CD add-library-rail
Step-by-step contribution guide for adding a new rail to nemoguardrails/library/: manifest, actions returning RailOutcome, config schema, flows, HTTP rules for vendor backends, Python package requirements, unit and recorded tests, docs and examples. Use when implementing, scaffolding, or reviewing a new built-in or vendor guardrail integration. Trigger keywords - add rail, new rail, library rail, vendor integration, guardrail integration, RailManifest, RailOutcome, RailRequirements, optional_dependencies, rail.py, guardrail catalog, third-party rail.
Step-by-step contribution guide for adding a new rail to nemoguardrails/library/: manifest, actions returning RailOutcome, config schema, flows, HTTP rules…
As a process D 44/100 · Unfinished process — References files that are not bundled: scripts/generate_rails_config_schema_snapshot.py, examples/configs/<rail>/
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- 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
body-longSKILL.md body ≈ 9776 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: scripts/generate_rails_config_schema_snapshot.py - warning
missing-refreference to a missing file: examples/configs/<rail>/ - note
edit-residuethe text marks something as outdated (lines 443, 577): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 44/100
- 0Tools and files. 2 referenced file(s) missing: scripts/generate_rails_config_schema_snapshot.py, examples/configs/<rail>/
- 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
- 40Execution cost. Instruction body is 9776 tokens: crowds the task out of the window
- 100Steps. 47 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (9 tags): a typed call is more reliable
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: 10 headings
- +3Step-by-step instructions: 47 items
- +4Has examples (4 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.