agentleFS
Sign inStart free
phahadekphahadek/claude-orchestrator/skills/wrap/SKILL.md

wrap

Skill1 starsChanged 3 months agoMITView on GitHub

Wrap up a session: scan it for durable information that was produced or decided but never persisted to its proper home, surface each item with a proposed home, and — on your confirmation — write it there. Use when the user says "wrap", "wrap up", "wrap the session", "let's close out", or before ending a long working session. Nothing important should die with the session.

45 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use start, update and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • AnthropicSkill

    start

    Set up your bio-research environment and explore available tools. Use when first getting oriented with the plugin, checking which literature, drug-discovery, or visualization MCP servers are connected, or surveying available analysis skills before starting a new project.

    Also in 5 projects that use this

  • AnthropicSkill

    update

    Sync tasks and refresh memory from your current activity. Use when pulling new assignments from your project tracker into TASKS.md, triaging stale or overdue tasks, filling memory gaps for unknown people or projects, or running a comprehensive scan to catch todos buried in chat and email.

    Also in 3 projects that use this

  • LangChainSkill

    remember

    Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture learnings.

    Also in 3 projects that use this

  • termdockSkill

    recall

    Retrieves cross-session memories about past decisions, lessons, and patterns. Use when user asks about prior work, past decisions, or mentions a feature. Triggers include check memory, what did we decide, how did we solve.

    Also in 3 projects that use this

  • Microsoft AzureSkill

    build

    Build the TypeSpec Rust emitter from source. Run this after cloning the repo, after pulling changes, or when TypeScript source files have been modified.

    Also in 3 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 7 projects that use this

  • +1 more from anthropics

The file

Create a free account to mount
Files
SKILL.md

Wrap

Long sessions accumulate durable facts — decisions, gotchas, root causes, config locations, task/status changes, edits discussed-but-not-made — that are easy to leave un-written. Per the memory policy (procedures.md), durable context must live in procedures.md, a project context.md, Notion, or the code — never in per-Claude-Code memory. /wrap is the end-of-session checklist that catches what didn't make it home.

Step 1 — Scan the session

Review this session's transcript for durable items produced or discovered. Look for:

  • Decisions locked (design / architecture / process) not yet written to Notion or the rulebook.
  • Rules / conventions the human asked to "remember."
  • Gotchas, root causes, non-obvious facts discovered (a bug's mechanism, where a config lives, a fragile invariant).
  • Notion / task changes made or agreed but not applied (status flips, Depends On edits, tasks to file).
  • procedures.md / context.md edits discussed but never made.
  • Code fixes identified but neither applied nor filed as a task.

Step 2 — Classify each item by its correct home

Per the memory policy, propose exactly one home per item:

  • procedures.md — a universal, cross-project rule.
  • project context.md — a per-project fact or specific.
  • Notion — decisions, task definitions, source-of-truth docs (task page / architecture page / project context).
  • the code — if it's verifiable-in-source and belongs as a change → file a 🔲 Backlog task (never hand-edit a managed repo from here).
  • drop — ephemeral; no need to persist. Say so explicitly so it's a choice, not an oversight.

Step 3 — Present for sign-off

Show a compact table grouped by home: item → proposed home → the exact text/change you'd write. Recommend; don't dump. Keep it skimmable.

Step 4 — Persist confirmed items

On the human's confirmation, write each item to its home:

  • procedures.md / context.md → Edit.
  • Notion → the appropriate MCP update/create (new tasks start at 🔲 Backlog per config/task-writing.md).
  • code → file the 🔲 Backlog task.

Never silently persist. Never write to per-Claude-Code memory. If an item's home is ambiguous, ask rather than guess.

Step 5 — Report

Summarize what was persisted and where, plus anything the human declined — so every durable item ends the session either written down or deliberately dropped.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free