Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/nhouseholder-wrap-up
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: writing, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/wrap-up
What's inside
- Skill name
wrap-up- Description
- Session end. Write a lean handoff in this project's handoffs/, commit it on the current branch. Do not auto-ship. Save standing memory to Engram MCP.
- License
- MIT
- Instructions
- 84 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Wrap up (`/wrap-up`) Last thing before ending a session. Write a lean handoff **in this project's** `handoffs/`. Save standing memory to the existing **Engram MCP** so other agents can `mem_search` it. Then stop. ## Hard gates - Header matches **this** git root. Never a different repo's name. - Do **not** auto-ship / deploy / `/safe-ship`. Wrap-up documents; it does not go live. - Engram: **save standing memory.** After the handoff is written, call `mem_save` (scope `project`, stable `topic_key`) for binding decisions / architecture / preferences / the work just finished, then `mem_session_summary`. Mid-task chatter stays out. If the Engram namespace is `error` or has no tools, print `Engram: unavailable` — do not invent a save. - Do not `git pull`, merge, or switch branches. - Do not invent anti-pattern IDs. Do not assume `~/.claude/anti-patterns.md` exists here. - Do **not** auto-archive this repo's dated notes unless it already uses `handoffs/_archived/` **and** `handoff_*.md` names. Repos that keep `YYYY-MM-DD_*.md` as history (sharp-oracle) keep them. ## 1. Detect convention Look at existing `handoffs/`: | What you see | New filename | |---|---| | `YYYY-MM-DD_*.md` | `handoffs/YYYY-MM-DD_<short-kebab>.md` (today's date, one-line topic) | | `handoff_*.md` | `handoffs/handoff_YYYY-MM-DD_HHMM.md` | | neither | `handoffs/YYYY-MM-DD_wrap-up.md` | Create `handoffs/` if missing. ## 2. Gather facts From **this** repo only: branch, `HEAD` short + subject, version if present, `git status --short`, commits on this branch since it diverged from its upstream (or last 12 hours if no upstream). ## 3. Write Match this repo's existing handoff shape if one is sitting there. If none, use: ```markdown # Handoff YYYY-MM-DD — <short title> HEAD: <sha> Version: <version or "n/a"> ## Shipped - [real bullets, files + outcome] ## State [where things stand. Learning / topics / todo / branches if this repo uses those lines] ## Next 1. [...] 2. [...] 3. [...] ``` Every section is real sentences. No placeholders, no "N/A" unless it is truly not applicable. ## 4. Engram (existing MCP) Use the **Engram** plugin tools already on the agent (`mem_save`, `mem_session_summary`). Do not add a second memory product. 1. `mem_save` — one observation per standing fact (decision / architecture / preference / bugfix). Reuse `topic_key` when the topic evolved. 2. `mem_session_summary` — Goal, Instructions, Discoveries, Accomplished, Next Steps, Relevant Files. Cloud VMs only share that write with the iMac / other agents when the account plugin wrapper has hydrated `~/.engram/cloud.json` (R2 `prompt-betting-engram/client.json`) and exported `ENGRAM_CLOUD_AUTOSYNC=1`. If hydrate skipped because Cloudflare creds are missing, still save locally **and** say the store is not replicated. ## 5. Commit (do not ship) ``` git add handoffs/<the-new-file> git commit -m "handoff: YYYY-MM-DD — <one-line summary>" ``` Push the **current** branch if this session already pushes to origin. Do not open a PR unless the session already uses PRs for this branch. Uncommitted other work: leave it uncommitted unless it was already meant to land; mention it under State. ## 6. Output ``` WRAP-UP ======= File: handoffs/<file> HEAD: <sha> Pushed: yes|no Engram: <topic_key list> | unavailable | saved-local-only (no cloud autosync) Next agent: /get-ready ```
From nhouseholder/cursor-laptop-skills, MIT.
More from nhouseholder/cursor-laptop-skills
- 0.524score
reflect
nhouseholder
Session retrospective — review what was accomplished in this session versus the original goal.
SkillBFreshness: BClaude Code +9 - 0.524score
estimate
nhouseholder
Effort, time, and complexity estimation before starting a task.
SkillBFreshness: BClaude Code +9 - 0.524score
debate
nhouseholder
Runs a formal 3-round debate between Claude (Proposer) and Gemini 3.1 Pro (Challenger), ending with an AI verdict via backend API.
SkillBFreshness: BClaude Code +9 - 0.524score
whats-next
nhouseholder
Strategic next-action prioritizer: anchors on the project's north star, scores impact vs effort vs confidence vs decay, filters already-killed work, and…
SkillBFreshness: BClaude Code +9 - 0.521score
kg
nhouseholder
Keep going — audit open work, pick the highest-leverage task, implement it end-to-end, verify, then immediately take the next highest-leverage step.
SkillBFreshness: BClaude Code +9 - 0.521score
clean-architecture-rebuild
nhouseholder
Same behavior; new seams / folders / decoupling.
SkillBFreshness: BClaude Code +9 - 0.521score
understand-and-refactor
nhouseholder
Join an unfamiliar product repo: map architecture and data flow, then apply the highest-ROI structural / duplication / perf / maintainability refactors.
SkillBFreshness: BClaude Code +9 - 0.521score
performance-optimize
nhouseholder
Performance engineer loop — speed, memory, scalability, extra rendering.
SkillBFreshness: BClaude Code +9 - 0.521score
fybr
nhouseholder
Follow your best recommendation — pick one course, execute it, do not interview.
SkillBFreshness: BClaude Code +9 - 0.521score
get-ready
nhouseholder
Session start, read-only.
SkillBFreshness: BClaude Code +9 - 0.521score
hq-law
nhouseholder
Always-on standing law for every Cloud Agent on any ProjectsHQ repo: honesty about what was run, fail-closed on unknowns, real-money safety for betting picks…
SkillBFreshness: BClaude Code +9 - 0.517score
tailscale-cloud
nhouseholder
ALWAYS ACTIVE on Cloud Agents.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 31, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from nhouseholder
- 0.524score
reflect
nhouseholder
Session retrospective — review what was accomplished in this session versus the original goal.
SkillBFreshness: BClaude Code +9 - 0.524score
whats-next
nhouseholder
Strategic next-action prioritizer: anchors on the project's north star, scores impact vs effort vs confidence vs decay, filters already-killed work, and…
SkillBFreshness: BClaude Code +9 - 0.524score
estimate
nhouseholder
Effort, time, and complexity estimation before starting a task.
SkillBFreshness: BClaude Code +9 - 0.524score
debate
nhouseholder
Runs a formal 3-round debate between Claude (Proposer) and Gemini 3.1 Pro (Challenger), ending with an AI verdict via backend API.
SkillBFreshness: BClaude Code +9 - 0.521score
clean-architecture-rebuild
nhouseholder
Same behavior; new seams / folders / decoupling.
SkillBFreshness: BClaude Code +9 - 0.521score
kg
nhouseholder
Keep going — audit open work, pick the highest-leverage task, implement it end-to-end, verify, then immediately take the next highest-leverage step.
SkillBFreshness: BClaude Code +9
Cite this page
wrap-up skill. Agent Mart. https://agentmart.dev/skills/nhouseholder-wrap-up (last updated 2026-10-24)