← Back to Skills Marketplace
144
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install procedural-distiller
Description
Distill successful multi-step OpenClaw sessions into reusable learned skills before compaction. Use when a task involved many tool calls, environment setup,...
Usage Guidance
This skill does exactly what it says: it reads a provided trace JSON and writes a learned skill (SKILL.md, agents/openai.yaml, memory.json) containing concrete commands, file paths, and snippets. Before running: (1) inspect the trace for secrets, credentials, or sensitive paths and redact them if present; (2) run the script in a controlled environment and set --output-root to a directory you control; (3) consider lowering --max-events or raising --min-tool-calls to limit persisted data; (4) review generated files before sharing or committing them to version control. The tool does not exfiltrate data over the network, but it will persist whatever is in the trace—treat that output as potentially sensitive.
Capability Analysis
Type: OpenClaw Skill
Name: procedural-distiller
Version: 1.0.0
The procedural-distiller skill is a utility designed to extract successful workflows from OpenClaw session traces and save them as reusable learned skills. The core logic in distill_logic.py parses local JSON trace files, identifies successful tool patterns, and writes new skill definitions to the filesystem using standard libraries. No evidence of data exfiltration, malicious execution, or prompt injection was found; the script's file operations are restricted to the specified output directory and follow the stated purpose of session compaction and memory preservation.
Capability Assessment
Purpose & Capability
Name/description match the included SKILL.md and distill_logic.py. Required capabilities (reading a trace, extracting events, writing skill files) align with the stated goal. No unrelated credentials, binaries, or install steps are requested.
Instruction Scope
The runtime instructions and the script read a user-supplied trace JSON and write a learned skill (SKILL.md, agents/openai.yaml, memory.json) under a skills/learned/ directory. This is expected, but the workflow explicitly preserves concrete commands, file paths, and code snippets from the trace without sanitization, which could capture and persist sensitive data (secrets, credentials, absolute paths).
Install Mechanism
No install spec; this is an instruction-only skill with an included Python script. That is low-risk—nothing is downloaded or executed automatically beyond running the provided script locally.
Credentials
The skill requests no environment variables or credentials (proportional). However, because it serializes whatever is in the trace into persistent files, it may store sensitive environment-derived data present in traces. The absence of declared credentials is appropriate, but users should verify trace contents before distillation.
Persistence & Privilege
always is false and the skill only writes files into an output-root/learned skill directory (default 'skills/learned/...'). It does not modify other skills, system-wide agent settings, or request permanent platform privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install procedural-distiller - After installation, invoke the skill by name or use
/procedural-distiller - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of procedural-distiller skill:
- Automatically distills successful, multi-step OpenClaw sessions into reusable learned skills.
- Triggers only after successful completion involving at least 5 relevant tool calls.
- Extracts and organizes concrete steps, failure triggers, and useful code snippets from session traces.
- Saves distilled workflows as structured skills with metadata and utility scores for future reuse.
- Skips trivial, incomplete, or insufficiently detailed sessions.
Metadata
Frequently Asked Questions
What is procedural-distiller?
Distill successful multi-step OpenClaw sessions into reusable learned skills before compaction. Use when a task involved many tool calls, environment setup,... It is an AI Agent Skill for Claude Code / OpenClaw, with 144 downloads so far.
How do I install procedural-distiller?
Run "/install procedural-distiller" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is procedural-distiller free?
Yes, procedural-distiller is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does procedural-distiller support?
procedural-distiller is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created procedural-distiller?
It is built and maintained by 曹广雨 (@xiaocaijic); the current version is v1.0.0.
More Skills