CtrlK
BlogDocsLog inGet started
Tessl Logo

ce-polish

Polish a working feature through user-directed live browser feedback. Use when a functional feature needs focused UX refinement before shipping.

68

Quality

82%

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

SKILL.md
Quality
Evals
Security

Quality

Content

86%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-structured, lean instruction skill whose body is an overview delegating concrete execution to a verified one-level-deep reference and bundled scripts, with a clear sequenced workflow and explicit checkpoints. The only gap is that executable commands live in the reference rather than the body itself.

DimensionReasoningScore

Conciseness

The ~15-line body is lean, assumes Claude's competence (no explaining dev servers or hot reload), and every line carries an instruction, matching the lean-and-efficient anchor with no real padding to trim.

5 / 5

Actionability

Guidance is concrete and executable via precise pointers to run.md, named bundled scripts, and the ce-commit invocation, but the body itself is not copy-paste ready because the executable commands are deliberately delegated to the reference.

4 / 5

Workflow Clarity

A clear four-step sequence with checkpoints (reachability gate and the done/blocked close condition), but the validation details live in the delegated reference rather than inline, leaving minor gaps versus the fully-inline anchor.

4 / 5

Progressive Disclosure

The body is a concise overview that delegates detail one level deep to a real references/run.md, which in turn points to real recipe files and scripts; navigation is clearly signaled and content is appropriately split.

5 / 5

Total

18

/

20

Passed

Description

78%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 concise, third-person description that cleanly states both capability and an explicit 'Use when' trigger, with good natural keyword coverage and a distinct niche. Its main limit is specificity: it describes one refinement action rather than enumerating several concrete actions.

DimensionReasoningScore

Specificity

Names the domain ('working feature', 'UX refinement') with 1-2 concrete actions ('Polish', 'live browser feedback') but does not list several distinct concrete actions, matching the anchor for domain-plus-1-2-actions rather than the multi-action anchor above.

3 / 5

Completeness

It explicitly answers both what ('Polish a working feature through user-directed live browser feedback') and when via a concrete 'Use when a functional feature needs focused UX refinement before shipping' trigger clause.

5 / 5

Trigger Term Quality

Good keyword coverage with natural phrases a user would say ('polish', 'working feature', 'UX refinement', 'before shipping'), but it lacks common synonyms and variations needed for the comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

The live-browser-feedback polish niche is mostly distinct with only minor overlap risk against general front-end styling or QA skills, falling just short of the minimal-conflict anchor.

4 / 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.

Validation15 / 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
EveryInc/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.