BD review-library-rail
Review a pull request that adds or modifies a rail in nemoguardrails/library/ (built-in or vendor guardrail integration). Runs the mechanical gates first, then judgment dimensions tests cannot check (privacy honesty, retry semantics, fail-closed behavior, dialect coverage, docs accuracy), then a security pass. Use when reviewing rail-integration PRs, vendor integration contributions, or changes under nemoguardrails/library/. Trigger keywords - review rail PR, rail integration review, vendor integration PR, library rail review, guardrail contribution.
The skill promises to review pull requests for NeMo's built-in guardrails — runs mechanical gates first, then judges dimensions that resist automation (privacy, honesty, retry semantics, fail-closed behavior, dialect coverage, docs accuracy), finishes with a security pass.
One instruction file at 4330 tokens, no scripts. Never executed on models. Zero critical or high findings, no medium/low either. Lint is clean. Quality score 85, process score 49 — the second number hints the execution flow is either undercooked or underdocumented. Works across nine platforms including Claude and Cursor.
Install if you review guardrail integrations regularly. For spot checks, it might be overkill.
Review a pull request that adds or modifies a rail in nemoguardrails/library/ (built-in or vendor guardrail integration).
As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- 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
- note
edit-residuethe text marks something as outdated (lines 214): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 49/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 10 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70Execution cost. Instruction body is 4330 tokens
- 100Steps. 30 steps
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 556: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 30 items
- +4Has examples (1 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.