clous-ai/platform-operation
clous-use/skills/platform-operation/SKILL.md
Use when an external AI agent needs to operate Clous safely across MCP, SDK, CLI, and API surfaces while preserving user/company context and avoiding unsafe mutations.
tools
Updated May 11, 2026
$ install --global
skillsauthnpx skillsauth add clous-ai/agents platform-operationInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 11, 2026, 2:32 AM109.6s1 file scanned
SKILL.md
- name:
- platform-operation
- description:
- Use when an external AI agent needs to operate Clous safely across MCP, SDK, CLI, and API surfaces while preserving user/company context and avoiding unsafe mutations.
Clous Platform Operation
Use this as the default operating skill for external AI agents using Clous.
Order of Operations
- Identify the user's goal, company context, and authorization surface.
- Prefer read-only discovery before mutation.
- Choose the safest interface: MCP first when the host has it, SDK/API second, CLI for automation and CI.
- Preserve object IDs, run IDs, and audit-relevant outputs.
- Summarize what changed and what still needs human review.
Safety Defaults
- Never export employee, candidate, or customer data without a stated destination and purpose.
- Do not execute write actions from browser push or passive notification payloads.
- Treat permission failures as real authorization boundaries, not retry prompts.
Related Skills
clous-ai/webhook-operations
development
VerifiedTrustedCommunity
Use when an AI agent needs to inspect, create, update, delete, or troubleshoot Clous webhook subscriptions and events.
SKILL.mdUpdated May 11, 2026
clous-ai/object-management
tools
VerifiedTrustedCommunity
Use when reading, creating, updating, or deleting Clous objects such as employees, candidates, jobs, reviews, skills, and forms.
SKILL.mdUpdated May 11, 2026
clous-ai/mcp-use
tools
VerifiedTrustedCommunity
Use when an AI agent can call Clous remote MCP tools to inspect or operate the Clous platform, HR, or employee surfaces.
SKILL.mdUpdated May 11, 2026
clous-ai/knowledge-retrieval
tools
VerifiedTrustedCommunity
Use when retrieving Clous HR knowledge, support docs, or system log context through Clous tool endpoints or MCP resources.
SKILL.mdUpdated May 11, 2026