Help us improve
Share bugs, ideas, or general feedback.
From software-engineering
Self-referential loop until task completion with configurable verification reviewer
How this skill is triggered — by the user, by Claude, or both
Slash command
/software-engineering:persistent-completion-loop <task description><task description>The summary Claude sees in its skill listing — used to decide when to auto-load this skill
<Purpose>
Share bugs, ideas, or general feedback.
<Use_When>
<Do_Not_Use_When>
<Why_This_Exists> Complex tasks often fail silently: partial implementations get declared "done", tests get skipped, edge cases get forgotten. This skill prevents this by:
<PRD_Mode>
A scaffold prd.json is auto-generated when the loop starts if none exists.
Startup gate: Always initialize and validate prd.json at startup.
Reviewer selection: The completion reviewer validates the stories, and the reviewer cannot be the same writer lane/agent that implemented the code. </PRD_Mode>
<Execution_Policy>
model or tier parameter explicitly when delegating to agentsPick next story: Select the highest-priority story with passes: false. This is your current focus.
Implement the current story:
Verify the current story's acceptance criteria: a. For EACH acceptance criterion in the story, verify it is met with fresh evidence b. Run relevant checks (test, build, lint, typecheck) and read the output c. If any criterion is NOT met, continue working -- do NOT mark the story as complete
Mark story complete:
a. When ALL acceptance criteria are verified, set passes: true for this story
b. Record progress (what was implemented, files changed, learnings)
Check PRD completion:
a. Are ALL stories marked passes: true?
b. If NOT all complete, loop back to Step 2
c. If ALL complete, proceed to Step 7 (reviewer verification)
Reviewer verification (tiered, against acceptance criteria):
7.5 Mandatory Cleanup Pass (runs after Step 7 approval, unless configured otherwise):
7.6 Regression Re-verification:
On approval: Report completion and clean up all intermediate state files.
On rejection: Fix the issues raised, re-verify, then loop back.
<Escalation_And_Stop_Conditions>
<Final_Checklist>
passes: truenpx claudepluginhub yeaight7/agent-powerups --plugin software-engineeringCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.