feat: Add story draft command and prompt for Jira-ready proposals with clear requirements
This commit is contained in:
60
.opencode/commands/story-draft.md
Normal file
60
.opencode/commands/story-draft.md
Normal file
@@ -0,0 +1,60 @@
|
||||
---
|
||||
description: Draft a Jira story proposal with Fidelity-ready context and acceptance criteria
|
||||
---
|
||||
|
||||
Draft a future Jira story from rough notes, findings, or follow-up ideas.
|
||||
|
||||
This command should optimize for:
|
||||
|
||||
- professional story wording
|
||||
- explicit scope
|
||||
- useful acceptance criteria
|
||||
- clear ownership framing
|
||||
- natural US English that Jeff can reuse or forward without rewriting
|
||||
|
||||
Input notes or rough idea:
|
||||
|
||||
$ARGUMENTS
|
||||
|
||||
Read:
|
||||
|
||||
@prompts/story-draft.md
|
||||
@ai/AGENTS.md
|
||||
@ai/context/project.md
|
||||
@ai/context/people/manager.md
|
||||
@ai/context/people/jeff-dewitte.md
|
||||
@ai/context/people/index.md
|
||||
@ai/state/current.md
|
||||
@ai/state/work-items.md
|
||||
@knowledge/communication-rules.md
|
||||
@knowledge/agent-memory-rules.md
|
||||
|
||||
Today's log, if present:
|
||||
|
||||
!`if [ -f ai/logs/$(date +%F).md ]; then cat ai/logs/$(date +%F).md; else echo "No log exists for today yet."; fi`
|
||||
|
||||
Latest Mattermost context, if available:
|
||||
|
||||
!`if [ -s ai/inbox/mattermost-latest.md ]; then cat ai/inbox/mattermost-latest.md; elif [ -s scripts/mattermost/generated/mattermost_context.jsonl ]; then cat scripts/mattermost/generated/mattermost_context.jsonl; else echo "No Mattermost context available."; fi`
|
||||
|
||||
Requirements:
|
||||
|
||||
- Preserve the exact technical meaning of the input
|
||||
- Rewrite fully when needed so the output sounds like a fluent senior engineer wrote it
|
||||
- Choose the most appropriate story framing: bug, enhancement, spike, task, or follow-up
|
||||
- Keep the title short, concrete, and Jira-ready
|
||||
- Make the description specific enough that another engineer can understand the intended work
|
||||
- Separate current problem, root-cause suspicion, workaround, and follow-up work when relevant
|
||||
- Do not overstate certainty; if something is still a hypothesis, label it clearly
|
||||
- Make ownership explicit when helpful: XFlow vs consumer app vs service/configuration vs other framework
|
||||
- Acceptance criteria should be testable and scoped to the proposed story
|
||||
- If the story looks too large or too ambiguous, say so explicitly and suggest spike framing instead
|
||||
- If useful, include a short note about dependencies, blockers, or coordination needed
|
||||
|
||||
Return:
|
||||
|
||||
1. Suggested story type
|
||||
2. Jira-ready title
|
||||
3. Description
|
||||
4. Acceptance criteria
|
||||
5. Optional notes on dependencies / blockers / sizing concerns
|
||||
@@ -41,3 +41,11 @@
|
||||
## Next Step
|
||||
|
||||
- Keep using explicit issue framing for future Mattermost and Jira updates
|
||||
|
||||
---
|
||||
|
||||
## Workflow Clarification
|
||||
|
||||
- This workspace is mainly used off the Fidelity work machine
|
||||
- Main practical use cases are: drafting Mattermost updates to Jeff, translating/refining English, reusing prior context, getting Swift technical support, and drafting PR/story text
|
||||
- Recommendations for new commands should prioritize communication support and context reuse over heavy local triage workflows that assume direct access to the product environment
|
||||
|
||||
33
prompts/story-draft.md
Normal file
33
prompts/story-draft.md
Normal file
@@ -0,0 +1,33 @@
|
||||
# Story Draft Prompt
|
||||
|
||||
Draft Jira-ready story proposals for Fidelity work.
|
||||
|
||||
The goal is not just to rephrase notes, but to turn them into work items another engineer, manager, or scrum contact can understand quickly.
|
||||
|
||||
Requirements:
|
||||
|
||||
- Write in natural, professional US English
|
||||
- Preserve exact technical meaning
|
||||
- Prefer explicit scope over broad or vague framing
|
||||
- Use bug / enhancement / spike / task language accurately
|
||||
- Keep titles concise and concrete
|
||||
- Separate these when relevant:
|
||||
- current issue
|
||||
- suspected root cause
|
||||
- workaround
|
||||
- follow-up work
|
||||
- If the notes describe a consumer issue that likely belongs outside XFlow, make that visible in the notes instead of hiding it
|
||||
- If the request is too ambiguous or too large, recommend turning it into a spike
|
||||
|
||||
Acceptance criteria guidance:
|
||||
|
||||
- Make ACs observable and testable
|
||||
- Do not include implementation details unless they are central to scope
|
||||
- Prefer behavior-based acceptance criteria over code-structure criteria
|
||||
- If risk of regression matters, include a regression-safety criterion
|
||||
|
||||
Useful output qualities:
|
||||
|
||||
- Jeff should be able to forward or paste it with little or no rewriting
|
||||
- Quy or another scrum/contact person should be able to create the story from it directly
|
||||
- Another engineer should understand what success looks like
|
||||
Reference in New Issue
Block a user