Synthesizes session progress, saves notes, and creates a wrap-up report for Egregore sessions.
Install
mkdir -p .claude/skills/wrap-egregore-labs && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/17491" && unzip -o skill.zip -d .claude/skills/wrap-egregore-labs && rm skill.zipInstalls to .claude/skills/wrap-egregore-labs
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Wrap an Egregore session when the user invokes /wrap or $wrap, or says they are done, wrapping up, or at a stopping point in Codex.Key capabilities
- →Synthesize a topic, summary, and open notes
- →Confirm session state if ambiguous
- →Resolve the author from state or git config
- →Write notes to a temporary markdown file
- →Run agent.sh wrap command
How it works
The skill synthesizes a summary and notes from the session, confirms state if needed, resolves the author, writes notes to a file, and executes the wrap command, optionally saving code changes.
Inputs & outputs
When to use wrap
- →End session
- →Wrap up project work
- →Save session summary
About this skill
Egregore wrap Adapter
This adapter runs the canonical Egregore workflow for wrap. Its one
maintained body is .claude/skills/wrap/SKILL.md; read that file completely and follow it here.
Use the project shell and filesystem directly. Do not invoke Claude Code
commands. Translate interactive choices to structured Codex question tooling
when it is available; otherwise render compact numbered choices with an
Other: option and wait for the user.
Structured UX parity
This workflow has a Claude skill with user-visible structured output. After
reading .claude/skills/wrap/SKILL.md, reproduce the same visible UX in Codex:
- Preserve TUI boxes, markdown tables, rich cards, browser artifact rendering, exact confirmation blocks, and "no preamble" rules from the source skill.
- Use the source skill's frame width, section order, labels, status footer, and examples as the contract for the final response.
- Never replace a required box/table/card/artifact view with a prose summary unless the user explicitly asks for a summary.
- When the source says to output a TUI box directly, paste that box as the
visible response, preferably in a
textfenced block. - If the canonical body says the command's stdout is the card and must not
be repeated, that rule assumes a host that displays command output in full;
in Codex, paste the card once as the visible response in a
textfenced block and do not print it a second time. - Never show raw JSON, raw command output, or unformatted script output when the source skill requires formatted status or rendered output.
- Read
.claude/skills/wrap/SKILL.mdfor the workflow details. - Run the referenced
bin/scripts directly from Codex. - Treat graph and publish steps as best-effort unless that workflow explicitly says they are required.
- For every external notification, follow
.claude/context/notification-consent.md: plan without sending, then show a separate exact Send / Edit / Cancel checkpoint. Never infer notification consent from the workflow request or a batch approval. - Keep local-mode behavior filesystem-first and avoid graph or notification
calls when
egregore.jsondeclares"mode": "local". - Never call the deprecated
egregore-handoffCLI for Egregore project handoffs.
When not to use it
- →When the user wants to invent finished work
- →When the user wants to leave local commits untouched after save failure
Limitations
- →Do not use Claude Code commands
- →Do not invent finished work
- →If save fails, report the failure and leave the local commits untouched
How it compares
This skill provides a structured, user-facing wrap-up confirmation with specific output formatting, unlike a simple prose summary of the session.
Compared to similar skills
wrap side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| wrap (this skill) | 0 | 4mo | Review | Beginner |
| notion-meeting-intelligence | 6 | 8mo | No flags | Intermediate |
| resume-handoff | 3 | 9mo | No flags | Intermediate |
| meeting-briefing | 2 | 8mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by egregore-labs
View all by egregore-labs →You might also like
notion-meeting-intelligence
openai
Prepare meeting materials with Notion context and Codex research; use when gathering context, drafting agendas/pre-reads, and tailoring materials to attendees.
resume-handoff
parcadei
Resume work from handoff document with context analysis and validation
meeting-briefing
anthropics
Prepare structured briefings for meetings with legal relevance and track resulting action items. Use when preparing for contract negotiations, board meetings, compliance reviews, or any meeting where legal context, background research, or action tracking is needed.
personal-assistant
ailabs-393
This skill should be used whenever users request personal assistance tasks such as schedule management, task tracking, reminder setting, habit monitoring, productivity advice, time management, or any query requiring personalized responses based on user preferences and context. On first use, collects comprehensive user information including schedule, working habits, preferences, goals, and routines. Maintains an intelligent database that automatically organizes and prioritizes information, keeping relevant data and discarding outdated context.
digital-brain
muratcankoylan
This skill should be used when the user asks to "write a post", "check my voice", "look up contact", "prepare for meeting", "weekly review", "track goals", or mentions personal brand, content creation, network management, or voice consistency.
meeting-sync
amanaiproduct
Sync new Granola meetings to local Knowledge folder. Use during morning planning, when user asks "what should I do today", or asks to review/sync meetings.