BB bootstrap_review
Review an agent workspace's boot files (AGENTS.md, USER.md, SOUL.md, MEMORY.md, IDENTITY.md, TOOLS.md, and optional HEARTBEAT.md) against registry-backed context notes and produce a concise audit, refactor recommendations, and optional staged rewrites. Use when the user asks to review boot files, audit bootstrap files, refactor agent context files, check USER/SOUL/AGENTS redundancy, validate boot-file references, or compare current boot files against shared user context.
As a process B 71/100 · Nearly there — weak spots: inputs and preconditions, consistency, running it twice
How to improve
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- 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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
description-long-hermesdescription is 475 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
Process rating: all ten parameters 71/100
- 0Progress reporting. Says nothing while it works
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 10 mutating operations with no state check
- 40Consistency. Frontmatter name (bootstrap_review) differs from the folder (bootstrap-review)
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 4 branches
- 100Tools and files. No external tools needed
- 100Steps. 132 steps
- 100Execution cost. Instruction body is 2452 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 17 top-level sections: this looks like several domains in one skill
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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +3Description length 475: enough signal without eating the budget
- +4Structure: 30 headings
- +3Step-by-step instructions: 132 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.