AC ftm-copilot
Expert-level IBM Financial Transaction Manager (FTM) knowledge base and development assistant. Invoke this skill whenever the user mentions FTM, IBM Financial Transaction Manager, payments hub, payment orchestration, ACE (IBM App Connect Enterprise / WebSphere Message Broker / IIB), RSA (IBM Rational Software Architect), ITX/WTX (IBM Transformation Extender / WebSphere Transformation Extender), DB2 in a payments context, ISF (Internal Standard Format), ISO 20022 in an IBM context, SWIFT integration with IBM tooling, FSM (Finite State Machine) in payments, BAR files, message flows, OAC (Operations and Administrative Console), or any combination of these. Also trigger when the user asks to act as an "FTM expert", references FTM configuration, or discusses financial transaction lifecycle management. When in doubt, trigger — FTM developers always benefit from this context.
As a process C 54/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- 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: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 54/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 23 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1603 tokens
- medium 3 test cases, all positive: not one "should refuse" or "should ask first"
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 881: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Structure: 10 headings
- +3Step-by-step instructions: 23 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.