CC easa-rules
Reconstructed reference notes on EASA acceptable means of compliance for airborne software and airborne electronic hardware, built from AMC 20-115D (ED Decision 2017/020/R, AMC-20 Amendment 14, consolidated in Amendment 23) and AMC 20-152A (ED Decision 2020/010/R, AMC-20 Amendment 19, consolidated in Amendment 23), read from the Easy Access Rules AMC-20 compilation (Amendment 23, June 2023) and pinned 2026-09-26. Use for EASA software means of compliance, EASA AEH means of compliance, AltMoC, ETSO software, and the joint software and hardware certification workflow. SCOPE LIMITS: the two AMC sections only; no FAA content (use faa-8110-49); no RTCA DO-178C or DO-254, EUROCAE ED-12C or ED-80, or supplement clause text (use avionics-signpost to name them); no Part-21 body; no bulk AMC-20; AMC 20-193 and AMC 20-189 are name-only; reflects Amendment 23 as consolidated in the June 2023 EAR, not a later AMC-20 amendment; synthesized reference notes, not legal advice and not the official AMC. LICENCE: per-document (EASA site reproduction-with-acknowledgement grant, qualified by ED Decision all-rights-reserved footers); pack-level commercial use is not granted.
Reconstructed reference notes on EASA acceptable means of compliance for airborne software and airborne electronic hardware, built from AMC 20-115D (ED…
As a process C 58/100 · Has gaps — weak spots: result and completion, when it triggers, failures and branches
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: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1170 chars, limit 1024
Process rating: all ten parameters 58/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 32 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2704 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 1170: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +2Single-language instructions
- +4Structure: 13 headings
- +3Step-by-step instructions: 32 items
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 53.