steelmorgan/escalation-format
framework_eng/rules/escalation-format/SKILL.md
When escalating a decision, provide options and recommendation
$ install --global
skillsauthnpx skillsauth add steelmorgan/1c-agent-based-dev-framework escalation-formatInstall 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: Jun 30, 2026, 5:38 AM145.3s1 file scanned
SKILL.md
- name:
- escalation-format
- description:
- When escalating a decision, provide options and recommendation
- alwaysApply:
- true
Escalation Format for the User
Trigger: an orchestrator or subagent requests a user decision —
clarification_needed, iteration limit exceeded (3+ BLOCK), an architectural choice without an unambiguous source, a conflict between source-of-truth levels, etc. When triggered, apply theescalation-formatskill (framework/skills/agent-process/escalation-format/SKILL.md): it defines the message structure, grouping rules, and examples.
IMPORTANT — the filter for "when to escalate" is in
framework/workflows/orchestrator/SKILL.md§ 4 "The principle of 'delegate, don't ask'". This trigger only defines the reason to apply the format. Before escalating, the orchestrator/subagent MUST go through the filter in orchestrator.md and make sure the escalation is legitimate (admin operation / changing the L1-L2 contract / business decision / 3+ BLOCK / scope expansion). Technical choices and diagnostics do NOT require escalation — they are resolved by delegating to a subagent.
Invariant (always)
- It is forbidden to escalate "one question without context" — the user will not be able to choose without understanding the problems behind the question.
- It is forbidden to hide options in a single phrase ("accept or change the spec") — each option must be expanded: what changes, where, and at what cost.
- Applying the escalation format to a technical question (which is resolved by delegating to a subagent) = an error.
depends_on:
- framework/skills/agent-process/escalation-format/SKILL.md
- framework/workflows/orchestrator/SKILL.md
Related Skills
steelmorgan/onec-server-maintenance-hooks
development
VerifiedTrustedCommunity
1C server maintenance webhooks: container restart and external component cache cleanup
83SKILL.mdUpdated Jul 4, 2026
steelmorgan/dap-bsl-code-debug-procedure
development
VerifiedTrustedCommunity
Interactive DAP debugging of a single BSL procedure
83SKILL.mdUpdated Jul 4, 2026
steelmorgan/rlm-bsl-search
tools
VerifiedTrustedCommunity
Rules for using RLM tools for project search and navigation in 1C/BSL
83SKILL.mdUpdated Jul 4, 2026
steelmorgan/winow
development
VerifiedTrustedCommunity
Creates web applications and routes on Winow (a web server on OneScript and Autumn). Use when working with a web server on OneScript, routing, or Winow controllers.
83SKILL.mdUpdated Jul 4, 2026