CtrlK
BlogDocsLog inGet started
Tessl Logo

build-review-interface

Build a custom browser-based annotation interface tailored to your data for reviewing LLM traces and collecting structured feedback. Use when you need to build an annotation tool, review traces, or collect human labels.

85

Quality

81%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Discovery

89%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a solid description that clearly communicates when to use the skill and covers relevant trigger terms. The main weakness is that the capability description could be more specific about the concrete actions the skill enables (e.g., specific annotation features, export formats, or configuration options).

Suggestions

Add more specific concrete actions like 'create labeling schemas', 'configure multi-annotator workflows', or 'export labeled datasets' to improve specificity

DimensionReasoningScore

Specificity

Names the domain (browser-based annotation interface) and some actions (reviewing LLM traces, collecting structured feedback), but lacks comprehensive specific actions like 'create labeling schemas', 'export annotations', or 'configure review workflows'.

2 / 3

Completeness

Clearly answers both what ('Build a custom browser-based annotation interface...for reviewing LLM traces and collecting structured feedback') and when ('Use when you need to build an annotation tool, review traces, or collect human labels') with explicit triggers.

3 / 3

Trigger Term Quality

Good coverage of natural terms users would say: 'annotation tool', 'review traces', 'collect human labels', 'LLM traces', 'structured feedback'. These are terms users would naturally use when needing this capability.

3 / 3

Distinctiveness Conflict Risk

Clear niche with distinct triggers around 'annotation', 'LLM traces', and 'human labels'. Unlikely to conflict with general web development or data processing skills due to the specific domain focus.

3 / 3

Total

11

/

12

Passed

Implementation

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill provides comprehensive, well-organized guidance for building an annotation interface with excellent conciseness and structure. The main weaknesses are the lack of executable code examples (HTML/CSS/JS snippets for the interface, Playwright test code) and an implicit rather than explicit build workflow. The content tells Claude what to build but could better show how with concrete code.

Suggestions

Add a minimal executable HTML/JS code example showing the basic interface structure with Pass/Fail buttons and trace display

Include a concrete Playwright test code snippet demonstrating at least one functional test case

Add an explicit numbered build workflow (e.g., 1. Create HTML structure, 2. Add data loading, 3. Implement navigation, 4. Add persistence, 5. Test with Playwright)

DimensionReasoningScore

Conciseness

The content is lean and efficient, providing specific guidance without explaining concepts Claude already knows. Every section delivers actionable information without padding or unnecessary context.

3 / 3

Actionability

Provides concrete guidance with specific features, keyboard shortcuts, and checklists, but lacks executable code examples. The Playwright testing section describes what to test but doesn't provide copy-paste ready test code.

2 / 3

Workflow Clarity

The overall build process is implied rather than explicitly sequenced. While individual sections are clear, there's no explicit workflow for building the interface step-by-step, and the testing section lacks validation checkpoints for catching errors during development.

2 / 3

Progressive Disclosure

Content is well-organized with clear section headers, appropriate use of bullet points, and logical grouping. The checklist format and collapsible content guidance demonstrate good structure for a self-contained skill file.

3 / 3

Total

10

/

12

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
hamelsmu/evals-skills
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.