bkr1297-RIO/agent-skills/interaction-monitor
agent-skills/interaction-monitor/SKILL.md
# SKILL: Interaction Monitor **Status:** Non-normative (Advisory Only) > This document defines a skill: a bounded way to use RIO. > It is NOT part of the RIO standard or enforcement mechanism. --- ## Purpose Monitor interactions for: - Ambiguity - Drift - Mismatch - False agreement This skill provides awareness and advisory signals. It does not execute, authorize, or route. --- ## Capabilities This skill MAY: - Detect ambiguity in intent or instructions - Detect drift between stated i
documentation
Updated Apr 23, 2026
$ install --global
skillsauthnpx skillsauth add bkr1297-RIO/rio-protocol agent-skills/interaction-monitorInstall 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: Apr 24, 2026, 3:08 AM63.0s1 file scanned
SKILL.md
SKILL: Interaction Monitor
Status: Non-normative (Advisory Only)
This document defines a skill: a bounded way to use RIO. It is NOT part of the RIO standard or enforcement mechanism.
Purpose
Monitor interactions for:
- Ambiguity
- Drift
- Mismatch
- False agreement
This skill provides awareness and advisory signals. It does not execute, authorize, or route.
Capabilities
This skill MAY:
- Detect ambiguity in intent or instructions
- Detect drift between stated intent and proposed action
- Detect mismatch between expected and actual outcomes
- Emit advisory signals for humans or other skills to consider
MUST NOT
This skill MUST NOT:
- Authorize actions
- Execute actions
- Route or trigger execution
- Modify tokens, receipts, or ledger
- Modify system state
- Generate or modify authorization mechanisms
It may only observe and advise.
Related Skills
bkr1297-RIO/agent-skills/enforcement
testing
VerifiedTrustedCommunity
# SKILL: RIO Enforcement (Execution Boundary) **Status:** Non-normative (Advisory Only) > This document defines a skill: a bounded way to use RIO. > It is NOT part of the RIO standard or enforcement mechanism. --- ## Purpose Use this skill when you need to: - Check whether a proposed action is admissible under RIO - Submit an authorized action for execution via the Gate - Obtain the resulting receipt and ledger reference The Gate is the only way actions become real. --- ## MUST NOT Whe
SKILL.mdUpdated Apr 23, 2026
steipete/gh-issues
documentation
VerifiedTrustedCommunity
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5] [--notify-channel -1002381931352]
356,423SKILL.mdUpdated Apr 13, 2026
steipete/wiki-maintainer
documentation
VerifiedTrustedCommunity
Maintain the OpenClaw memory wiki vault with deterministic pages, managed blocks, and source-backed updates.
356,423SKILL.mdUpdated Apr 13, 2026
steipete/feishu-wiki
documentation
VerifiedTrustedCommunity
Feishu knowledge base navigation. Activate when user mentions knowledge base, wiki, or wiki links.
356,423SKILL.mdUpdated Apr 13, 2026