EO
Escalate or Hold
🔵 Stable🕐 updated 2026-09-22
🔷 SkillSpec L3
pm-decisions
Decide whether an issue gets escalated now, held with a re-check time, or closed — as a typed decision with probabilities rather than a judgment call in a thread. Use when asked should I escalate this, is this a P1, do we page someone, hold or escalate, or when an on-call, support lead or PM is staring at an issue and unsure. Produces the issue state in a fixed schema, the three-way decision with probabilities and confidence, the act-or-hold verdict, and the re-check time when holding.
🗣 Say this to your agent
“Should I escalate this or wait for the owner's fix?”“Is this a page-someone situation?”“Third ticket on this today — hold or escalate?”
What to give it
▸issue — what happened, when first reported, current status
▸impact — customers or revenue affected, SLA state, any regulatory or safety angle
▸owner — who has it, their capacity, when they last updated
▸trend — worse, stable, or improving, with the evidence
▸prior_escalations — escalated before? what happened
▸asks — what the reporter is asking for
✅ The bar it holds itself to
Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.
✓Trend is stated with evidence, not assumed from severity
✓All three probabilities shown; the verdict cites the thresholds
✓A hold has a re-check time in hours and a named early trigger
✓The reporter gets one sentence with a time in it
✓Safety or regulatory angles, if present, are stated explicitly and force `escalate`
⚠️ What it refuses to do
**Escalating the loudest reporter** rather than the largest impact
**Holding without a clock** — "let's see how it goes" is not a hold, it is a drift
**Closing to reduce the queue** when impact was never verified
**Re-litigating the options** — inventing "soft escalate" to avoid paging someone
**Skipping the reporter line** — silence is how holds turn into escalations from above
Install
npx pm-claude-skills add --agent claude # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y pm-claude-skills-mcpRelated skills
🔌 Embed this skill
Drop this on your blog, docs, or site — it renders a "Run this skill" card:
<div data-pm-skill="escalate-or-hold"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>💬 Discussion
Escalate or Hold is one of 1182 open-source professional AI agent skills — all SkillSpec L3.
Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog