Workflow Crystallizer

Analyze memory logs to detect recurring patterns and suggest automations — cron jobs, skills, or workflow shortcuts. The agent builds its own shortcuts over...

Security Scan

The skill's code, instructions, and file access align with its stated purpose (mining local memory logs to detect recurring workflows and propose automations); it reads and caches local files and suggests cron/skill drafts but does not call external endpoints or request unrelated credentials.

Purpose & Capability

The name/description match the implementation: scripts parse memory/YYYY-MM-DD.md, extract events, cluster recurring patterns, and produce cron/skill/workflow/monitor suggestions. The generator also checks local cron jobs (~/.openclaw/cron/jobs.json) and existing skills directories to avoid duplicates — behavior consistent with deduplication and the stated purpose.

Instruction Scope

Runtime instructions direct the agent to run the included Python scripts over local memory files and to inspect or edit state.json. The scripts read the user's memory files and local OpenClaw cron/skills directories (home directory paths). This is coherent with the goal but means the skill will access potentially sensitive local memory content; the code does not contain network calls or external endpoints in the provided files.

Install Mechanism

There is no install spec — this is instruction-plus-scripts only. Nothing is downloaded or written outside the normal state.json and cache locations documented in the SKILL.md and state.py.

Credentials

The skill requests no environment variables or credentials. It does, however, read files from user home locations (memory files, ~/.openclaw/cron/jobs.json, and workspace/skills directories) and writes a local state.json. Those filesystem accesses are proportionate to the purpose (analyzing and deduplicating against existing automations) but have privacy implications because memory logs can be sensitive.

Persistence & Privilege

The skill intentionally persists state across runs (state.json) to track prior suggestions and avoid repeats; always:false (no forced global inclusion). It only generates cron definitions and skill drafts — it does not automatically register crons or publish new skills in the provided code. Scheduling via cron is suggested in documentation but requires the user to set up that cron. Overall privileges and persistence are consistent with its design.

Assessment

This skill appears to do what it says: it analyzes local memory logs and proposes automations while caching results in a local state.json. Important things to consider before installing/running it: (1) it will read your memory/YYYY-MM-DD.md files and other OpenClaw-related files under your home directory — these can contain sensitive information, so review the memory contents first or run the tool on a copied/sanitized dataset; (2) inspect the included scripts (they are all present) so you are comfortable they don't send data externally — the provided code shows no network/exfiltration calls; (3) the skill will write state.json (store suggestions and history) in the workspace — back it up if needed and review its contents periodically; (4) suggestions include ready-to-approve cron definitions and draft SKILL.md files but the scripts do not auto-deploy them — you must manually approve/instantiate automations; (5) if you plan to schedule it (cron/heartbeat), ensure the cron job and the agent executing it run with appropriate permissions and review outputs before allowing any automated enactment. If you want extra assurance, run the pipeline in a sandboxed environment or on a restricted copy of your memory files first.

Mines memory logs (memory/YYYY-MM-DD.md) for recurring patterns — repeated requests, multi-step workflows, time-correlated tasks — and generates actionable suggestions: cron jobs, skill drafts, workflow shortcuts, or monitoring proposals.

Unlike a one-shot "analyze my logs" prompt, this skill persists state across runs. It remembers what it suggested, what was accepted/rejected, and only surfaces new insights backed by real evidence.

All scripts live in scripts/ relative to this SKILL.md.

---

Quick Run (Full Pipeline)

cd /Users/openclaw/.openclaw/workspace/skills/workflow-crystallizer
python3 scripts/analyze_patterns.py --full | python3 scripts/generate_suggestions.py | python3 scripts/report.py --state-file state.json

This analyzes all memory files, generates suggestions, and prints a markdown report.

Incremental Run (Cached — Recommended)

cd /Users/openclaw/.openclaw/workspace/skills/workflow-crystallizer
python3 scripts/analyze_patterns.py | python3 scripts/generate_suggestions.py | python3 scripts/report.py --state-file state.json

Only processes new/modified memory files. Uses cached events from prior runs.

Managing Suggestions

Check state: python3 scripts/state.py — shows cached dates, events, suggestions.

To accept/reject/snooze: edit state.json directly. Set status to accepted, rejected (add rejection_reason), or snoozed. Or use state.py imports.

Reset everything: python3 scripts/state.py --reset

---

Individual Scripts

Each script accepts --help. Key options:

• analyze_patterns.py: --memory-dir PATH, --state-file PATH, --full, --min-confidence 0.4
• generate_suggestions.py: --state-file PATH, --cron-path PATH, --clusters FILE
• report.py: --state-file PATH, --output PATH, --clusters FILE, --suggestions FILE
• state.py: (no args = inspect state), --reset (clear everything)

---

What It Detects

Pattern Type	Evidence Needed	Suggestion Output
Recurring request	3+ occurrences, 2+ days	Workflow shortcut or monitor
Multi-step workflow	2+ occurrences with step similarity	Skill draft
Time-correlated	2+ at similar times/days	Cron job definition
Already formalized	Contains "cron", "automated", etc.	Skipped (no suggestion)
Project (not pattern)	Same entity, different actions	Skipped

See references/pattern-types.md for detailed detection logic and scoring weights.

---

How It Avoids Being Annoying

• Max 3 suggestions per run — quality over quantity
• Confidence threshold (60%) — no low-quality guesses
• Deduplication — checks existing crons and skills before suggesting
• Never repeats — tracks what was already suggested
• Snooze — deferred suggestions resurface after 30 days
• Rejected = dormant — only resurfaces at 80%+ confidence with new evidence

---

Scheduling

Run weekly via cron or heartbeat. Cost: ~5-10K tokens incremental, ~30K first run.

Name: Weekly Workflow Crystallizer
Schedule: 0 20 * * 0 (Sunday 8 PM ET)
Message: Run the workflow-crystallizer skill and present any new suggestions.

Troubleshooting

• No patterns: Need 3+ days of substantive memory files
• All filtered: Existing crons/skills already cover detected patterns
• State corrupt: python3 scripts/state.py --reset
• Too noisy: Increase min_confidence in state.json config