CtrlK
BlogDocsLog inGet started
Tessl Logo

ce-prototype

Build a throwaway prototype to answer how something should work, feel, or read. Use when committing the wrong answer would be expensive to unravel and a cheap sketch cannot settle it. Not a rough visual probe during brainstorming, not for deciding what to build, not polishing a feature that already works, not implementing the real thing.

64

Quality

76%

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 ./skills/ce-prototype/SKILL.md

The canonical home for this skill is ce-prototype in EveryInc/compound-engineering-plugin

SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

A well-engineered instruction body: dense, purposeful prose with concrete commands and decision gates, delegating detail to a real, correctly-gated reference bundle that is one level deep. The prose density and inline reliance on references for executable detail are the only things keeping conciseness and actionability from the top anchors.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence, explains no known concepts, and ties nearly every rule to a failure mode ("Do not fake the dimension being tested", "Do not start a preview or invent how it should feel"); a few guardrail sentences and the dense conditional prose could still be tightened, keeping it below the lean anchor 5.

4 / 5

Actionability

Concrete guidance is present — the exact probe "git -C <repo root> check-ignore -q .context/compound-engineering/" with the trailing-slash requirement, explicit directory patterns, and exact invocation renderings — but key execution detail (server commands, sizing, yields) is delegated to references rather than executable inline, leaving minor gaps.

4 / 5

Workflow Clarity

The scope → build → keep decisions → apply/continue sequence is clear with checkpoints (stop when no human is present, probe gitignore before resolving the root, "Do not build until authorized", report files you cannot restore); validation of the restored overlay tree is left somewhat implicit, holding it below the explicit-feedback-loop anchor 5.

4 / 5

Progressive Disclosure

Verified against the actual bundle: all six references cited in the body (scoping.md, build.md, preview.md, annotation-loop.md, craft-floor.md, write-back.md) exist, are one level deep, and each is gated to the point in the flow where it is needed; scripts/light-webserver.js and the annotate assets sit behind those references, giving a clear overview with easy navigation.

5 / 5

Total

17

/

20

Passed

Description

73%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.

A strong description: it states a clear purpose, gives an explicit use condition, and fences itself off from adjacent skills with explicit not-for clauses. The main weakness is capability coverage — only one action is named — and a few natural synonyms (mock, mockup, wireframe) are absent.

DimensionReasoningScore

Specificity

"Build a throwaway prototype to answer how something should work, feel, or read" names the domain and one concrete action, but the description does not enumerate multiple capabilities (e.g., apply decisions, hand off, run an annotation loop), matching the '1-2 concrete actions, not comprehensive' anchor rather than the 'several specific actions' anchor.

3 / 5

Completeness

Both what ("Build a throwaway prototype to answer how something should work, feel, or read") and when ("Use when committing the wrong answer would be expensive to unravel and a cheap sketch cannot settle it") are explicit, plus explicit exclusions; the when clause is condition-based rather than concrete user trigger phrases, so it is not a 5.

4 / 5

Trigger Term Quality

Natural phrases like "throwaway prototype", "how something should work, feel, or read", "a cheap sketch", and "polishing a feature that already works" give good coverage, but common synonyms a user might say (mock, mockup, spike, wireframe) are missing, so it does not reach comprehensive coverage.

4 / 5

Distinctiveness Conflict Risk

The exclusion chain "Not a rough visual probe during brainstorming, not for deciding what to build, not polishing a feature that already works, not implementing the real thing" carves out a clear niche against neighboring brainstorm/plan/implementation skills, giving minimal conflict risk.

5 / 5

Total

16

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
crdant/compound-engineering-plugin
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.