Skip to content
Skills Library
Management & product · Writing

session-closeout

/session-closeout

Use this skill when closing a finished task — writing the SUMMARY.md final report, the phase-09 retrospective, and task documentation in the workspace task dir. Don't use it for mid-task status updates or commit messages.

Repository
swarmery ↗
Licence
Apache-2.0
Last repository change
27.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
4
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 27.10.2026, without references to retired models or APIs.

Licence

Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.

What it does and when to use it

Use this skill when closing a finished task — writing the SUMMARY.md final report, the phase-09 retrospective, and task documentation in the workspace task dir. Don't use it for mid-task status updates or commit messages.

Original author description

Use this skill when closing a finished task — writing the SUMMARY.md final report, the phase-09 retrospective, and task documentation in the workspace task dir. Don't use it for mid-task status updates or commit messages.

How it works

  1. What it does
  2. When to use it
  3. How to invoke
  4. Worked example
Original SKILL.md headings · 56 lines, 435 words
SKILL.md preview
---
name: session-closeout
version: "1.1.0"
owner: "swarmery-core"
description: "Use this skill when closing a finished task — writing the SUMMARY.md final report, the phase-09 retrospective, and task documentation in the workspace task dir. Don't use it for mid-task status updates or commit messages."
color: yellow
docs:
  status: draft
  updated: 2026-09-01
---

# Purpose

Closing artifacts are how finished work becomes visible: the dashboard reads
`SUMMARY.md`, and the retro/advisor loop ingests `phases/09-retrospective.md`
and the delegation ledger. A task closed without them is invisible work.

# What to write

1. **`{task-dir}/SUMMARY.md`** (canonical final report, ≤300 lines) — exactly
   these seven sections: `## Результат`, `## Змінені файли`, `## Агенти`,
   `## Сесії`, `## Відхилення від плану`, `## Скріншоти`, `## Follow-ups`.
   Deviations compare actual agents/loops against ORCHESTRATION.md, not only
   the plan; the screenshots section lists `{task-dir}/screenshots/` files
   with captions or states "None captured". Format details:
   `resources/summary-format.md`.
2. **`{task-dir}/phases/09-retrospective.md`** (≤150 lines) — for non-trivial
   tasks. MUST use the machine-parsed headings: `## Lessons Learned` with
   `### Lesson N: <title>` subsections each carrying a `**Action**: …` line,
   and `## Process Improvements` (that exact heading — the ingester regexes
   match it, not synonyms). Read `{task-dir}/logs/agents.md` (7-cell ledger)
   first — its quality/mistakes cells are the evidence base. Format:
   `resources/retrospective-format.md`.
3. **`{task-dir}/plan/SUMMARY.md`** (≤120 lines) — for plan-driven tasks: the
   plain-language overview the dashboard shows at the top of the plan's
   Summary tab, above the per-phase reports. Written for the operator, not
   for an engineer: what the task was in plain words, what was built and how
   it works, where to see it, the headline numbers, what is left and what the
   operator has to do. No commit hashes or file paths in the body. Format:
   `resources/plan-summary-format.md`.
4. **Archive** when every criterion is met:
   `bash "${CLAUDE_PLUGIN_ROOT}/bin/agent-work.sh" complete {task-id}`. Never
   archive with unmet criteria or a missing SUMMARY.md — escalate instead.

Honesty rule: outcome is `Success | Partial | Failed` as it actually was;
lessons cite specific phases/files; a flattering retro poisons the
self-improvement loop.

# How to use

## What it does

Carries the closing-artifact contract for a finished task: the seven-section `SUMMARY.md`, the plain-language `plan/SUMMARY.md` overview, the machine-parseable retrospective, and the archive step — the formats the dashboard and the retro/advisor loop actually ingest.

## When to use it

At the end of any orchestrated or plan-driven task: the last checkbox is ticked, the work is verified, and the task dir needs its final report and retrospective before archiving.

## How to invoke

`@core:tech-lead` and `@core:implementation-agent` load it via `skills:` at close-out; load it manually when finishing a task by hand and follow `resources/summary-format.md`, `resources/plan-summary-format.md` and `resources/retrospective-format.md`.

## Worked example

After a 3-phase plan finishes, the orchestrator writes `SUMMARY.md` (result, changed files, agents used with loop counts, deviations: "phase 2 needed one correction loop — planned 0"), then `phases/09-retrospective.md` with `### Lesson 1: verify fixture DBs after migrations` and its `**Action**:` line under `## Lessons Learned`, one entry under `## Process Improvements`, and runs `agent-work.sh complete 2026-09-01-rate-limiting`.
Files in this package (4)
  • SKILL.md 4 KB
  • resources/plan-summary-format.md 2 KB
  • resources/retrospective-format.md 2 KB
  • resources/summary-format.md 2 KB

Versions

RepositoryScoreLicence
This page · atretyak1985/swarmery100Apache-2.0
CptNiemo/harness-patterns95MIT

Database snapshot: 13.11.2026 · package version 349ef2a15450 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100run-project-retrospective
    Runs a blameless retrospective for a Penroe project at closeout or the end of a phase. Builds the fact timeline from the plan against what actually happened, the risks that came true or were resolved, and how client sentiment moved, then facilitates what went well and what to…
  • 86closing-deliveries
    Closes a delivery: checks the order is done and proven, cleans the machine, updates documents, plan and commits, and writes the final report. Use before the final report of a delivery or session, and when the user says to stop, wrap up or that they are done for the day.
  • 86closing-deliveries
    Closes a delivery: checks the order is done and proven, cleans the machine, updates documents, plan and commits, and writes the final report. Use before the final report of a delivery or session, and when the user says to stop, wrap up or that they are done for the day.
  • 90task-closeout
    Close out a task before saying it is done; remove the scratch files it created, check the diff for private material and unsupported claims, write a handoff, or retire a branch or worktree. Use when finishing work, when asked for a handoff or session summary, or before deleting a…
  • 90plan-done-closeout
    Close a completed framework/app plan by updating concise plan state, moving plan records to completed, and appending decision history. Use when user says a plan is DONE and asks for closeout.
  • 100task-closeout
    Capture the current task into a structured temporary session bundle under `.agents/sessions/` so a learning agent can later distill durable repo knowledge. Use for completed, blocked, or abandoned tasks with meaningful changes, debugging, validation, or reusable lessons.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.