CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

show-me

Help the user understand the current topic visually with concise diagrams, code-shape sketches, and focused HTML artifacts.

Quality

78%

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 ./.agents/skills/show-me/SKILL.md

The canonical home for this skill is show-me in humanlayer/skills

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 a lean, example-driven playbook that teaches each visualization format by showing it, with explicit selection criteria and placement guidance, and assumes Claude's competence throughout. Its only weaknesses are minor: a placeholder in the open command, no concrete HTML artifact example, and slightly thin heading structure.

DimensionReasoningScore

Conciseness

Prose is minimal and directive ("Skip the preamble and keep prose brief. Pick the smallest view that makes the key point clear.") and every example demonstrates a distinct output pattern with no padding or explanation of concepts Claude already knows; each token earns its place.

5 / 5

Actionability

Concrete, imitable examples cover each visualization type (pseudocode, call tree, component tree, file tree, Mermaid, four diff shapes, full code block) plus an executable open command "Bash(open path/to/show-me-{description}.html)"; minor gaps are the placeholder filename and the absence of any HTML starter example despite an entire bullet devoted to HTML artifacts.

4 / 5

Workflow Clarity

This is a simple single-purpose skill and the action is unambiguous: pick the smallest view, match the format to the topic with explicit selection criteria ("Use `diff` when the point is what changes and the surrounding shape already exists", "Show the whole block when most of it is new"), place each visual next to its text, and open HTML artifacts via Bash; no destructive or batch operations, so no validation cap applies.

5 / 5

Progressive Disclosure

Well-organized bullet structure with no nested references (none are needed at this size); minor gaps keep it from a 5 — the lone heading "### guidance" is an h3 with no parent h2, and the body is ~120 lines so the under-50-line simple-skill exception does not strictly apply.

4 / 5

Total

18

/

20

Passed

Description

58%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 clearly states what the skill produces with three concrete output types, but entirely lacks a 'Use when...' trigger clause and natural user-facing trigger phrases. It is mostly distinct from other skills though it leans on some invented vocabulary like "code-shape sketches".

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to see, visualize, or diagram how something works, or says 'show me' about the current topic."

Include natural trigger terms and synonyms users would actually say ("show me", "visualize", "diagram", "how it works", "what changes") alongside the output-type list.

Replace invented jargon like "code-shape sketches" with vocabulary a user would naturally use (e.g. "call trees", "file trees", "diffs").

DimensionReasoningScore

Specificity

"concise diagrams, code-shape sketches, and focused HTML artifacts" names the domain (visual understanding) and three concrete output types, matching the several-specific-actions anchor; not a 5 because call trees, diffs, and Mermaid — formats the body actually teaches — are not covered.

4 / 5

Completeness

There is a clear 'what' ("Help the user understand the current topic visually with concise diagrams, code-shape sketches, and focused HTML artifacts") but no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

"visually" and "diagrams" are relevant keywords, but common natural phrases users would say ("show me", "visualize", "how it works", "diagram") and their synonyms are missing, and "code-shape sketches" is invented jargon rather than a user phrase.

3 / 5

Distinctiveness Conflict Risk

"understand the current topic visually" with distinct output types (diagrams, code-shape sketches, HTML artifacts) carves a mostly distinct explanation niche; minor overlap risk remains with charting/dataviz and general artifact-creation skills, so it is not a 5.

4 / 5

Total

14

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

withcoral/coral

Path

.agents/skills/show-me/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.