agentleFS
janelleciprianojanellecipriano/pm-skills/skills/escalation/SKILL.md

escalation

Skill1 starsChanged 5 months agoMITView on GitHub

Draft a clear, professional, unemotional escalation — the problem, impact, what's been tried, and a specific ask with a deadline. Use when the user says "escalate this", "write an escalation", "I need to raise this to leadership", "we're blocked and need help", or needs to ask for intervention without sounding alarmist or blaming.

8 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep it short and respectful.

    line 42

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Escalation

Draft an escalation that gets help fast by being calm, factual, and specific — not a complaint, a request for a decision or unblock.

When to use

  • A blocker, risk, or conflict needs a higher level of authority to resolve.
  • The user needs help framing a hard message constructively.

Principles

  • Facts, not feelings. Describe impact objectively; avoid blame and adjectives.
  • Lead with the ask. The reader should know within two sentences what you need from them.
  • Quantify impact. Tie it to dates, dollars, scope, or risk leadership cares about.
  • Show your work. What you've already tried signals this is a real escalation, not a first resort.
  • Make saying yes easy. Offer options and a recommendation; give a clear deadline.

Process

  1. State the ask up front: what decision/action/resource you need, from whom, by when.
  2. Describe the situation in 2–4 neutral sentences.
  3. Quantify the impact if unresolved (timeline, cost, scope, risk).
  4. Summarize what's been tried and why it wasn't enough.
  5. Offer options with a recommendation.
  6. Pick the right audience and channel and match the tone to the relationship.

Output format

**Subject:** Decision needed by {{date}}: {{one-line ask}}

**Ask:** {{specific request}} from {{name}} by {{date}}.
**Situation:** {{neutral facts}}
**Impact if unresolved:** {{quantified}}
**Tried so far:** {{what + outcome}}
**Options:**
1. {{option}} — {{trade-off}}  ← recommended
2. {{option}} — {{trade-off}}

Keep it short and respectful. Escalation is about the problem, never the person.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.