Create a new skill from a capability gap (Evolution layer). When the system repeatedly fails on a topic, this generates a full skill package in vault/evolution/skills/<skill-id>/: - SKILL.md — procedure/SOP - tool.py — executable Python tool - metrics.json — fitness tracking - tests/test_cases.js...
AI agents use create_skill to create or update resources in Entroly Context Engine — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Entroly Context Engine environment.
The tool creates and writes new files and directories to persistent storage (vault/evolution/skills/). While reversible (files can be deleted), this modifies the codebase structure and introduces new executable Python tools (tool.py) into the system.
From the tool's definition Creates new skill packages in vault/evolution/skills/<skill-id>/ including SKILL.md, tool.py, metrics.json, and test_cases.json. This writes multiple files to the filesystem as part of an 'Evolution layer' capability system.
Documented attack patterns abuse exactly the kind of access create_skill gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Entroly Context Engine, and nothing reaches the server without passing your rules. This is the rule we recommend for create_skill:
{
"version": "1",
"default": "deny",
"tools": {
"create_skill": {
"limits": [
{
"counter": "create_skill_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_skill stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Create a new skill from a capability gap (Evolution layer). When the system repeatedly fails on a topic, this generates a full skill package in vault/evolution/skills/<skill-id>/: - SKILL.md — procedure/SOP - tool.py — executable Python tool - metrics.json — fitness tracking - tests/test_cases.json — regression tests Args: entity_key: The entity this skill handles (e.g., 'protobuf_analysis') failing_queries: Pipe-separated list of failing queries intent: The intent class for this skill. It is categorised as a Write tool in the Entroly Context Engine MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Entroly Context Engine MCP server in PolicyLayer and add a rule for create_skill: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Entroly Context Engine. Nothing to install.
create_skill is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_skill rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for create_skill. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
create_skill is provided by the Entroly Context Engine MCP server (juyterman1000/entroly). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Entroly Context Engine, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
52 Entroly Context Engine tools catalogued and risk-classified — across an index of 43,000+ MCP servers.