scenario-refine
Use when product intent is vague, a scenario lacks testable outcomes, or draft work must be assessed for readiness.
- License 许可
- MIT
- 最近更新
- 2026-07-18
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- scenario-refine
- description
- Use when product intent is vague, a scenario lacks testable outcomes, or draft work must be assessed for readiness.
02 资源文件 1
- 参考文档agents/openai.yaml212 B
03 SKILL.md 正文
Scenario Refine
Turn one user outcome into a bounded scenario. Preserve framework fields and
refs in English; write reader-facing artifacts in profile.language.
Procedure
- Run
toolbox workbench check, then inspect the product and existing scenario through public toolbox commands. - Describe the triggering situation and observable user states, including loading, empty, error, success, permission, and recovery states when relevant.
- Write independently verifiable acceptance criteria. Identify dependency refs, design refs, and explicit non-goals. Put narrative discovery and non-goals in the owning codebase's product artifact; reference that artifact from the scenario rather than adding private schema fields.
- Examine value risk, usability risk, and feasibility risk. Record the riskiest assumption and the smallest evidence needed to resolve it.
- Keep status
draftwhile any critical risk, dependency, observable state, or acceptance criterion is unresolved. Movedrafttoreadyonly after this review; readiness is not an implementation estimate. - Write a strict
toolbox-scenario/v1document to a temporary path and apply it only withtoolbox scenario apply --product <product-id> --file <file>. Re-run product status and report the result.
Do not implement code, alter priority without product judgment, or edit living state directly.
04 同仓库更多 Skills
ticket-incubate
Use to turn an idea that has no issue/ticket yet into an actionable GitHub issue. Grow a vague notion by divergence, narrow only the gaps via a deficit-based interview, and create the issue once the four required elements (background, goal, done criteria, out-of-scope) are filled. Triggers on "I have an idea", "let's make this a ticket", "create an issue", "interview me", or describing something to make/fix/improve without an issue number, even if the user never says the word "ticket". It is the front of the workbench lifecycle (idea -> ticket-incubate -> issue -> task-start). Distinct from brainstorming/design skills: those work out the how of what to build now; this captures the what of later work as a well-honed ticket.
task-tickets
Use to scan open workbench tickets joined with task branches and lifecycle events into unstarted / claim-attempted / in-progress / awaiting-PR / cleaned-up states. Read-only.
task-submit
Use when the user asks to submit, wrap up, or extract from a task, or when work has reached a point to open a PR.
task-status
Use to see local and remote task status at a glance and diagnose drift (unpushed, stale status, missed cleanup). When you want to know where everything stands before starting or submitting, or after a multi-device handoff.
task-start
Use when the user asks to start a task, pick up an issue, or begin a new attempt, or hands over an issue number to start work.
task-done
Use when the user asks to clean up or discard a task, or to clear the workspace after a PR is merged.