Install
$ agentstack add skill-mohitagw15856-pm-claude-skills-managing-up ✓ 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
Managing Up Skill
Managing up isn't politics — it's making it easy for your manager to support you and trust you with more. That means understanding how they operate, communicating in their format, bringing solutions not just problems, and escalating the right things the right way. This skill turns "I need something from my boss" into a plan that lands.
Required Inputs
Ask for these only if they aren't already provided:
- The goal — what you need (a decision, resources, air cover, autonomy, a yes) or the situation to navigate.
- Your manager — how they operate: detail vs. headlines, written vs. verbal, risk-averse vs. bold, what they're measured on and worried about.
- The context — what's happened, any history, and the urgency.
Output Format
Managing Up: [the goal] with [manager]
1. What they need — read their world: the pressures they're under, what they're accountable for, and what makes their job easier or harder. You get support by helping them succeed, not just by asking.
2. Frame the ask in their terms — connect what you want to what they care about ("this de-risks the Q3 launch you're on the hook for"), in their preferred format (a 3-bullet Slack vs. a one-pager vs. a 1:1).
3. Bring vs. escalate — what to decide/handle yourself (and just inform them), vs. what genuinely needs their call. Bring a recommendation, not an open problem: "here's the issue, here are 2 options, I recommend A — do you agree?"
4. The message — a ready draft (Slack/email/1:1 talking points) that's concise, leads with the ask or headline, and makes saying yes easy.
5. Anticipate — their likely concern or pushback, and how you'll address it up front.
Cadence note — no surprises: flag risks early, keep them informed at their preferred altitude, and make your 1:1s about decisions and growth, not status.
Quality Checks
- [ ] The ask is framed in terms of what the manager is accountable for/worried about
- [ ] It's in the manager's preferred format and altitude (detail vs. headline)
- [ ] Problems come with a recommendation and options, not just the problem
- [ ] It's clear what you'll handle vs. what genuinely needs their decision
- [ ] Likely pushback is anticipated and pre-addressed
- [ ] The principle of "no surprises" is honoured (risks flagged early)
Anti-Patterns
- [ ] Do not bring a problem with no recommendation — "what should I do?" offloads your job; bring options + a pick
- [ ] Do not communicate in your preferred style — match theirs (a detail-lover and a headline-skimmer need different messages)
- [ ] Do not surprise your manager — surfacing a risk late is the fastest way to lose trust
- [ ] Do not escalate everything (looks like you can't decide) or nothing (looks like you hide things) — calibrate
- [ ] Do not frame the ask around what you want — connect it to what they're measured on
Based On
Managing-up practice — Drucker on managing the boss, Gabarro & Kotter's "Managing Your Boss," no-surprises and solution-oriented escalation.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: mohitagw15856
- Source: mohitagw15856/pm-claude-skills
- License: MIT
- Homepage: https://mohitagw15856.github.io/pm-claude-skills/
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.