CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

prototype

Build multiple genuinely different versions of a UI piece you describe, rendered behind a visual picker so you can flip through them live and promote the one that feels right. Only runs when explicitly invoked; it does not trigger on its own.

Quality

71%

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/prototype/SKILL.md

The canonical home for this skill is prototype in emilkowalski/skills

SKILL.md
Quality
Evals
Security

Quality

Content

63%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 well-sequenced, mostly lean multi-phase workflow with explicit verification gates and checklists, but its actionability and progressive disclosure are undercut by the missing PICKER.md file that the core picker mechanic depends on.

Suggestions

Provide the referenced PICKER.md (or inline its markup/styles/keyboard wiring) so the 'copy verbatim' instruction is actually fulfillable — this is the single biggest lift for both actionability and progressive disclosure.

Make the Phase 5 verification loop explicit: 'if any variant fails to render or the console reports errors, fix and re-verify before showing the user' to push workflow clarity toward 5.

Trim the slightly philosophical Operating Posture / craft-bar passages to the essential directives to move conciseness from 4 to 5.

DimensionReasoningScore

Conciseness

The body is lean and directive with no padding about what a UI is or how libraries work; the rationale passages (Operating Posture, the craft-bar paragraph) earn their place by driving behavior but are slightly more than minimal, so it is efficient with minor trim potential rather than every-token-essential at 5.

4 / 5

Actionability

Guidance is concrete and specific (named phases, '/prototypes/<slug>', 3-5 variants, naming like 'Quiet' not 'Option A', a hand-off table template), but the core mechanic — the picker markup to 'copy verbatim' — lives in PICKER.md, which is referenced yet absent from the bundle, leaving a key executable detail missing.

3 / 5

Workflow Clarity

Phases 1-6 are clearly sequenced with an explicit verification gate in Phase 5 ('flip through all of them yourself before showing the user') and completion-criterion checklists, but the validate->fix->retry feedback loop on console errors is implied rather than spelled out, keeping it just below 5.

4 / 5

Progressive Disclosure

Structure is well-organized with clear sections and a clearly signaled one-level reference to PICKER.md ('load it now and build exactly that'), but no bundle files exist and PICKER.md is missing, so the signaled reference leads to a dead end — the picker detail that should be in a separate file is neither inlined nor reachable.

3 / 5

Total

14

/

20

Passed

Description

66%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 conveys what the skill does with several concrete actions and a distinct niche, but it lacks an explicit 'Use when...' trigger clause, relying instead on an invocation constraint that caps completeness at 3.

Suggestions

Add an explicit 'Use when...' trigger clause naming the situations that call for this skill (e.g., 'Use when the user wants to explore several distinct directions for a single UI piece before committing').

Surface natural synonyms users actually say — 'prototype', 'variants', 'alternatives', 'compare options' — to broaden trigger-term coverage toward 5.

Tighten the abstract phrases ('feels right', 'genuinely different') into more concrete capability language to lift specificity from 4 to 5.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'Build multiple genuinely different versions', 'rendered behind a visual picker', 'flip through them live', 'promote the one that feels right' — with only minor abstraction in phrases like 'feels right' and 'genuinely different', so it sits above the 3-anchor but not fully comprehensive at 5.

4 / 5

Completeness

The 'what' is clearly stated, but the 'when' is only the constraint 'Only runs when explicitly invoked; it does not trigger on its own' — this is not an explicit 'Use when...' trigger clause, so per the rubric completeness caps at 3.

3 / 5

Trigger Term Quality

Natural phrases users would say are present ('versions of a UI piece you describe', 'flip through them live', 'promote'), giving good coverage, though common synonyms like 'prototype', 'variants', 'alternatives', or 'compare' are missing, which keeps it just below 5.

4 / 5

Distinctiveness Conflict Risk

The 'visual picker to flip through versions' niche is distinct and the explicit 'does not trigger on its own' minimizes auto-conflict, but there is residual overlap risk with general UI-building skills, placing it just below a 5.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 missing

Warning

Total

15

/

16

Passed

Repository

spree/spree

Path

.agents/skills/prototype/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.