Bkit Evals

What it does

When your agent uses it

• Tasks that involve LLM evaluation
• Tasks that involve Agent evaluation and testing

Example prompts

• “/bkit-evals”

Requirements

• Pre-approved tools (allowed-tools): Bash, Read, Glob, Grep

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

1. 1Validate skill against /^a-z{0,63}$/. Reject anything else
2. 2Spawn node evals/runner.js --skill via child_process.spawnSync
3. 3Capture stdout / stderr. Parse the trailing JSON block via
4. 4Apply fail-closed defense: if parsed === null and stdout includes
5. 5Persist the structured result to
6. 6Render a one-line summary in the chat

What it can do on your machine

Read from SKILL.md and the folder at commit 85b4913. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Bash
  • Read
  • Glob
  • Grep

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • node

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Bkit Evals loads about 1k tokens when it runs. Until then it costs about 47 tokens; SKILL.md has 373 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~47

When it runs · the whole SKILL.md, loaded when a task matches

~1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Bash, Read, Glob, Grep

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ww-w-ai/bkit-claude-code at commit 85b4913, republished under its Apache-2.0 licence (© ww-w-ai). 373 words, ~1,015 tokens.

name

bkit-evals

description

Run skill evals via evals/runner.js — wrapper validates skill names, captures stdout/stderr, persists JSON results. Triggers: bkit evals, evals run, skill quality, eval runner

allowed-tools

Bash, Read, Glob, Grep

classification

capability

classification-reason

Eval runner is a development-time quality tool, not a workflow phase

deprecation-risk

none

effort

low

argument-hint

run <skill> | list

user-invocable

true

task-template

[Evals] {action}

{
  "skill": "gap-detector",
  "invokedAt": "<ISO 8601>",
  "exitCode": 0,
  "timedOut": false,
  "stdoutTail": "...",
  "stderrTail": "...",
  "parsed": { /* whatever runner.js prints as JSON, or null */ }
}

# Single eval
/bkit-evals run gap-detector

# Discovery
/bkit-evals list

© ww-w-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/bkit-evals of ww-w-ai/bkit-claude-code.

Open the folder on GitHubat commit 85b4913