CC mil-hdbk-61
Knowledge base from MIL-HDBK-61B, the DoD Configuration Management (CM) guidance handbook (7 April 2020, cataloged with Change 1, 2025). Use for defense CM across the acquisition and sustainment life cycle: the five CM functions (planning, identification, control/change management, status accounting, verification & audit), the three configuration baselines (FBL/ABL/PBL) and FCD→ACD→PCD documentation, configuration items (CIs/HWCI/CSCI), change instruments (ECP/NOR/RFV), the CCB and Class I/II classification, CDCA/AA authority, FCA/PCA audits, data management and data rights (CDRL/DID, DFARS rights ladder, master/authoritative source), and tailoring CM by phase (EIA-649-1 R/T/NR matrix, Appendix C templates), plus digital-era CM (digital twin, viewpoints, MOSA). NOTE: 61B is advisory guidance that adopts and points to the SAE EIA-649 / EIA-649-1 / GEIA-HB-649 suite for the authoritative CM requirements — this pack names and describes that suite but does not reproduce its copyrighted requirement text. Thin on: the EIA-649 requirement clauses themselves, form-level detail (DD-form field instructions, full DID content), and non-DoD/commercial CM frameworks.
Knowledge base from MIL-HDBK-61B, the DoD Configuration Management (CM) guidance handbook (7 April 2020, cataloged with Change 1, 2025).
As a process C 63/100 · Has gaps — 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: 14. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1171 chars, limit 1024
Process rating: all ten parameters 63/100
- 0Result and completion. Does not say what the result is
- 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
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4491 tokens
- 100Tools and files. No external tools needed
- 100Steps. 57 steps
- 100Consistency. Name and required fields are in place
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 1171: 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: 57 items
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 53.