← Back to Skills Marketplace
284
Downloads
1
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install socrates
Description
Use when an agent is about to plan, choose an approach, do non-trivial coding, refactor, decompose work, or delegate and the quality of execution depends on...
Usage Guidance
This skill is instruction-only and internally consistent with its stated purpose: it only runs a short Socratic pass and uses bundled reference docs. It does not request credentials, install software, or contact external endpoints. If you enable it, be aware it may be invoked implicitly by agents (policy.allow_implicit_invocation is true) and that delegation sections assume child agents can be spawned — review your agent's delegation policies and any downstream sub-agents before allowing automated handoffs or exposing sensitive data during delegation.
Capability Analysis
Type: OpenClaw Skill
Name: socrates
Version: 0.1.1
The 'socrates' skill is a reasoning framework designed to improve the quality of an AI agent's output by enforcing a structured 'think-before-acting' protocol. The bundle consists entirely of Markdown instructions (SKILL.md, protocol.md, examples.md) and configuration files (agents/openai.yaml) that guide the agent to identify risks, assumptions, and goals before executing tasks. There is no executable code, no data exfiltration logic, and no evidence of malicious prompt injection intended to subvert the agent's safety or the user's intent.
Capability Assessment
Purpose & Capability
The name and description (a Socratic pre-flight for planning, coding, refactors, and delegation) align with the provided SKILL.md and reference documents. No unrelated binaries, env vars, or cloud creds are requested.
Instruction Scope
Runtime instructions are limited to running a concise Q&A pass, producing an Action Plan, and optionally a Delegation Contract. The skill references only its bundled reference files (references/protocol.md and references/examples.md). It does not instruct reading arbitrary host files, environment variables, or sending data to external endpoints.
Install Mechanism
No install spec and no code files; this is an instruction-only skill so nothing is written to disk or downloaded during installation.
Credentials
The skill requires no environment variables, credentials, or config paths. All required content is included in the package, so no external secrets or services are needed.
Persistence & Privilege
always:false (default) and no system modifications are requested. The agent metadata allows implicit invocation (policy.allow_implicit_invocation: true) which is reasonable for a helper skill; this is not flagged as a problem by itself.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install socrates - After installation, invoke the skill by name or use
/socrates - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.1
- Added LICENSE.txt and icon assets for clearer licensing and improved visual identification.
- Updated the skill description and documentation to clarify when and how to use the Socratic protocol, with a new quick trigger guide.
- Refined language to emphasize practical execution over philosophical discussion.
- No changes to the core protocol; documentation now stresses brevity and correct use cases.
v0.1.0
Initial release of the Socrates skill.
- Introduces a concise Socratic self-Q&A protocol to clarify goals, highlight unknowns, and reduce risk before action.
- Default flow includes one round of targeted questions; opens a second round only if unresolved ambiguity or risk remains.
- Supports task planning, architecture choice, non-trivial coding, refactors, decomposition, and work delegation to sub-agents.
- Includes clear rules for when to skip, compress, or run the full Socratic pass.
- Defines specific delegation handoff requirements and mini-Socratic pass for sub-agents.
- Provides strict guardrails to avoid unnecessary philosophy, verbosity, or redundant rounds.
Metadata
Frequently Asked Questions
What is Socrates?
Use when an agent is about to plan, choose an approach, do non-trivial coding, refactor, decompose work, or delegate and the quality of execution depends on... It is an AI Agent Skill for Claude Code / OpenClaw, with 284 downloads so far.
How do I install Socrates?
Run "/install socrates" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Socrates free?
Yes, Socrates is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Socrates support?
Socrates is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Socrates?
It is built and maintained by Hongyi3 (@hongyi3); the current version is v0.1.1.
More Skills