do-issuelisted

# Create Issue (Quality Issue Creator) ## Stage Marker At the very start of this skill, write an in_progress marker: ```bash sdlc-tool stage-marker --stage ISSUE --status in_progress --issue-number {issue_number} 2>/dev/null || true ``` After the issue is created (Step 7), write the completion marker: ```bash sdlc-tool stage-marker --stage ISSUE --status completed --issue-number {issue_number} 2>/dev/null || true ``` Creates GitHub issues that are self-contained documents a stranger could understand. Every issue must teach the reader what they need to know — define terms, link sources, and state the problem from the reader's perspective. ## Core Philosophy: Think Like a Teacher The reader of your issue has general software engineering experience but **zero context about this specific codebase**. Every named concept that isn't common knowledge needs: 1. A one-sentence definition 2. A link to its source (repo, docs page, file path, or RFC) This isn't optional politeness — it's functional. The `/do-plan` skill reads the issue description as its primary input. Undefined terms produce vague plans. Defined terms produce precise plans. ## When to load sub-files | Sub-file | Load when... | |----------|-------------| | `RECON.md` | After Step 2, before writing — run the reconnaissance routine | | `ISSUE_TEMPLATE.md` | Writing the issue body (use as the structural skeleton) | | `CHECKLIST.md` | Before publishing — run every check, fix failures | ## Cross-Repo Resolution