SKILLEMALL.ai
GitHub ↗ RU Sign in

BD 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).

foryourhealth111-pixel/Vibe-Skills Agent Skills author: foryourhealth111-pixel Apache-2.0 1 file body ≈ 1 781 tokens Open the sourcegithub.com↗ analyzed 30 h ago

Provides context about the Roo Code evals system structure in this monorepo.

As a process D 37/100 · Unfinished process — References files that are not bundled: packages/evals/ADDING-EVALS.md, packages/evals/src/cli/, packages/evals/src/cli/runEvals.ts

AnalyzerDockerVS CodePostgreSQLSoftware developmenttype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
B
90/100
safety, quality, tests
Safety 60%
100
Quality 40%
75
Run on models
none yet
Process rating
D
37/100
Unfinished process
References files that are not bundled: packages/evals/ADDING-EVALS.md, packages/evals/src/cli/, packages/evals/src/cli/runEvals.ts
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 0

✓ No critical or high findings

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: packages/evals/ADDING-EVALS.md
  • warning missing-ref reference to a missing file: packages/evals/src/cli/
  • warning missing-ref reference to a missing file: packages/evals/src/cli/runEvals.ts
  • warning missing-ref reference to a missing file: packages/evals/src/cli/runTask.ts
  • warning missing-ref reference to a missing file: packages/evals/src/cli/runUnitTest.ts
  • warning missing-ref reference to a missing file: apps/web-evals/src/
  • warning missing-ref reference to a missing file: apps/web-evals/src/app/runs/new/new-run.tsx
  • warning missing-ref reference to a missing file: apps/web-evals/src/actions/runs.ts
  • warning missing-ref reference to a missing file: apps/web-roo-code/src/app/evals/
  • warning missing-ref reference to a missing file: apps/web-roo-code/src/app/evals/evals.tsx
  • warning missing-ref reference to a missing file: apps/web-roo-code/src/app/evals/plot.tsx
  • warning missing-ref reference to a missing file: packages/evals/src/db/schema.ts
  • warning missing-ref reference to a missing file: packages/evals/src/index.ts

Process rating: all ten parameters 37/100

Will not run. References files that are not bundled: packages/evals/ADDING-EVALS.md, packages/evals/src/cli/, packages/evals/src/cli/runEvals.ts
  • 0Tools and files. 13 referenced file(s) missing: packages/evals/ADDING-EVALS.md, packages/evals/src/cli/, packages/evals/src/cli/runEvals.ts
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 50When it triggers. No condition that starts the skill
  • 85Steps. 30 steps, 2 vague phrases
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1781 tokens
  • 100Running it twice. No mutating operations

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 3 example trigger phrases
  • +3Description length 358: enough signal without eating the budget
  • +4Structure: 18 headings
  • +3Step-by-step instructions: 30 items
  • +4Has examples (6 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.