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 a local weekly-retrospective pipeline: it reads local memory files, analyzes them, and writes markdown/history to the user's vault — it does not request credentials or perform network calls.

Purpose & Capability

Name/description (weekly retrospective over memory logs) match the delivered artifacts: scripts parse memory Markdown files, analyze patterns, and generate retros. Required resources (local memory dir, history file, vault output) are proportional to the stated purpose; there are no unrelated env vars, binaries, or cloud credentials requested.

Instruction Scope

SKILL.md instructs the agent to read memory files (default ~/.openclaw/workspace/memory), pipe through analyze.py and retrospective.py, and optionally record history. The scripts also look for SOUL.md and AGENTS.md (to detect formalized workflows) and read/write a history.json under ~/.openclaw/workspace/skills/weekly-retro. This is within scope for a retrospective tool, but users should be aware the skill will read arbitrary files from the indicated memory and workspace paths.

Install Mechanism

No install spec; the skill is instruction + Python scripts using the standard library only. Nothing is downloaded or installed by the skill itself.

Credentials

The skill declares no required environment variables or credentials. The only file/system access is to local workspace paths (memory files, SOUL.md, AGENTS.md, history.json, vault output). Those permissions are consistent with a log-analysis/retrospective tool.

Persistence & Privilege

The skill is not always-enabled (always:false). It does persist state locally via history.json (expected for longitudinal tracking) and writes retros to a vault path. It does not modify other skills' configs and does not request elevated privileges.

Assessment

This skill appears internally consistent and intended to run locally. Before installing or running it: 1) Review or adjust the default paths in assets/config.example.json so the skill reads only the memory directories you intend (it defaults to ~/.openclaw/workspace/memory). 2) Be aware it will read local files like SOUL.md and AGENTS.md and will write history.json and markdown files to your vault/workspace; adjust locations or permissions if needed. 3) Because it reads your memory logs, ensure those logs don't contain secrets you don't want aggregated into retros. 4) The code uses only Python standard library (no network calls visible in the provided files), but if you plan to enable cron/automated runs, confirm the scheduled payload and timing are acceptable. 5) If you want extra caution, run the pipeline manually on a small sample folder first or inspect the scripts locally before giving the agent autonomous invocation rights.

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.