5; it is not 4 because there is no meaningful overlap risk with closely related skills.

5 / 5

Total

13

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

vanillagreencom/kendex

Path

.agents/skills/iced-rs/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.