plugins/gsd/skills/complete-milestone/SKILL.md
Archive completed milestone and prepare for next version
npx skillsauth add davepoon/buildwithclaude gsd:complete-milestoneInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Purpose: Create historical record of shipped version, archive milestone artifacts (roadmap + requirements), and prepare for next milestone. Output: Milestone archived (roadmap + requirements), PROJECT.md evolved, git tagged. </objective>
<execution_context> Load these files NOW (before proceeding):
User input:
Follow complete-milestone.md workflow:
Check for audit:
.planning/v{{version}}-MILESTONE-AUDIT.md/gsd:audit-milestone firstgaps_found: recommend /gsd:plan-milestone-gaps firstpassed: proceed to step 1## Pre-flight Check
{If no v{{version}}-MILESTONE-AUDIT.md:}
⚠ No milestone audit found. Run `/gsd:audit-milestone` first to verify
requirements coverage, cross-phase integration, and E2E flows.
{If audit has gaps:}
⚠ Milestone audit found gaps. Run `/gsd:plan-milestone-gaps` to create
phases that close the gaps, or proceed anyway to accept as tech debt.
{If audit passed:}
✓ Milestone audit passed. Proceeding with completion.
Verify readiness:
Gather stats:
Extract accomplishments:
Archive milestone:
.planning/milestones/v{{version}}-ROADMAP.mdArchive requirements:
.planning/milestones/v{{version}}-REQUIREMENTS.md.planning/REQUIREMENTS.md (fresh one created for next milestone)Update PROJECT.md:
<details> (if v1.1+)Commit and tag:
chore: archive v{{version}} milestonegit tag -a v{{version}} -m "[milestone summary]"Offer next steps:
/gsd:new-milestone — start next milestone (questioning → research → requirements → roadmap)<output_format>
After the milestone is archived and tagged, emit a Milestone Complete continuation block following the pattern in references/continuation-format.md (§ Milestone Complete variant):
## 🎉 Milestone v{{version}} Complete with phase/plan/task summary## ▶ Next Up heading`/clear` then: before /gsd:new-milestone/clear is safe — /gsd:resume-work restores position from HANDOFF.json if you change your mind)/gsd:audit-milestone (retrospective audit) or /gsd:review-backlog (deferred items review)Milestone close is the single biggest context-shed point in the workflow. The just-shipped milestone's plan/execute conversation is finished; the next milestone wants a clean slate. Always suggest /clear.
</output_format>
<success_criteria>
.planning/milestones/v{{version}}-ROADMAP.md.planning/milestones/v{{version}}-REQUIREMENTS.md.planning/REQUIREMENTS.md deleted (fresh for next milestone)<critical_rules>
/gsd:new-milestone which includes requirements definition
</critical_rules>tools
Assesses the current state of the startup project and recommends what to focus on next. Use when there is a need or a question from the user to understand what the next steps are or what to focus on next.
data-ai
Use at the start of any conversation about a startup idea, product validation, founder strategy, or work inside a `startup/` workspace. Establishes file conventions, voice-input handling, subagent dispatch rules, and how to update each artifact safely. Activate before invoking any other startup-superpowers skill.
tools
Manages the founder's survey-based validation — crafting the right questions, deploying a survey to the internet, and analyzing results against hypotheses. Use when the founder wants to run a survey, create survey questions, validate hypotheses at scale, check how a survey is going, understand whether a survey is the right tool right now, or deploy a question set to get quantitative signal. Also bring this up if you believe that creating a survey to collect quantitative evidence may be useful at this point.
development
Guides the founder through designing and optionally building the simplest MVP or prototype that validates their current hypotheses. Use when the founder wants to build something to test assumptions, discusses what to build next, wants to interpret results from a live MVP, or is deciding whether the current approach is still right. Also use when a founder proposes something to build — the skill will check whether the proposed form is the simplest thing that generates honest signal.