All skills
deanpeters avatar

/incoming-request-advisor

@b68bf96

Decode an incoming message into a structured breakdown separating the literal ask from the job-to-be-done. Use when a loaded Slack ping, email, mandate, or escalation needs a reply.

Use this Skill: https://skilld.dev/gh/deanpeters/product-manager-skills/incoming-request-advisor

This session only. Nothing lands on disk.

examplesconversation-flow.md

≈919 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Example Conversation Flow — incoming-request-advisor

A full end-to-end interaction: message extraction, one gap-filling question, the rendered breakdown, and the closing options. Names and details are anonymized.


User:

incoming-request-advisor

Screenshot attached. It's a Slack thread. My eng lead posted it in our team channel this morning.

(attached image contains:)

Priya Nadel (Director of Engineering) "Team — leadership wants the AI summarization feature demoable by the all-hands on the 30th. I know discovery isn't done but we need SOMETHING on screen. Can product commit to a scope by EOD so we can start? Not looking for the full thing, just don't want to show up empty-handed."


Agent:

I've extracted the message. It's readable in full. One thing changes the read before I analyze:

Do you want analysis only, or a drafted reply too?


User:

Analysis first. I'll decide on a reply after.


Agent:

Incoming Request Breakdown

1. Classify

  • Mandate with deadline, Slack thread

2. Sender Read

  • Priya Nadel, Director of Engineering
  • Relationship: peer, high influence
  • Relaying leadership pressure downward

3. Literal Ask

  • Commit demo scope by EOD

4. Underlying Problem Space

  • Leadership wants visible AI progress
  • Job: avoid empty-handed all-hands
  • Outcome is credibility, not shipped feature

5. Sentiment and Subtext

  • Urgent, slightly defensive tone
  • Tell: "just don't want to show up empty-handed"
  • Cover-me energy, not malice

6. Must-Haves vs Nice-to-Haves

  • Must: something on screen by the 30th
  • Nice: real summarization accuracy

7. Hard Negatives

  • Not the full feature
  • No expectation of production quality

8. Success Criteria

  • Leadership sees credible progress (inference)
  • All-hands demo does not embarrass team (inference)

9. Hard Constraints

  • All-hands date: the 30th
  • Scope decision wanted by EOD

10. Gaps and Ambiguities

  • Who in leadership is actually asking
  • What "demoable" means to them
  • Is discovery still allowed to continue

11. Risks

  • EOD scope lock precedes discovery
  • Demo becomes the de facto spec
  • Scope creep after the demo lands

12. Recommended Next Steps

  • Confirm what leadership needs to see
  • Offer a thin demoable slice
  • Protect discovery timeline in writing

Assumptions to Validate

  • Success is credibility, not shipped feature
  • "Leadership" is unnamed and unconfirmed
  • Discovery can continue past the demo

Two questions sharpen this:

  1. Is the all-hands date on the 30th actually fixed, or aspirational?
  2. Does leadership need working software, or a credible plan-plus-mockup?

Now, pick your next move:

  1. Draft a reply to Priya (Recommended)
  2. Build a meeting agenda for this ask
  3. Reframe the ask as a discovery framing
  4. Draft a counter-proposal that protects the outcome

Reply with 1, 2, 3, 4, a combination like 1 and 4, or describe your own path.


User:

1 and 4


Agent:

Blending them: a reply to Priya that is the counter-proposal — commits to a thin, honest slice by the 30th while protecting the discovery track.

"Priya — yes, we'll have something demoable by the 30th. Proposing we show a working summarization slice on one real document type (support tickets), with a clear 'here's what's next' framing rather than implying it's done. That gets leadership a credible on-screen story without locking full scope before discovery closes. I'll send the one-pager by EOD. Sound right?"

Want me to tighten the tone, add the one-pager outline, or draft the discovery-protection note for leadership?

Source: SKILL.md on GitHub

1 alert1mo3 checks · Risk SAFE
  • Gen Agent Trust Hub1mo

    The skill is safe for its intended purpose of analyzing professional communication. It possesses a minor vulnerability to indirect prompt injection as it processes external messages, though it lacks the capabilities to perform dangerous actions.

  • Socket1mo

    No alerts

  • Snyk1mo

    Risk: HIGH · 2 issues

Signed by skilld at b68bf96. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last month.

Activeupdated 2 months ago
argument-hint
[paste or describe the incoming message + who sent it]
type
interactive
theme
stakeholder-comms
Other metadata
intent
Act as a chief-of-staff-grade analyst that decodes an incoming message into a structured breakdown, separating the literal ask from the job-to-be-done underneath it, reading sender power and stake from a product leader's chair, and opening the conversation toward a reply or next artifact. Trains the PM habit of finding the outcome before responding.
best_for
[
  "Triaging a loaded exec escalation before you fire back a reply",
  "Decoding a vague feature request into the outcome underneath it",
  "Reading power, stake, and subtext in a request from someone senior"
]
scenarios
[
  "My VP just Slacked me 'can we get the dashboard redesign into next sprint?' and I need to read what's really going on",
  "I got a long escalation email from a frustrated customer-success lead and I don't know how to respond",
  "A stakeholder sent a mandate that sounds like a build order and I want the job-to-be-done first"
]
estimated_time
5-10 min

README badge

README badge for deanpeters/product-manager-skills/incoming-request-advisor