cintegrity/skill-plugin/SKILL.md
Use when search_tools, execute_tool, or execute_workflow tools are available. For multi-step operations, use execute_workflow with proper imports.
npx skillsauth add abilashraghuram/arrakis cintegrity-secure-tool-executionInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
search_tools(query) - Find tools and their schemasexecute_tool(tool_name, args) - Execute single toolexecute_workflow(planner_code) - Execute Python workflowfrom cintegrity.mcp_tools.<server> import <tool_name>
async def workflow():
result = await <tool_name>(arg=value)
return result
async def workflow():await for tool callstool(arg=value)Scalars (int, str, bool): Assign directly to variables
count = await add(a=10, b=5) # Returns: 15
total = await multiply(a=count, b=2) # Returns: 30
Objects (dict): Access fields by name
user = await get_user(id=123) # Returns: {"name": "Alice", "age": 30}
name = user["name"]
age = user["age"]
User Input: Request values with elicit()
c = await elicit(message="Enter value:", response_type=int) # Returns: 42
result = await compute(a=10, b=c)
from cintegrity.mcp_tools.database import get_user, update_score
async def workflow():
# Get user data (returns dict)
user = await get_user(user_id=123)
current_score = user["score"]
# Request bonus points
bonus = await elicit(message="Enter bonus points:", response_type=int)
# Calculate new score (scalar)
new_score = await update_score(user_id=123, score=current_score + bonus)
return {"user": user["name"], "new_score": new_score}
data-ai
Analyze datasets using pandas, generate reports, and create visualizations
tools
Use when work should span one or more detached tasks but still behave like one job with a single owner context. TaskFlow is the durable flow substrate under authoring layers like Lobster, ACPX, plugins, or plain code. Keep conditional logic in the caller; use TaskFlow for flow identity, child-task linkage, waiting state, revision-checked mutations, and user-facing emergence.
tools
# Lobster Lobster executes multi-step workflows with approval checkpoints. Use it when: - User wants a repeatable automation (triage, monitor, sync) - Actions need human approval before executing (send, post, delete) - Multiple tool calls should run as one deterministic operation ## When to use Lobster | User intent | Use Lobster? | | ------------------------------------------------------ | --------------------------
tools
# Lobster Lobster executes multi-step workflows with approval checkpoints. Use it when: - User wants a repeatable automation (triage, monitor, sync) - Actions need human approval before executing (send, post, delete) - Multiple tool calls should run as one deterministic operation ## When to use Lobster | User intent | Use Lobster? | | ------------------------------------------------------ | --------------------------