CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

anatomy

Explain an idea as an interactive isometric machine figure.

60

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./optional-skills/creative/anatomy/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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 operational document: exact commands, signatures, numeric bounds, and a fully validated workflow with explicit pass/fail gates and feedback loops. Its only weaknesses are verbose narrative in the examples section and bundle references (kit/, examples/) that don't resolve in the shipped files. It is among the more actionable skill bodies the rubric's top anchors describe.

DimensionReasoningScore

Conciseness

The core guidance is maximally dense and assumes competence — "Solids, not wireframes", "bevels of 0.4–1.6, grooves inset 3–5 from an edge", no elementary explanation of SVG or isometric projection. The one padded area is the examples section, where narrative vignettes ("A quarter flies into the slot, rolls down the coin chute at the speed a rolling disc reaches on a 30° slope") describe outcomes at length rather than instruct; trimming those to the teaching point of each example would fit anchor 5. Not anchor 3: the vast majority of tokens are actionable instructions, not explanation Claude already knows.

4 / 5

Actionability

Fully executable throughout: copy-paste-ready bash blocks ("cd "$WORK/figures/dial-indicator" && node build.mjs && node build.mjs --light"), exact commands with flags and outputs ("node scripts/lines.mjs page.html --out shots/lines.png"), exact function signatures ("fitProjection(points, width, height, { pad, azimuth })", "A.recorder(P, { order, spring })"), and precise numeric bounds for every craft rule. This matches anchor 5 ("Fully executable; copy-paste ready code or commands; specific examples cover the common cases").

5 / 5

Workflow Clarity

A clearly sequenced 10-step workflow with explicit validation checkpoints and pass conditions: "Run the audit to zero" ("must end `audit passed`, every failing line at 0"), "Run the line check to zero" ("must print `line ends: 0`"), "Read every PNG you make with `vision_analyze`". Feedback loops are explicit ("Iterate until yes", "Fix an interlock in the geometry, never with a key bias"), and step 1 adds time-boxing and user escalation ("when a step runs past twice its share of the estimate, tell the user where it stands"). This is anchor 5's clear sequence + explicit validation + error-recovery loops + checklist (references/verify.md).

5 / 5

Progressive Disclosure

Structure is strong: a dedicated References section signals all eight one-level-deep files with read-when guidance ("Read it before designing", "Read `references/webgl.md` before writing any shader", "Read `references/3d.md` first"), and bulk detail (API, craft recipes, verification) is correctly split out of SKILL.md. However, against the actual bundle the body references paths that are not present — every `kit/*` file in the Setup table (`kit/lathe.mjs`, `kit/tube.mjs`, `kit/audit.mjs`) and all `examples/*` directories — so a reader following the quick-start commands would hit missing files. That gap keeps it below anchor 5; it stays above anchor 3 because the references that do exist are complete, well-signaled, and shallow.

4 / 5

Total

18

/

20

Passed

Description

53%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 short, concrete, and distinctive about what the skill produces, but it omits any trigger guidance and gives no hint of the output formats (HTML, SVG, React) the skill actually delivers. It communicates the core idea efficiently but under-serves skill selection and routing. Adding an explicit use-when clause with natural synonyms would move it substantially.

Suggestions

Add an explicit trigger clause, e.g. "Use when asked to explain a concept, mechanism, or system as a visual figure, diagram, or interactive illustration — isometric machine style."

Mention the concrete outputs (standalone HTML page, .svg file, or React/Next.js components) so the description states what the skill builds, not just what the figure represents.

Include natural synonyms users would say ("diagram", "illustration", "explainer", "isometric", "3D-style cutaway") alongside "machine figure", which is the skill's own vocabulary rather than a user's.

DimensionReasoningScore

Specificity

"Explain an idea as an interactive isometric machine figure" names the domain (isometric machine figures) and one concrete action (explain an idea as such a figure), but lists no deliverables or build actions (standalone HTML, SVG, React components) that the body shows the skill actually performs. It sits at anchor 3 ("Names domain and 1-2 concrete actions, but not comprehensive"): above anchor 2 because the action is concrete rather than generic, below anchor 4 because it does not list several specific actions.

3 / 5

Completeness

The "what" is clear ("Explain an idea as an interactive isometric machine figure"), but there is no "Use when..." clause or equivalent explicit trigger guidance, so completeness is capped at 3 per the judging guidelines. The "when" is only weakly implied by "Explain an idea".

3 / 5

Trigger Term Quality

Natural phrases like "Explain an idea", "interactive", and "isometric" are present, but common variations a user would actually say — "diagram", "illustration", "explainer", "visualization", "SVG" — are absent, and "machine figure" is idiosyncratic vocabulary. This matches anchor 3 ("Some relevant keywords but missing common variations or synonyms"); it is not anchor 4 because keyword coverage is thin for an eight-word description.

3 / 5

Distinctiveness Conflict Risk

"interactive isometric machine figure" carves a clear niche with minimal generic conflict, though the broad opening "Explain an idea" could overlap with closely related diagram skills listed in frontmatter (concept-diagrams, architecture-diagram). This fits anchor 4 ("Mostly distinct; minor overlap risk with closely related skills") better than anchor 5, whose exemplars pair the niche with explicit distinct trigger phrases.

4 / 5

Total

13

/

20

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.

Validation — 13 / 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

NousResearch/hermes-agent

Path

optional-skills/creative/anatomy/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.