Workflow Crystallizer
v1.1.0Analyze memory logs to detect recurring patterns and suggest automations — cron jobs, skills, or workflow shortcuts. The agent builds its own shortcuts over...
⭐ 0· 77·0 current·0 all-time
byNew Age Investments@newageinvestments25-byte
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & 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.Like a lobster shell, security has layers — review code before you run it.
latestvk973df3am2dftyaffc4nxadgk583n8f7
License
MIT-0
Free to use, modify, and redistribute. No attribution required.