CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

isometric-explainer

Builds an interactive isometric machine page. Each station of one invented machine stands for one step of a process. A pure, tested state model drives the motion, the readouts and the copy. The page has controls and a verification loop. Trigger phrases: "isometric explainer", "machine explainer", "explain this as a machine", "interactive isometric figure", "explorable explainer", "show how it works inside".

Quality

95%

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

The canonical home for this skill is isometric-explainer in rohitg00/ai-engineering-from-scratch

SKILL.md
Quality
Evals
Security

Quality

Content

100%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.

An exemplary skill body: a lean, telegraphic overview with exact constants and runnable commands, a 12-step method ending in explicit verification, and a pre-finish validation checklist with feedback loops. Detail is appropriately pushed into six real, one-level-deep reference files that are clearly cataloged in the Files section; the only unverifiable items are the templates/ and kit/ paths, which are not present in the provided evaluation bundle but are clearly signaled and described.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence: no explanations of known concepts, no padded sections, and every rule carries a specific non-obvious value ("Elevation is 30 degrees", "stiffness 64, damping 14.2 and a 0.04 s stagger", "Clamp the frame step to 1/20 s"). Anchor 4 would require trimmable over-explanation, and none is present.

5 / 5

Actionability

Fully executable guidance: runnable commands ("node templates/build.mjs", "node --test templates/model.test.mjs"), named kit functions ("inkSolid", "silhouetteSvg", "castShadowSvg", "glassSvg", "pillSvg", "wobbleFilter"), exact constants, and concrete URL behaviors ("reads ?labels=0"). Per the code-vs-instruction scoring note, the absence of inline code blocks is not penalized because a working starter template is provided and every instruction is concrete.

5 / 5

Workflow Clarity

The Method section gives 12 clearly sequenced steps, step 12 is an explicit headless-browser verification step, and "Check before you finish" is a 16-item validation checklist with feedback loops ("Rebuilding produces no diff", "scenario sweep runs every config to the end with zero console errors", "line-end check reports zero loose ends"). This matches anchor 5's sequence-plus-validation-plus-checklist pattern.

5 / 5

Progressive Disclosure

The body is a true overview: a 12-step method and rules inline, with all detail split into six one-level-deep reference files (references/concept.md, state-model.md, geometry.md, colour-and-ink.md, live.md, verify.md) that all exist in the bundle and are each described with their scope in the Files section. Cross-references between reference files are peer-level, not nested, so navigation stays one level deep.

5 / 5

Total

20

/

20

Passed

Description

91%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 in third-person voice: it states what the skill builds, how it works (model-driven), and when to use it via six explicit trigger phrases. The trigger coverage is comprehensive for its niche; the only weaknesses are slightly abstract action phrasing and a couple of broad trigger phrases with minor overlap risk against sibling visualization skills.

DimensionReasoningScore

Specificity

Lists several concrete actions — "Builds an interactive isometric machine page", "A pure, tested state model drives the motion, the readouts and the copy", "The page has controls and a verification loop" — but the actions are slightly more abstract than anchor 5's fully tangible action lists. Not 3 because it names more than 1-2 concrete actions with a clear domain; not 5 because coverage is not fully comprehensive in tangible, verbatim-executable terms.

4 / 5

Completeness

Explicitly answers both questions: the "what" ("Builds an interactive isometric machine page", "A pure, tested state model drives the motion, the readouts and the copy") and the "when" ("Trigger phrases: ..." listing six concrete triggers). This matches anchor 5's pattern of clear what-and-when with concrete trigger phrases; a 4 would require the when to be less explicit.

5 / 5

Trigger Term Quality

Six natural trigger phrases — "isometric explainer", "machine explainer", "explain this as a machine", "interactive isometric figure", "explorable explainer", "show how it works inside" — comprehensively cover the synonyms a user would plausibly say for this niche. Anchor 4 would require missing natural variations, and none are apparent for this domain.

5 / 5

Distinctiveness Conflict Risk

The niche is clear and the core triggers ("isometric explainer", "machine explainer", "interactive isometric figure") are distinct, but broader phrases like "explorable explainer" and "show how it works inside" could overlap with general interactive-explainer or visualization skills. Mostly distinct with minor overlap risk against closely related skills fits anchor 4; anchor 5 would require minimal conflict risk across all triggers.

4 / 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

frontmatter_unknown_keys

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

Warning

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

14

/

16

Passed

Repository

rohitg00/ai-engineering-from-scratch

Path

.claude/skills/isometric-explainer/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.