CB nrc-nuclear
Reconstructed reference notes on US NRC software assurance guidance for digital computer software in nuclear power plant safety systems, built from seven public-domain sources (Regulatory Guide 1.168 Revision 2, July 2013; Regulatory Guides 1.169, 1.170, 1.171, 1.172, and 1.173 Revision 1, July 2013; NUREG-0800 Branch Technical Position 7-14 Revision 6, August 2016; pinned 2026-10-12). Use for software life cycle process questions, software requirements specifications, software configuration management plans, verification and validation with reviews and audits, test documentation and unit testing, and what NRC staff examine in a BTP 7-14 software review of plans, implementation, and design outputs. SCOPE LIMITS: NRC Regulatory Guides and the BTP 7-14 staff review position only; the endorsed IEEE standards (IEEE Std 603-1991, 7-4.3.2-2003, 828-2005, 829-2008, 830-1998, 1008-1987, 1012-2004, 1028-2008, 1074-2006), IEC 60880, IEC 61513, IEC 62138, and IAEA guides are cited by designation and edition only, with no standard text; RG 1.152 Rev 4, BTP 7-18, BTP 7-19, other SRP Chapter 7 sections, and NUREG/CR contractor reports are outside the pack; reflects the pinned 2013 and 2016 editions, not later agency actions; synthesized reference notes, not legal or licensing advice and not a substitute for the source documents. LICENCE: Public Domain (US Government work, 17 U.S.C. § 105).
Reconstructed reference notes on US NRC software assurance guidance for digital computer software in nuclear power plant safety systems, built from seven…
As a process B 68/100 · Nearly there — weak spots: result and completion, failures and branches, running it twice
How to improve
- Shorten the description to 1024 characters.
- 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: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1398 chars, limit 1024
Process rating: all ten parameters 68/100
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 50When it triggers. No condition that starts the skill
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 44 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3577 tokens
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)
- +3Description length 1398: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +2Single-language instructions
- +4Structure: 12 headings
- +3Step-by-step instructions: 44 items
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 53.