Weekly Retro

Weekly retrospective that analyzes memory logs to identify accomplishments, recurring patterns, friction points, and forward-looking recommendations. More st...

Security Scan

The skill's code, instructions, and defaults are coherent with its stated purpose of reading local memory logs, analyzing patterns, and producing a weekly retrospective; it does not request credentials or perform network activity.

Purpose & Capability

The name/description (weekly retrospective over memory logs) matches the included scripts and SKILL.md: gather_week.py reads memory files, analyze.py finds patterns, retrospective.py writes a markdown report, and history.py records longitudinal data. Defaults and example config point at local workspace files, which is appropriate for a retrospective tool.

Instruction Scope

Instructions operate on local markdown memory files (default ~/.openclaw/workspace/memory) and produce a vault/weekly-retro output; analyze.py can also read SOUL.md and AGENTS.md (if provided) and history.py reads/writes a history JSON. This is consistent with the tool's purpose, but it means the skill will read all content in the specified memory directory (and any additional files you point it at), so sensitive data in those logs will be included in analysis/output.

Install Mechanism

No install spec is provided; the skill is instruction/code-only and uses Python standard library only. Nothing is downloaded or executed from external URLs during installation.

Credentials

The skill requests no environment variables or credentials. The example config references local files (memory_dir, vault_output_dir, history_file, SOUL.md, AGENTS.md) which are reasonable for the function but may cause the tool to read additional workspace files if configured that way. No unexplained secrets or external service keys are required.

Persistence & Privilege

always is false and the skill does not request permanent platform-wide privileges. It writes output (markdown) and a history JSON into user workspace paths (configurable), which is expected for this functionality and scoped to its own data files.

Assessment

This skill appears to do what it says: read local memory logs, analyze patterns, and produce a markdown retrospective. Before running it: 1) Inspect the memory files that will be read (default ~/.openclaw/workspace/memory) for any secrets or sensitive content you don't want included; 2) Run the pipeline against a small test directory first (use --memory-dir to point to a safe test folder) to see output format; 3) Note that analyze.py can read SOUL.md and AGENTS.md if you pass those paths or configure them — don't point it at files with credentials; 4) The skill writes reports and a history file into your workspace (vault/history paths are configurable) — ensure those output locations are acceptable; 5) There is no network/exfiltration observed in the code, but always run third-party scripts in a controlled environment if you have high sensitivity requirements.

Generate a strategic weekly retrospective from memory log files.

Quick Start

Run the full pipeline:

python3 scripts/gather_week.py --memory-dir PATH | \
python3 scripts/analyze.py | \
python3 scripts/retrospective.py --output vault/weekly-retro/YYYY-MM-DD.md

Pipeline

Step	Script	Input	Output
1. Gather	gather_week.py	memory/*.md files	Structured JSON (per-day + aggregated)
2. Analyze	analyze.py	Gathered JSON	Pattern analysis JSON
3. Report	retrospective.py	Analysis JSON	Markdown retrospective

Scripts

gather_week.py

Read memory files for the past N days and extract structured data.

python3 scripts/gather_week.py --memory-dir ~/.openclaw/workspace/memory --days 7

Options:

• --memory-dir PATH — Path to memory directory (default: ~/.openclaw/workspace/memory)
• --days N — Number of days to look back (default: 7)
• --end-date YYYY-MM-DD — End date (default: today)
• --config PATH — Config JSON file

analyze.py

Detect patterns from gathered data. Reads JSON from stdin.

Identifies:

• Accomplishments (shipped, published, fixed, built)
• Recurring themes (topics appearing 3+ days)
• Repeated failures and friction points
• Time sinks (disproportionate attention)
• Unfinished threads (started but not completed)
• Work schedule patterns (time-of-day distribution)

python3 scripts/gather_week.py ... | python3 scripts/analyze.py

Options:

• --history-file PATH — Path to retro history for longitudinal comparison

retrospective.py

Generate the markdown retrospective. Reads analysis JSON from stdin.

Sections:

• Week at a Glance (3-sentence summary)
• Wins (with evidence)
• Patterns (recurring topics, toolchain, work schedule, attention distribution)
• Friction Points (with recurrence flags)
• Unfinished Business (carry-forward items)
• Recommendations (2-3 actionable changes for next week)
• Week Score (1-10 with justification)

python3 scripts/analyze.py ... | python3 scripts/retrospective.py --output PATH

Options:

• --output PATH — Write to file instead of stdout
• --no-frontmatter — Skip YAML frontmatter

history.py

Track retrospective history for longitudinal patterns.

python3 scripts/history.py --record --analysis analysis.json
python3 scripts/history.py --show
python3 scripts/history.py --trends

Options:

• --record — Record this week's analysis
• --analysis PATH — Analysis JSON to record
• --show — Show past retro summaries
• --trends — Show longitudinal trends
• --data-dir PATH — Storage directory

Cron Integration

Schedule a Sunday evening retrospective:

{
  "name": "Weekly Retrospective",
  "schedule": {"kind": "cron", "expr": "0 20 * * 0", "tz": "America/New_York"},
  "payload": {
    "kind": "agentTurn",
    "message": "Run the weekly-retro skill. Gather the past 7 days of memory logs, analyze patterns, generate the retrospective, and save to vault/weekly-retro/."
  }
}

Output

The retrospective is Obsidian-compatible markdown with YAML frontmatter including date range, week score, and auto-detected tags. Designed for vault storage and long-term pattern review.

Dependencies

Python standard library only. No external packages required.