CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

system-atlas

Build explorable isometric architecture atlases as HTML.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

85%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 content is an exemplary skill body: a tightly written, ordered procedure with real validation checkpoints, concrete commands and formats, and clean separation of all heavy material into existing, clearly signaled one-level-deep bundle files. The only flaws are minor: a few compressible asides and a small node/bun inconsistency between the body and the example data file.

DimensionReasoningScore

Conciseness

The body is dense and telegraphic — "Letters on boxes are not enough", "Never delete a question — resolve or mark it dropped" — and assumes Claude's competence, explaining nothing Claude already knows. A few earned-but-trimmable asides ("(Committing the whole set once produced a 3,900-line docs PR and four review rounds...)", the doctype/quirks-mode pitfall rationale) keep it just short of the leanest anchor; not 3 because there is no genuinely unnecessary explanation.

4 / 5

Actionability

Concrete, executable guidance throughout: a copy-paste bash block ("cp <skill>/assets/{template.html,build.mjs} <atlas home>/atlas/", "node <atlas home>/atlas/build.mjs"), an exact question format ("Q-<code><n>" with open/resolved/routed states), and specific verification commands ("new Function(js)", ~1280x800). Minor gaps: the data schema is delegated entirely to assets/data.example.mjs, and that example file says "bun" where the body says "node" — a small inconsistency that could confuse.

4 / 5

Workflow Clarity

A nine-step numbered Procedure with explicit ordering ("Follow the order — each step was earned by a correction") plus a dedicated Verification section that is a real validation checklist: build exits 0, syntax-check the built script, browser checks of first/middle/last chapter, click-to-pin and packet-inspect assertions. Feedback loops are explicit ("After each round: rebuild, republish, update memory"; sweep every file after a rejection). Clear sequence, explicit validation steps, feedback loops for error recovery — the top anchor.

5 / 5

Progressive Disclosure

Scored against the actual bundle: the heavy material — the 38k template.html, build.mjs, the full data schema ("Every field of the data file is documented in assets/data.example.mjs"), the visual rules ("read references/design-language.md"), and the process record ("table in references/process-and-lessons.md") — is split into real one-level-deep files, all of which exist in the bundle and are clearly signaled from the body. The 89-line SKILL.md stays an overview with a Quick Reference table; nothing inline belongs in a separate file.

5 / 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, third-person, and names a distinctive niche, but it answers only the 'what'. It lacks a 'Use when...' trigger clause and the natural phrases users would say when they need this skill, so it under-sells the skill's full capability set and risks not firing on relevant requests.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases users would say, e.g. "Use when someone wants to make an atlas, map the system, make the architecture explorable, or visualize a codebase/agent/pipeline to discuss it."

List the key capabilities beyond building the HTML view: the interactive isometric map with progressive disclosure, the generated text twin (SYSTEM.md), question tracking across feedback rounds, and the rebuild/republish update loop.

Include common synonyms of the domain — 'architecture map', 'architecture diagram', 'interactive system diagram', 'explore the architecture' — so the description matches the varied ways users phrase the need.

DimensionReasoningScore

Specificity

The description names a concrete domain ("isometric architecture atlases") and one concrete action ("Build ... as HTML"), but stops at a single action — capabilities the body documents (progressive-disclosure chapters, question tracking, the generated text twin, the update loop) are absent. This matches the 'names domain and 1-2 concrete actions, but not comprehensive' anchor; it is not 4 because several specific actions are missing, and not 2 because the action named is concrete rather than generic.

3 / 5

Completeness

It has a clear 'what' ("Build explorable isometric architecture atlases as HTML") but no 'Use when...' clause or equivalent explicit trigger guidance — the judging guideline explicitly caps completeness at 3 for this. Not 4 because the 'when' is entirely missing rather than merely implicit.

3 / 5

Trigger Term Quality

It includes relevant keywords ("architecture", "isometric", "explorable", "atlases", "HTML") but misses the natural phrases a user would actually say, which the body itself lists ("map the system", "make the architecture explorable", "visualize the codebase/agent/pipeline", "architecture diagram"). Some relevant keywords, missing common variations and synonyms — anchor 3, not 4 because several natural trigger phrases are absent.

3 / 5

Distinctiveness Conflict Risk

"Isometric architecture atlases" is a clear niche with distinct triggers (atlas, isometric, explorable), and the body's Doesn't section carves out static-diagram territory. Only minor overlap risk with closely related diagramming skills (architecture-diagram, excalidraw), matching 'mostly distinct; minor overlap risk with closely related skills'; not 5 because without a use-when clause, an 'architecture diagram' request could plausibly route here.

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/system-atlas/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.