All skills
data-format-contract-usage
FoundationJIT onlyanalysis-agent/task-agent/review-agent: use when Protobuf schemas, parsers, or old-reader/new-writer compatibility changes; skip work without a data-format contract.
- Group
- Data & API contracts
- Supported roles
- MainAnalysisTaskReview
- Source
- SKILL.md
Use when
Trigger signals that make this skill the right owner
- JSON Schema YAML XML TOML CSV CPE Protobuf Avro Parquet schema registry parser compatibility parser serializer deserializer serialization wire format storage format field evolution compatibility generated model golden fixture
- protobuf field number reserved field enum value wire type breaking change old reader new writer YAML safe loader YAML 1.1 YAML 1.2 scalar coercion TOML type strictness duplicate key unknown field boolean timestamp XML canonicalization size depth limit parser differential CPE normalization version matching
Do not use when
Anti-triggers — as binding as the triggers above
- no task-local data format contract usage 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
- data-format decision with effective dialect, semantic states, evolution constraints, mixed-version evidence, resource bounds, canonicalization, generated lineage, proof limits, and residual owners
Escalation signals
When this skill must hand the decision back
- Data format changes can break consumers or stored data through parser defaults coercion field-number reuse generated drift unsafe loaders duplicate keys and untested old-reader new-writer behavior
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 |
|---|---|---|---|
| benchmarks-and-patterns.mdbenchmark-pattern | Format, parser, compatibility, or security semantics require comparison. | Schema authority and parser behavior are already fixed. | TaskAnalysisReview |
| checklist.mddecision-checklist | Boundary changes coercion, unknown fields, limits, or generated artifacts. | No serialized shape or parser option changes. | TaskAnalysisReview |
| evidence-patterns.mdevidence-pattern | Format claims need fresh fixtures, validators, or generated diffs. | No compatibility or parser-safety claim awaits proof. | TaskAnalysisReview |