CtrlK
BlogDocsLog inGet started
Tessl Logo

remediation

**CRITICAL**: Use this skill for ALL CVE remediation workflows. DO NOT use individual skills piecemeal for end-to-end remediation. Use when users request: - CVE remediation playbooks or security patch deployment - Multi-step remediation (validation → context → playbook → execution) - Batch remediation across multiple systems or CVEs - End-to-end CVE management (analysis + remediation + verification) - Prioritizing and remediating CVEs (not just listing them) - Emergency security response with immediate remediation plans DO NOT use for simple queries: - "List critical CVEs" → Use `/cve-impact` skill - "What's the CVSS score for CVE-X?" → Use `/cve-impact` or `/cve-validation` - Standalone impact analysis without remediation → Use `/cve-impact` This skill orchestrates 6 specialized skills (cve-impact, cve-validation, system-context, playbook-generator, playbook-executor, remediation-verifier) for complete remediation workflows.

89

2.71x
Quality

85%

Does it follow best practices?

Impact

95%

2.71x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Evaluation results

87%

87%

CVE Remediation Kickoff Documentation

Upfront workflow plan presentation

Criteria
Without context
With context

MCP validation step

0%

100%

Impact analysis step

0%

100%

CVE validation step

0%

100%

System context step

0%

100%

Playbook generation step

0%

100%

Execution step

0%

100%

Verification step

0%

100%

All 7 steps present

0%

100%

Confirmation prompt included

0%

20%

Abort option in prompt

0%

0%

100%

55%

CVE Triage Runbook: Handling Unavailable Automated Remediation

Non-remediatable CVE gate handling

Criteria
Without context
With context

No automated remediation message

100%

100%

Manual patching alternative

100%

100%

Red Hat errata alternative

0%

100%

Continue anyway prompt

58%

100%

Yes path: proceed with warning

0%

100%

Warning language: may have no effect

0%

100%

No path: stop

100%

100%

Batch handling: skip non-remediatable

33%

100%

Batch warning consistent

0%

100%

Stop before further steps on no

50%

100%

100%

38%

Security Patch Deployment Approval Request

Pre-execution remediation plan format

Criteria
Without context
With context

Summary section present

100%

100%

Table with CVE column

100%

100%

Table with Target Systems column

100%

100%

Table with Key Action column

0%

100%

Ordered checklist present

100%

100%

Completed steps marked done

100%

100%

Confirmation prompt present

70%

100%

Yes/proceed option

30%

100%

Dry-run only option

0%

100%

Abort option

20%

100%

Repository
RHEcosystemAppEng/agentic-collections
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.