agentleFS
egregore-labsegregore-labs/egregore/.claude/skills/wrap/SKILL.md

wrap

Skill293 starsChanged 10 days agoMITView on GitHub

Close the current Egregore session with a personal, canonical summary. Use for /wrap or when the user says they are done, wrapping up, or at a stopping point. Route work assigned to another person to /handoff and save-without-closing to /save.

46 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use start, remember and 8 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

  • 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

  • SentrySkill

    spec

    Produce a verified spec — problem, desired outcome, and acceptance criteria — before building. Use when given a GitHub/Linear issue link, when starting from a fuzzy in-conversation idea, or asked to "figure out what to do" / "scope this" / "what should I build" — whenever the *what* isn't yet pinned down. Grills the ambiguities, checks the premise against the code, and produces acceptance criteria you sign off on — then hands to design-first.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 2 are distinctive, and 6 are very specific to this project.

  • 0

    Common

    Most of the 40 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 6

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the proposed summary is materially ambiguous, show it once and ask for correction.

    line 28
  2. Very specific:

    If project changes need delivery, invoke /save once before the wrap.

    line 31
  3. Distinctive:

    Use this body shape, omitting empty sections:

    line 35
  4. Very specific:

    Write this body to the file tmp/wrap-body.md, then pass it to the Runtime-neutral wrap adapter in one command:

    line 57
  5. Very specific:

    Use {topic} for the short topic and {summary} for the two-to-four sentence summary derived from the session during preparation:

    line 64
  6. Very specific:

    Do not call artifact-writeback.sh, capture-run.sh, Git, QMD, graph, telemetry, publication, or notification mechanics directly.

    line 73
  7. Very specific:

    Keep open threads in the wrap even when they are also promoted through their own quest/todo/thread Runtime action.

    line 92
  8. Very specific:

    Do not claim graphed, published, notified, or shared unless a separate explicit action actually occurred.

    line 102

“Common” is measured: kept by at least 6 in 10 of the 40 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Personal session wrap

Record what this actor finished, what was verified, and what remains. A wrap is personal session closure, not a handoff, notification, publication, or claim that an organizational obligation is complete.

Canonical Markdown and Git provenance are authoritative. The Egregore Runtime owns authorization, stable ActorContext resolution, persistence, provenance, retrieval refresh, background embedding, and content-free telemetry through one writeback transaction.

When to invoke

Close the current Egregore session with a personal, canonical summary. Use for /wrap or when the user says they are done, wrapping up, or at a stopping point. Route work assigned to another person to /handoff and save-without-closing to /save.

Prepare

  1. Reuse the current conversation and relevant EGREGORE_ORG_CONTEXT_V1 evidence. Do not search organizational memory again merely to summarize the session.
  2. Derive a short topic, a two-to-four sentence summary, verified outcomes, and concise open threads. Separate completed work from unverified work.
  3. If the proposed summary is materially ambiguous, show it once and ask for correction. Skip confirmation when the user already supplied exact wrap wording.
  4. If project changes need delivery, invoke /save once before the wrap. That is a separate project-delivery action; do not reproduce Git commands in this skill and do not run a second save after canonical wrap succeeds.

Use this body shape, omitting empty sections:

## Summary

<what changed and the current state>

## Completed

- <completed outcome>

## Verification

- <test or check and its result>

## Open Threads

- [ ] <unfinished item or next step>

Write once

Write this body to the file tmp/wrap-body.md, then pass it to the Runtime-neutral wrap adapter in one command:

<body markdown>

Use {topic} for the short topic and {summary} for the two-to-four sentence summary derived from the session during preparation:

bash bin/agent.sh wrap \
  --topic '{topic}' \
  --summary '{summary}' --body-file tmp/wrap-body.md

Do not call artifact-writeback.sh, capture-run.sh, Git, QMD, graph, telemetry, publication, or notification mechanics directly. The adapter enters one personal canonical writeback transaction:

authorize → persist Markdown → Git provenance → retrieval update → background embed → telemetry

On success, report the returned memory/wraps/... path and the project save status. If the adapter fails, show the concise error and stop; never fall back to writing the file or updating projections directly.

Lifecycle boundary

  • A personal wrap never creates a recipient obligation; use /handoff for work another person must receive or continue.
  • A wrap never silently completes, expires, or supersedes a handoff, quest, todo, or thread. Age is not completion evidence.
  • The canonical wrap receipt may support a later, explicitly authorized lifecycle transition. That lifecycle service must verify the target, expected revision, actor membership, and typed evidence separately.
  • Keep open threads in the wrap even when they are also promoted through their own quest/todo/thread Runtime action.

Output

The adapter renders the wrap result card — actor, topic, summary, open-thread count, canonical path, and save/writeback status — as its stdout. The card is already fully visible there and must appear exactly once in the conversation. Never copy, re-render, summarize, or repeat it in your reply; add nothing beyond an answer to something the user separately asked. Do not claim graphed, published, notified, or shared unless a separate explicit action actually occurred.

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.