A strategic analysis pipeline that transforms daily memory logs into high-level retrospectives to identify work patterns and friction points.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install weekly-retro
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install weekly-retro using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
Weekly Retro is a sophisticated analytical framework designed for the Openclaw Skills ecosystem. Unlike simple daily recaps, this skill performs a deep-dive longitudinal analysis of an AI agent's memory logs over a seven-day period. It is engineered to answer the critical question: what should change next week?
By processing raw memory files through a multi-stage pipeline, Weekly Retro identifies recurring themes, repeated failures, and time sinks that are often invisible in day-to-day operations. It provides developers and knowledge workers with a data-driven mirror of their work week, enabling continuous improvement through structured reflection.
gather_week.py script scans the memory directory to extract and structure data from the last N days.analyze.py script processes the gathered data to detect patterns, such as themes appearing more than three times or disproportionate time sinks.retrospective.py script synthesizes the analysis into a human-readable Markdown report with strategic recommendations.history.py script records the analysis into a longitudinal database to track trends over months or years.To integrate this into your environment, ensure you have the Openclaw Skills scripts available. The pipeline relies on standard Python libraries.
# Run the full retrospective pipeline
python3 scripts/gather_week.py --memory-dir ~/.openclaw/workspace/memory | \
python3 scripts/analyze.py | \
python3 scripts/retrospective.py --output vault/weekly-retro/$(date +%F).md
The skill produces Obsidian-compatible Markdown files with rich YAML frontmatter. Data is organized as follows:
| Component | Type | Description |
|---|---|---|
| Frontmatter | YAML | Contains date ranges, auto-detected tags, and a numerical week score. |
| Wins | List | Evidence-based accomplishments (shipped, fixed, built). |
| Patterns | Analysis | Recurring topics and work schedule distribution. |
| Friction Points | Issues | Repeated failures or bottlenecks encountered during the week. |
| Recommendations | Actionable | 2-3 specific changes suggested for the upcoming week. |
Loading
A local, CLI-driven 3D printing filament inventory manager for tracking spool usage, stock levels, and material costs.

A comprehensive digital garden assistant for tracking plant growth stages, automating watering schedules, and receiving localized frost warnings.

An AI-powered multi-factor analysis engine providing structured market insights and trading vibes for stocks and crypto.

An intelligent pattern-mining tool that transforms recurring memory logs into actionable automation suggestions like cron jobs and skill drafts.

Screen Reviewer is an automated monitoring tool that captures screenshots, extracts text via OCR, and uses AI to generate structured daily productivity reports.

A powerful orchestrator that fetches Jira issues, processes log attachments, and generates detailed Markdown reports via subagents.

An automated monitoring tool for GitHub repositories and npm packages that highlights breaking changes in new releases.








































