CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

toy

Build a world the human drives until how a thing behaves is intuitive. Use when the user needs to hold how something behaves and reading has not made it intuitive.

Quality

77%

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 ./hold/skills/toy/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

80%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 exceptionally concise and well-structured with concrete patterns and a clear default medium, but its workflow is presented as principles rather than an explicitly sequenced process with validation checkpoints.

Suggestions

Add a short explicit build sequence (e.g., 1. pick one behavior 2. reveal hidden state 3. wire prediction slots 4. ship one HTML page 5. step out) to make the workflow sequenced.

Include a minimal copy-paste HTML scaffold so the concrete default medium is executable, not just described.

Make the validation/stop checkpoint explicit as a step (e.g., 'Stop when the human's predictions land — they report it, you do not score it').

DimensionReasoningScore

Conciseness

The body is lean and terse with every sentence earning its place and no padding or explanation of concepts Claude already knows, matching 'lean and efficient; assumes Claude's competence'.

5 / 5

Actionability

Provides concrete guidance — a specific filename format (`YYYY-MM-DD-<slug>.html`), the `open <path>` command, and four concrete pattern/case pairs (regex engine, rename over forty files, B-tree, rate limiter) — but lacks an executable code scaffold, keeping it just below fully copy-paste ready; not a 3 because the guidance is concrete rather than pseudocode.

4 / 5

Workflow Clarity

Content is organized thematically (build constraints, reveal hidden state, prediction setup, default medium, stop/boundary routing) but there is no explicit numbered sequence and validation checkpoints are only implicit ('Held is when their predictions land'); not a 4 because checkpoints are not made explicit.

3 / 5

Progressive Disclosure

A self-contained skill under 50 lines with no bundle files and well-organized thematic sections plus a routing table; per the under-50-lines/no-external-references exception this scores 5, and there are no nested references.

5 / 5

Total

17

/

20

Passed

Description

62%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 explicitly covers both what the skill does and when to use it, with a reasonably distinct niche, but its action vocabulary and natural trigger terms are limited and lean on the skill's own jargon.

Suggestions

Add a second concrete action verb beyond 'Build a world' (e.g., 'Scrubbable, single-behavior HTML playgrounds') to raise specificity.

Broaden the trigger with natural user phrasings and synonyms (e.g., 'when the user says they still don't get how it works after reading the docs or staring at the code').

Replace the idiosyncratic 'hold how something behaves' with phrasings a user would actually say.

DimensionReasoningScore

Specificity

Names the domain and one concrete action ("Build a world the human drives") but offers no further concrete actions, matching 'names domain and 1-2 concrete actions, not comprehensive'; it is not a 2 because a concrete artifact/action is named, and not a 4 because coverage is thin.

3 / 5

Completeness

Explicitly states both what ("Build a world the human drives...") and when ("Use when the user needs to hold how something behaves and reading has not made it intuitive"), satisfying the Use-when requirement; not a 5 because the trigger could use more concrete, varied phrasing.

4 / 5

Trigger Term Quality

Contains some natural phrases ("how something behaves", "reading has not made it intuitive") but lacks common variations or synonyms, and "hold how something behaves" is skill-specific jargon rather than a phrase users naturally say.

3 / 5

Distinctiveness Conflict Risk

Targets a clear niche (interactive toy worlds for building behavioral intuition when reading fails) that is mostly distinct with only minor overlap risk against general demo/playground skills; not a 5 because 'build a world' could be conflated with general UI/demo skills.

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

saadshahd/moo.md

Path

hold/skills/toy/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.