All skills
error-code-design
FoundationJIT onlytask-agent: use when error codes, safe messages, retryability, remediation, status mapping, or client behavior needs a stable contract; skip when no error contract changes.
- Group
- Data & API contracts
- Supported roles
- MainAnalysisTaskReview
- Source
- SKILL.md
Use when
Trigger signals that make this skill the right owner
- design error model codes messages remediation and client behavior
Do not use when
Anti-triggers — as binding as the triggers above
- no task-local error code design decision is required
Required inputs
What must be supplied before this skill can decide anything
- current task contract
- selected primary Professional Skill
- task-local trigger evidence
Output contract
What this skill owes the next role
- error contract decision with stable identity, classification, safe detail, retry and remediation meaning, boundary mapping, compatibility, consumer evidence, proof limits, and residual owners
Escalation signals
When this skill must hand the decision back
- Poor errors hide recoverability and create inconsistent frontend handling
Loaded by
This skill never owns a task. These professionals may pull it in as Layer 3.
Targeted references
Each reference carries its own load condition. None of them enter context by default.
| Reference | Load when | Do not load when | Required by |
|---|---|---|---|
| checklist.mddecision-checklist | Errors change codes, statuses, retry behavior, or diagnostic separation. | No client-visible failure contract changes. | Task |
| evidence-patterns.mdevidence-pattern | Error claims require fresh negative tests and consumer evidence. | No compatibility, redaction, or retryability claim needs proof. | Task |
| industry-benchmarks.mdbenchmark-pattern | Public error semantics, retryability, or disclosure rules need calibration. | The private error never crosses a client boundary. | Task |