yaojingang
27 lines
1.4 KiB
Markdown
27 lines
1.4 KiB
Markdown
# Intent Confidence
|
|
|
|
- Confidence score: `100/100`
|
|
- Confidence band: `high`
|
|
- Gate passed: `True`
|
|
- Recommended action: Intent is clear enough to package the first routeable version.
|
|
|
|
## Current Reading
|
|
|
|
Turn repeated workflows, prompts, transcripts, runbooks, documents, or existing skill packages into routeable, evaluable, packageable, and governable agent skills for personal, team, library, or governed reuse. Primary output: A working skill package with lean SKILL.md, aligned agents/interface.yaml, justified references, scripts only when useful, eval evidence, reports, packaging metadata, and clear next iteration recommendations.. Exclusions: one-off writing, translation, explanation, or brainstorming requests that do not need a reusable skill, general code review or debugging unless the user is packaging that workflow as a skill, raw private material that was not intentionally supplied as skill evidence, platform-specific plugin creation when the request is not about an agent skill package.
|
|
|
|
## Strong Signals
|
|
|
|
- The recurring job is concrete enough to anchor the package.
|
|
- Real input shape is explicit.
|
|
- The hand-back output is concrete.
|
|
- Boundary exclusions are already explicit.
|
|
- Operational constraints are visible.
|
|
|
|
## Gaps To Close
|
|
|
|
- No major intent gaps detected.
|
|
|
|
## Follow-Up Questions
|
|
|
|
- No extra follow-up questions required before the first package.
|