Automated summary
Reviews session history, decisions, and project progress over time.
Strengths
- Provides a quick overview of recent activity via time-period summaries.
- Automatically generates standup and retrospective notes.
- Allows reviewing past decisions with full context.
- Searches across history using text queries.
Limitations
- Requires sessions and decisions to be recorded in .claude/memory files.
- Summaries are limited to already collected data—no external synthesis.
- Search depends on the memory file format.
Use for preparing standups, retrospectives, or understanding project progress over a specific period.
Avoid if session history is not maintained or if real-time deep analysis is needed.
Security analysis
SafeThis skill only reads internal project memory files and generates review summaries; no dangerous operations are instructed.
No concerns found
How this analysis is madeExamples
Show me the recent activity from the last week.Generate a standup summary for today.Review decision #0005.description: Review session history, decisions, and project progress over time. Use for weekly reviews, standups, retrospectives, or understanding past work.
Memory Review
Review and analyze session history, decisions, and project progress over time.
Instructions
When this skill is triggered, determine the user's intent:
Intent: Recent Activity Overview
Default view when no specific request:
Memory Review
Period: Last 7 days (2024-01-08 to 2024-01-15)
## Sessions: 8 recorded
| Date | Duration | Focus | Key Outcome |
|------|----------|-------|-------------|
| Jan 15 | 2.5h | Auth refactor | Completed token refresh |
| Jan 14 | 1.5h | Auth refactor | Fixed race condition |
| Jan 13 | 3h | Auth refactor | Started Phase 2 |
| Jan 12 | 2h | Bug fixes | Resolved 3 issues |
## Decisions: 3 made
- #0005: Exponential backoff for retries (Jan 14)
- #0004: Token bucket rate limiting (Jan 12)
- #0003: PostgreSQL for session storage (Jan 10)
## Knowledge: 2 updates
- authentication.md: Added rate limiting section
- api-patterns.md: Added retry patterns
Commands:
- "details [date]" - Show specific session
- "decision [number]" - Review a decision
- "this week" / "last week" / "this month"
- "search [query]" - Find in history
- "standup" - Generate standup summary
- "retro" - Generate retrospective notes
Intent: Time-Based Review
This Week / Last Week / This Month
Generate summary for the specified period including:
- Session count and total time
- Main focus areas
- Accomplishments
- Decisions made
- Discoveries
- Blockers encountered
Intent: Generate Standup Summary
If user asks for standup:
## Standup Summary
**Yesterday**:
- Completed token refresh implementation
- Fixed race condition in auth middleware
- Added retry logic with exponential backoff
**Today**:
- Continue Phase 2: Token rotation
- Write tests for refresh flow
- Start Redis connection pooling
**Blockers**:
- None currently
Intent: Generate Retrospective
If user asks for retro/retrospective:
## Retrospective: Auth Refactor
### What Went Well
- Clear plan helped track progress
- Decision records captured rationale
- Finding about race condition saved debugging time later
### What Could Be Improved
- Underestimated complexity of token rotation
- Should have checked API rate limits earlier
### Action Items
- [ ] Add API limit checking to research phase
- [ ] Create template for concurrent code review
### Key Learnings
- Always check for race conditions in token handling
- Token bucket is better than fixed window for rate limiting
Intent: Review Specific Decision
If user asks about a specific decision:
- Read the decision file
- Show full content with formatting
- Note if it has been superseded
Intent: Search History
If user wants to find something:
Delegate to /memory-search skill.
File Paths
- Sessions:
.claude/memory/sessions/ - Decisions:
.claude/memory/decisions/ - Knowledge:
.claude/memory/knowledge/
Related Skills
/memory-search- Search across memory files/memory-status- Current state overview
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/memory-review-mm8o52gq/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/memory-review-mm8o52gq' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/memory-review-mm8o52gq/download' --output '.skill-downloads/memory-review-mm8o52gq/SKILL.md.part' && mv '.skill-downloads/memory-review-mm8o52gq/SKILL.md.part' '.skill-downloads/memory-review-mm8o52gq/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.
Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/memory-review-mm8o52gq/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
PDF Reader
Productivity
Read and extract text from PDF files, including documents, reports, contracts, and spreadsheets. Works with local files, URLs, and WhatsApp attachments. Use whenever PDF content is needed, even if not explicitly requested.
Discord Messaging Workflows
Productivity
Use the message tool to send, edit, and moderate Discord messages with interactive components.
Interactive Verdict Preview
Productivity
Generate an interactive HTML preview of keep/drop verdicts for maintainer review, then process the pasted feedback JSON.