SkillHub

Skills rohitg00 agentmemory agentmemory

recap

Use it when:
You want a rollup of recent work: "recap", "what have we been doing", today or this week.
It does:
Fetches the project's sessions for the window you name, the last 10 by default, and searches memory for each one's highlights.
You get:
Sessions grouped by date with id, title, observation count, status and highlights, ending with a line of totals.
Needs:
agentmemory's memory server and MCP tools, plus its capture hooks recording your sessions: connecting the tools alone records no sessions.
Unlike session-history:
It takes a time window and groups the sessions by date.

Skill 6 of 8 in the agentmemory bundle, after session-history and before commit-history.

TL;DR

Part of agentmemory, a memory server that records what coding agents do in each session as observations. recap takes a window: today, this week (the last seven days), the last N sessions, or the last 10 when you give none. The agent fetches the project's sessions, paging until the window is covered, and matches them to this project by working directory when its identifier is unknown. It groups them by local date and lists each session's short id, title or first prompt, observation count and status, with highlights from a memory search, kept only when they belong to that session. It ends with a totals line: N sessions across M days, K observations. An empty window is reported as empty, not summarized from the conversation.

Summarizes the skill at f0f7378.

npx skills add https://github.com/rohitg00/agentmemory --skill recap

skills.sh pageSource on GitHubAll skills from rohitg00/agentmemory

Total Downloads
14,300 on skills.sh, Nov 9, 2026
Repo stars
30,216 rohitg00/agentmemory
First seen
May 18, 2026 on skills.sh
Weekly Downloads
261
-34% over the 8 weeks to Nov 9
Weekly values
Week toInstalls
Sep 21396
Sep 28372
Oct 5345
Oct 12314
Oct 19330
Oct 26321
Nov 2300
Nov 9261
Category
category:agentscategory:software-engineering

Build agents, orchestrate workers and give agents memory.

Everything for building software: planning, coding, debugging, design, frameworks, cloud, agents and skills.
Type
type:tool

Operates a CLI, API, app or bundled script to get something done.
Effect
effect:none

Adds no side effects of its own. It shapes how the agent thinks, writes or reviews. Guidelines and routers are always effect:none, even when the task they support edits code.
Needs
needs:mcp

Needs an MCP server connected.
Publisher
by:official

A verified publisher on skills.sh, or the company or maintainer behind the product the skill operates.
Topics
memory
Stack
stack:agentmemory

SKILL.md

From rohitg00/agentmemory at f0f7378. Checked daily, last changed Nov 6, 2026.

Frontmatter
name: recap
description: Summarize the last N agent sessions for the current project, grouped by date, with highlight observations per session. Use when the user asks "recap", "what have we been doing", "today", "this week", or wants a rollup of recent work.
argument-hint: "[last N | today | this week]"
user-invocable: true

The user wants a recap. Time window args: $ARGUMENTS

Quick start

memory_sessions { "project": "<current-project-id>", "limit": 30 }

Then per surviving session: memory_recall { "query": "<top concepts>", "project": "<current-project-id>", "limit": 3 }. When an agent is requested, pass the same agentId to both calls.

Expected output:

2026-06-07
  7f3a9c2 · "Auth refresh rework" · 14 obs · completed
    - [8] Rotate refresh tokens on every use
3 sessions across 2 days, 41 observations.

Why

Only summarize sessions and observations the tools returned. An empty window is a real answer, not a prompt to invent activity.

Workflow

  1. Parse $ARGUMENTS: today = current local date; this week = last 7 days; last <n> or bare numeric = most recent N; empty = last 10.
  2. Call memory_sessions with the exact recorded project identifier when known and the requested agentId. Follow nextCursor with the same filters until the requested window is covered or pages end. When the project identifier is unknown, match normalized cwd by directory boundary across pages before applying the time/count window. Sort by startedAt descending.
  3. Group survivors by local calendar date (YYYY-MM-DD).
  4. Per session list id (first 8), title or first prompt, observation count, status. Obtain highlights with memory_recall, retaining project/agent scope, and verify each result belongs to that session before including it.
  5. End with "N sessions across M days, K observations."

Anti-patterns

WRONG: window is empty, so you summarize "a productive week of auth work" from memory of the conversation.

RIGHT: "No sessions in the last 7 days for this project."

Checklist

  • Window parsed correctly from the argument.
  • Sessions filtered to the current project's cwd.
  • Highlights come from memory_recall, not paraphrase.
  • Totals line reflects the actual counts shown.

See also

  • handoff, session-history, recall: same session data, different lens.

Troubleshooting

See TROUBLESHOOTING.md if memory_sessions or memory_recall is not available.