GravionLabs/elysion / .agents/skills/deliver
deliver
VerifiedDeliver a PBI, Bug, Feature or Epic item by item with subagents (implement, review, PR, CI, merge). Use for "/deliver 12" or "deliver feature 7".
references/feedback.md
View on GitHub# Feedback during a run
In an interactive run (control session or `--inline`) the user reports what they see: manual test findings, UI wishes, ideas. This session turns each into an issue in the milestone and implements nothing itself.
## Capture
1. A message that describes a defect or a change is a finding. One message with several findings gives one draft per finding. Screenshots and files the user names are referenced in the body (path or link), not described from memory.
2. Per finding a draft, shown in at most 6 lines: type (`[Bug]` or `[PBI]`), title (`fix: …` or `feat: …`), repro (Bug) or acceptance criteria (PBI), `Tier:` and `Size:`.
3. Ask once for confirmation of all drafts together. Unattended there is no user, so this never runs.
4. On confirmation create each with `github-issue` (title `[<Level>] <summary>`, label `bug` or `pbi`) in the current milestone (the `milestone.title` of step 1) or the one the user names. Print the URL per issue.
## Ready or refine
- Small and clear (Size S, criteria testable, no open decision): no `needs-refinement`. The next selection (step 1) of the same run picks it up, or the loop does on its next PBI.
- Unclear (open question, Size L, unknown cause): label `needs-refinement` and the hint `planner refine <nr>`; selection skips it.
## No implementing here
The control session never changes code for feedback. "Fix it now" from the user: create the PBI as above, deliver it with steps 2 to 8 (subagents, review, PR, CI, merge), report the PR as usual.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |