Summary
This one helps Claude figure out when to escalate a support issue versus handle it directly, then structures proper escalation briefs that give the next team what they need. It's got clear decision trees for when to keep working versus when to hand off, plus templates for documenting context so nothing gets lost in translation. Honestly pretty useful if you're building any kind of support workflow into your agent, since escalation logic is one of those things everyone implements slightly differently and usually half-broken. The skill comes from Anthropic's knowledge work plugins collection, which passed the major security audits and has decent adoption at 165 installs.
Install to Claude Code
npx -y skills add anthropics/knowledge-work-plugins --skill escalation --agent claude-codeInstalls into .claude/skills of the current project.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Files
SKILL.md
Select a file.
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
