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

86%

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

Quality

Content

82%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 content is highly actionable and well structured as a codebase-orientation reference, with concrete paths and commands throughout. It is slightly long for a SKILL.md overview and lacks explicit validation steps for the riskier schema-migration workflow.

Suggestions

Move the exhaustive directory trees and ASCII architecture diagram into a reference file (e.g. references/ARCHITECTURE.md) and link to it, keeping SKILL.md as a lean overview.

Add a validation/checkpoint note to the Database Schema Changes workflow (e.g. verify migrations apply cleanly / run tests after `drizzle-kit migrate`) since migrations carry batch/destructive risk.

Trim redundant restatements of the two-evals-locations disambiguation already covered by the description and the table.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean directory trees, tables, and exact commands, but the inlined ASCII architecture diagram and exhaustive file listings add length beyond the strictly essential; efficient overall with minor trim opportunities.	4 / 5
Actionability	Concrete file paths, exact commands (`pnpm evals`, `pnpm drizzle-kit generate`, `pnpm drizzle-kit migrate`, `npx vitest run`), default ports, and direct file links make the guidance copy-paste ready and cover common cases.	5 / 5
Workflow Clarity	"Adding a New Eval Exercise" and "Database Schema Changes" are clearly sequenced, and as an orientation skill there is no destructive/batch operation requiring validation; not a 5 because validation/feedback checkpoints are absent where schema migrations do carry risk.	4 / 5
Progressive Disclosure	Sections are well organized with clear headers and one-level-deep file links, but at ~185 lines with inlined directory trees and an architecture diagram that could arguably live in a reference file, it stops short of the lean overview-plus-references ideal.	4 / 5
	Total	17 / 20 Passed

Description

90%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 is strong: explicit what/when structure with rich natural trigger terms and clear distinctiveness via a dedicated disambiguation. Its only soft spot is specificity, since a context skill inherently frames rather than performs concrete actions.

Dimension	Reasoning	Score
Specificity	It names the domain ("the Roo Code evals system structure in this monorepo") and a concrete distinguishing function plus specific paths, but describes orientation/context rather than concrete transformative actions; not a 4 because the "actions" are framing/navigating rather than a list of specific operations.	3 / 5
Completeness	It explicitly answers both what ("Provides context about the Roo Code evals system structure") and when (explicit "Use when tasks mention..." clause with concrete trigger phrases).	5 / 5
Trigger Term Quality	"Use when tasks mention 'evals', 'evaluation', 'eval runs', 'eval exercises', or working with the evals infrastructure" gives comprehensive natural triggers with several synonyms users would actually say.	5 / 5
Distinctiveness Conflict Risk	It carves a clear niche (Roo Code evals infra disambiguation) with distinct triggers and explicit boundary guidance between two confusingly-named locations, minimizing conflict risk.	5 / 5
	Total	18 / 20 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: d5ae560

Reviewed: 1 day 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.