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

SKILL.md
Quality
Evals
Security

Quality

Content

96%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 unusually disciplined skill document: a tight when-to-use / when-not-to-use pair, a 12-step method with exact constants and commands, rule sections that read as testable assertions, and a verification checklist with feedback loops. Its only real defect is bundle completeness — the templates and kit it directs the reader to run and reuse are referenced but not present in the bundle, which keeps progressive disclosure one notch below the top.

Suggestions

Ship the `templates/` and `kit/` files (or note in the Files section how they are obtained), since the body instructs the reader to run `node templates/build.mjs` and to use `kit/ink.mjs` functions but neither directory exists in the bundle.

Move or footnote the repo-specific pointer to `scripts/decompiler-machine/` and `site/test_decompiler_machine.js` — these paths exist only inside the source repo and add dead navigation for any reader outside it.

Consider a one-line inline signature for `simulate(config)`'s event shape (or a pointer to the exact section of `references/state-model.md`) so the model-contract step can be started without opening the reference.

DimensionReasoningScore

Conciseness

Every line carries project-specific instruction or an exact value the model could not invent ("Elevation is 30 degrees", "spring with stiffness 64, damping 14.2 and a 0.04 s stagger", "Buttons are at least 44 px tall"); there is no explanation of concepts Claude already knows and no padding. The single illustrative example ("a request card moves on a carriage, a probe drops, and a press stamps the card") earns its place.

5 / 5

Actionability

Guidance is executable throughout: copy-paste commands ("Run `node templates/build.mjs`", "Run `node --test templates/model.test.mjs`"), named APIs (`simulate(config)`, `inkSolid`, `wobbleFilter`), a tier-approval table, and concrete config behaviors like "reads `?labels=0`". Per the rubric's code-vs-instruction note, an instruction-only skill with this level of concrete guidance meets the top anchor.

5 / 5

Workflow Clarity

The 12-step Method is sequenced in dependency order (model and tests before any geometry), with an explicit test-first checkpoint ("Test it before any geometry"), a dedicated headless verification step with screenshots and a zero-console-error scenario sweep, and a 15-item "Check before you finish" checklist. This matches the anchor-5 pattern of clear sequence, explicit validation, and checklists.

5 / 5

Progressive Disclosure

The body is a genuine overview with well-signaled, one-level-deep references — all six `references/*.md` files exist and each is summarized with its scope in the Files section. It falls short of anchor 5 because 9 of the 15 files listed in the Files section (`templates/model.mjs`, `templates/build.mjs`, `kit/iso-kit.mjs`, `kit/ink.mjs`, etc.) are absent from the bundle as shipped, leaving key instructions like "Run `node templates/build.mjs`" pointing at files the reader cannot open; still clearly above anchor 3 since references are clearly signaled and nothing that belongs in a reference is inlined.

4 / 5

Total

19

/

20

Passed

Description

95%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 is a strong example: third-person voice, concrete about the artifact and its state-model-driven design, and it pairs a clear what with an explicit list of natural trigger phrases. The only mild weakness is that it states capabilities as properties of one built artifact rather than as a list of discrete actions, leaving specificity just short of the top anchor.

DimensionReasoningScore

Specificity

Names the concrete domain and several specific capabilities ("A pure, tested state model drives the motion, the readouts and the copy", "controls and a verification loop") beyond the 1-2 actions of anchor 3, but it describes one artifact's properties rather than the comprehensive list of discrete actions exemplified by anchor 5.

4 / 5

Completeness

Explicitly answers "what" (builds an interactive isometric machine page where stations stand for process steps, driven by a tested state model) and "when" via concrete trigger phrases, matching the anchor-5 pattern of a clear what plus explicit trigger guidance. The "Trigger phrases:" clause is equivalent explicit trigger guidance, so the missing-'Use when' cap does not apply.

5 / 5

Trigger Term Quality

Six natural, varied trigger phrases including synonyms ("isometric explainer", "machine explainer", "explain this as a machine", "interactive isometric figure", "explorable explainer", "show how it works inside") give comprehensive coverage of how a user would naturally request this skill. Not anchor 4, because no dominant common phrasing for this niche is missing.

5 / 5

Distinctiveness Conflict Risk

A clear niche (isometric machine explainers for processes) with distinctive triggers like "isometric explainer" and "explain this as a machine"; minimal risk of triggering for a generic diagram or document skill. Above anchor 4 because the triggers are niche-specific rather than merely mostly distinct.

5 / 5

Total

19

/

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

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.