Install
$ agentstack add skill-ramanbamba-10x-pm-stakeholder-comms ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Stakeholder Comms
Draft the messages PMs dread sending. The formula for all of them: lead with the news, show your reasoning, preserve the relationship, and make the next step concrete. Never bury the point.
Before drafting
- Ask who the recipient is and what they care about — the same "no" reads differently to a sales lead protecting a deal versus an engineer protecting quality.
- Ask what the user's actual position is: is this a firm no, a "not now", a negotiation, or a done decision being communicated? The message must not pretend a decision is open when it's closed (cruelest failure mode) or closed when it's open.
- Ask the medium: Slack, email, or talking points for a live conversation. Match length and formality.
Message patterns
Pick the pattern; all share the spine news → reasoning → what survives → next step.
Saying no to a request:
- The decision, first sentence, unhedged. "We're not building X this quarter."
- The real reason, briefly — the tradeoff, not corporate fog. "It would displace Y, which serves 10× the accounts."
- Acknowledge what's legitimate in their ask — most requests contain a real problem even when the proposed solution is wrong. Name the problem.
- What you can offer: a workaround, a revisit trigger ("if two more enterprise accounts raise this"), or the criteria that would change the answer.
- Keep the door open on the relationship, not the decision.
Announcing a delay / de-scope:
- The news with the new date/scope, first sentence. No "quick update on timelines :)".
- Cause, honestly and without blaming individuals or teams.
- What you're doing so it doesn't recur (or an honest "this was an estimation miss").
- Impact on the recipient specifically, and what you need from them.
- Never announce a new date you don't believe. A second slip costs 10× the first.
Escalating a blocker:
- Frame as a decision request, not a complaint: "I need a decision between A and B by [date]."
- One paragraph of context — the escalation reader wasn't in the meetings.
- The two (max three) options with costs, and your recommendation.
- The default: what happens if no decision arrives by the date.
- Confirm the person being escalated around saw this framing first, or knows it's coming. Ask the user if unsure — surprise escalations burn bridges.
Pushing back on an executive:
- Steel-man their position first — show you understood the strategic intent.
- Present the data or constraint they may not have. New information, not re-argued preference.
- Offer a middle path where one honestly exists; don't invent fake compromises.
- End with commitment: "If you still want X knowing this, we'll execute well." Disagree-and-commit stated up front, not extracted later.
Workflow
- Identify the pattern; confirm the user's true position (firm/negotiable/closed).
- Draft in the user's voice, matched to medium. Default short: hard messages inflate with anxiety padding — cut it.
- Strip hedges that blur the news ("just", "sort of", "we're thinking maybe"). Keep softeners that serve the relationship ("I know this lands badly for the Northwind deal").
- Read it as the recipient: what's the first question they'll fire back? Add a P.S.-level answer or prep the user for it.
- Offer a 2-line and a full version when medium is ambiguous.
Quality bar — self-check
- News in the first sentence. If the first sentence could open a good-news message, rewrite.
- The decision's openness is represented honestly — no fake consultation, no fake finality.
- A real reason is given. "Bandwidth" and "priorities" are fog; the actual tradeoff is respect.
- Something constructive survives: workaround, revisit trigger, or decision criteria.
- No blame laundering. Systems and tradeoffs, not named individuals or "the eng team".
- Anticipates the recipient's first counter.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: ramanbamba
- Source: ramanbamba/10x-pm
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.