Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
rohitg00 avatar

Recap

  • 9k installs
  • 26.6k repo stars
  • Updated August 3, 2026
  • rohitg00/agentmemory

Time-windowed summary of agent sessions for the current project, grouped by date with key observation highlights

About

Recap generates time-windowed summaries of agent sessions for the current project, grouping completed work by calendar date with observation highlights. Developers invoke it when asking "what have we been doing" or "recap this week" to review recent progress without reading full session logs. The workflow queries memory_sessions with a time filter (today, last N days, this week), filters results to the current working directory, then pulls high-importance observations (score >=7) via memory_recall. Output shows session IDs, titles, observation counts, and indented highlights, ending with aggregate counts across the window.

  • Parses natural time windows: 'today', 'this week', 'last N' or defaults to last 10 sessions
  • Filters sessions to current project by matching cwd to working directory
  • Groups surviving sessions by local calendar date (YYYY-MM-DD) in descending order
  • Surfaces 2-3 high-importance observations (>=7) per session via memory_recall
  • Returns empty result if no sessions match the window, never invents activity

Recap by the numbers

  • 9,014 all-time installs (skills.sh)
  • +656 installs in the week ending Aug 5, 2026 (Skillselion tracking)
  • Ranked #95 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
  • Security screen: HIGH risk (skills.sh audit)
  • Data as of Aug 5, 2026 (Skillselion catalog sync)
At a glance

recap capabilities & compatibility

Capabilities
time window parsing · session filtering · date grouping · observation ranking · aggregate counting
Use cases
project management · memory · documentation
From the docs

What recap says it does

Summarize the last N agent sessions for the current project, grouped by date, with highlight observations per session.
SKILL.md
npx skills add https://github.com/rohitg00/agentmemory --skill recap

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs9k
repo stars26.6k
Security audit2 / 3 scanners passed
Last updatedAugust 3, 2026
Repositoryrohitg00/agentmemory

What it does

Summarize recent agent work sessions by date with key observations when developers need project progress rollups.

Who is it for?

Reviewing recent agent work, understanding project progress across sessions, preparing status updates

Skip if: Real-time session monitoring, detailed observation search, cross-project rollups

When should I use this skill?

User asks 'recap', 'what have we been doing', 'today', 'this week', or requests recent work summary

What you get

Date-grouped session summaries showing IDs, titles, observation counts, and top highlights with aggregate totals

  • Date-grouped session list
  • Session IDs (first 8 chars)
  • Observation counts

By the numbers

  • Defaults to last 10 sessions if no argument provided
  • Surfaces 2-3 highlights per session
  • Filters observations with importance >= 7

Files

SKILL.mdMarkdownGitHub ↗

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

Quick start

memory_sessions { "limit": 30 }

Then per surviving session: memory_recall { "query": "<top concepts>", "limit": 3 }.

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, filter to the current project (match cwd against the working directory), apply the 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. Indent 2-3 highlights (importance >= 7) from memory_recall. 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 ../_shared/TROUBLESHOOTING.md if memory_sessions or memory_recall is not available.

Related skills

How it compares

Pick recap over commit-history when you need session narratives and observations rather than git SHAs linked to agent work.

FAQ

What happens if no sessions match the time window?

Returns 'No sessions in the last N days for this project' - never invents activity from conversation memory

How does recap filter to the current project?

Matches session cwd field against the current working directory to exclude other projects

Where do the observation highlights come from?

Pulled via memory_recall querying top session concepts, filtered to importance >= 7, limited to 2-3 per session

Is Recap safe to install?

skills.sh reports 2 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.

AI & Agent Buildingagentsautomation

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.