evals-context

Provides context about the Roo Code evals system structure in this monorepo. Use when tasks mention "evals", "evaluation", "eval runs", "eval exercises", or working with the evals infrastructure. Helps distinguish between the evals execution system (packages/evals, apps/web-evals) and the public website evals display page (apps/web-roo-code/src/app/evals).

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./bundled/skills/evals-context/SKILL.md

Quality

Content

65%

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

A well-organized context skill with concrete commands, specific file paths, and clear sectioning. It is held back by redundant directory listings across sections, a missing validation step in the database-migration workflow, and a monolithic single-file structure with no progressive disclosure into bundle references.

Suggestions

De-duplicate file listings: list each file path once (either in the directory trees or in 'Common Tasks Quick Reference', not both) to tighten the token budget.

Add a validation/verification checkpoint to the 'Database Schema Changes' workflow (e.g. run migrations against a test DB or confirm schema drift) before declaring the change complete.

Move the full per-file directory trees and ASCII architecture diagram into a reference bundle file (e.g. references/ARCHITECTURE.md) and keep SKILL.md as a concise overview with signaled one-level-deep links.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient reference material Claude would not know (repo paths, ports, architecture), but full directory trees are listed twice — once in 'Directory Structure Reference' and again as specific file links under each 'Common Tasks' subsection — adding redundant tokens, matching the 'mostly efficient but could be tightened' anchor rather than the lean level 3.	2 / 3
Actionability	Quotes concrete executable commands ('pnpm evals', 'cd packages/evals && npx vitest run', 'pnpm drizzle-kit generate', 'pnpm drizzle-kit migrate') and specific file paths per task (e.g. 'packages/evals/src/cli/runEvals.ts'), giving copy-paste-ready guidance that matches the level-3 anchor.	3 / 3
Workflow Clarity	Multi-step sequences are present ('Database Schema Changes': 1. Edit schema.ts, 2. Generate migration, 3. Apply migration), but the database-migration workflow lacks a validation/verification checkpoint; per the rubric, missing feedback loops for database operations caps workflow_clarity at 2.	2 / 3
Progressive Disclosure	The skill has no bundle files and ships everything inline in a single ~180-line SKILL.md; sections are well-organized with clear headers, but large directory trees and architecture detail that could live in separate reference files are inline, matching the 'some structure, content that should be separate is inline' anchor rather than the split-and-signaled level 3.	2 / 3
	Total	9 / 12 Passed

Description

90%

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 with explicit what/when structure, natural trigger terms, and clear disambiguation of two confusingly-named evals locations. Its only weakness is that the stated actions ('provides context', 'helps distinguish') are abstract rather than concrete operations.

Dimension	Reasoning	Score
Specificity	Quotes 'Provides context about the Roo Code evals system structure' and 'Helps distinguish between the evals execution system... and the public website evals display page' — these name the domain and a concrete disambiguation purpose, but the actions ('provides context', 'helps distinguish') are abstract rather than multiple concrete operations, so it matches the 'names domain and some actions' anchor rather than the multi-action level 3.	2 / 3
Completeness	It explicitly answers what ('Provides context about the Roo Code evals system structure in this monorepo') and when ('Use when tasks mention...'), with an explicit trigger clause, matching the level-3 anchor for both what AND when.	3 / 3
Trigger Term Quality	Quotes 'Use when tasks mention "evals", "evaluation", "eval runs", "eval exercises", or working with the evals infrastructure' — a good coverage of natural terms a user would say, matching the level-3 anchor rather than the partial-coverage level 2.	3 / 3
Distinctiveness Conflict Risk	It targets a clear niche (Roo Code evals infrastructure in a specific monorepo) and explicitly disambiguates the execution system from the website display page, making it unlikely to trigger for the wrong skill.	3 / 3
	Total	11 / 12 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
relative_links	Relative link issues: 13 missing, 13 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/evals-context/SKILL.md
Commit: f627ab5

Reviewed: about 9 hours ago

Table of Contents

Discovery Implementation Validation

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.