CC mrl-deskbook
Knowledge base from the DoD Manufacturing Readiness Level (MRL) Deskbook (Version 2022, OSD ManTech / Joint Service–Industry MRL Working Group). Use for assessing and managing manufacturing maturity and producibility risk in defense acquisition: the 10-level MRL scale and its non-linear, target-not-grade nature; the five demonstration environments (laboratory → production-relevant → production-representative → pilot line → production line); the nine manufacturing-risk threads and sub-threads; how MRL targets map onto Adaptive Acquisition Framework milestones (MRL 4/6/7/8/9); conducting an MRL Assessment; building a Manufacturing Maturation Plan; putting MRL maturity into contract language (Section L/M, SOW, AS6500A, DIDs); tailoring criteria for S&T, single-system, ship, sustainment, and industry contexts; and screening operational-technology cybersecurity. Manufacturing-readiness focused — it measures producibility risk and frames mitigation; it is NOT a technology-readiness (TRL) guide, a full systems-engineering process model, a cost-estimating or schedule guide, or a deep cybersecurity audit method (see sibling packs for those).
Knowledge base from the DoD Manufacturing Readiness Level (MRL) Deskbook (Version 2022, OSD ManTech / Joint Service–Industry MRL Working Group).
As a process C 61/100 · Has gaps — weak spots: result and completion, when it triggers, 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: 14. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1150 chars, limit 1024
Process rating: all ten parameters 61/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 56 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3846 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 1150: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +2Single-language instructions
- +4Structure: 16 headings
- +3Step-by-step instructions: 56 items
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 53.