From rapid-mvp
Use when user says "wrap up", "close session", "end session", "wrap things up", "close out this task", or invokes /wrap-up — runs end-of-session checklist for shipping, memory, and self-improvement
npx claudepluginhub kjgarza/marketplace-claude --plugin rapid-mvpThis skill uses the workspace's default tool permissions.
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.
Reviews prose for communication issues impeding comprehension, outputs minimal fixes in a three-column table per Microsoft Writing Style Guide. Useful for 'review prose' or 'improve prose' requests.
Run four phases in order. Each phase is conversational and inline — no separate documents. All phases auto-apply without asking; present a consolidated report at the end.
Commit:
git status in each repo directory that was touched during the sessionFile placement check: 4. If any files were created or saved during this session:
Deploy: 6. Check if the project has a deploy skill or script 7. If one exists, run it 8. If not, skip deployment entirely — do not ask about manual deployment
Task cleanup: 9. Check the task list for in-progress or stale items 10. Mark completed tasks as done, flag orphaned ones
Review what was learned during the session. Decide where each piece of knowledge belongs in the memory hierarchy:
Memory placement guide:
.claude/rules/ (modular project rules) — Topic-specific instructions
that apply to certain file types or areas. Use paths: frontmatter to scope
rules to relevant files (e.g., testing rules scoped to tests/**)CLAUDE.local.md (private per-project notes) — Personal WIP context,
local URLs, sandbox credentials, current focus areas that shouldn't be
committed@import references — When a CLAUDE.md would benefit from referencing
another file rather than duplicating its contentDecision framework:
.claude/rules/.claude/rules/ with paths:
frontmatterCLAUDE.local.md@import insteadNote anything important in the appropriate location.
Analyze the conversation for self-improvement findings. If the session was short or routine with nothing notable, say "Nothing to improve" and proceed to Phase 4.
Auto-apply all actionable findings immediately — do not ask for approval on each one. Apply the changes, commit them, then present a summary of what was done.
Finding categories:
Action types:
.claude/rules/ filePresent a summary after applying, in two sections — applied items first, then no-action items:
Findings (applied):
✅ Skill gap: Cost estimates were wrong multiple times → [CLAUDE.md] Added token counting reference table
✅ Knowledge: Worker crashes on 429/400 instead of retrying → [Rules] Added error-handling rules for worker
✅ Automation: Checking service health after deploy is manual → [Skill] Created post-deploy health check skill spec
No action needed:
After all other phases are complete, review the full conversation for material that could be published. Look for:
If publishable material exists:
Draft the article(s) for the appropriate platform and save to a drafts folder. Present suggestions with the draft:
All wrap-up steps complete. I also found potential content to publish:
Wait for the user to respond. If they approve, post or prepare per platform. If they decline, the drafts remain for later.
If no publishable material exists:
Say "Nothing worth publishing from this session" and you're done.
Scheduling considerations: