All skills
cli-daemon-interface-design
FoundationJIT onlyanalysis-agent/task-agent/review-agent: use when CLI, TUI, or daemon commands, flags, config, streams, exit codes, signals, or dry-run behavior change; skip unrelated work.
- Group
- Interface contracts
- Supported roles
- MainAnalysisTaskReview
- Source
- SKILL.md
Use when
Trigger signals that make this skill the right owner
- CLI TUI daemon command flags config precedence stdout stderr exit codes signals dry run background process scriptability
Do not use when
Anti-triggers — as binding as the triggers above
- no task-local cli daemon interface 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
- Return a CLI or daemon decision: define command model, config precedence, output, exits, dry-run, signals, lifecycle, daemon behavior, and tests
Escalation signals
When this skill must hand the decision back
- Ambiguous command and daemon contracts break automation hide failures and make destructive operations hard to recover
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 | Output, retry, destructive-action, or daemon lifecycle semantics remain open. | No command or daemon interface contract changes. | TaskReviewAnalysis |
| checklist.mddecision-checklist | Interface changes span signals, exit codes, automation, or cleanup. | Only internal implementation changes behind stable command behavior. | TaskReviewAnalysis |
| evidence-patterns.mdevidence-pattern | Compatibility claims require fresh help, outputs, scripts, or tests. | No interface-consumer claim awaits validation. | TaskReviewAnalysis |