Install
$ agentstack add skill-mohitagw15856-pm-claude-skills-one-on-one-prep ✓ 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
One-on-One Prep Skill
The 1:1 is the highest-leverage meeting you have — and it's wasted when it defaults to status (which belongs in writing). This skill preps an agenda built around the outcomes you want: the decisions to unblock, the asks to make, the feedback to exchange, and the career threads to keep warm — so 30 minutes moves things instead of just reporting them.
Required Inputs
Ask for these only if they aren't already provided:
- Direction — prepping for a 1:1 with your manager (managing up) or with your report (managing down)? The agenda differs.
- What's on your mind — blockers, decisions, tensions, wins, career topics (rough notes are fine).
- Anything time-sensitive or any hard thing you've been avoiding raising.
- Last 1:1's follow-ups, if any.
Output Format
1:1 Prep — with [name], [date]
1. Top topics (most important first) — for each: the topic, the outcome you want, and the framing. Lead with what needs a decision or unblock, not updates.
| Topic | Outcome I want | How I'll frame it | |---|---|---|
2. Asks — explicit requests (a decision, air cover, a connection, time). Naming the ask is the point of the meeting.
3. Status — kept brief — 2–3 bullets of what they genuinely need to know; link the rest. Don't let this eat the meeting.
4. Feedback (both ways) — feedback to give (specific, kind, actionable) and a prompt to ask for feedback on yourself.
5. Growth / career — the longer-game thread to keep warm (a stretch goal, a development area, a promotion track).
6. Follow-ups — from last time, and what you'll commit to from this one.
Direction note: managing up → lead with decisions you need and asks; surface risks early; make it easy to help you. Managing down → lead with their agenda and growth, listen more than you talk, end with clear next steps.
Quality Checks
- [ ] Topics lead with a desired outcome, not a status recap
- [ ] At least one explicit ask is named
- [ ] Status is condensed to a few bullets (the rest written/linked)
- [ ] Feedback flows both ways, and is specific and actionable
- [ ] A growth/career thread is kept on the agenda, not just the urgent stuff
- [ ] The agenda is tuned to direction (managing up vs. down)
Anti-Patterns
- [ ] Do not turn the 1:1 into a status report — status belongs in writing; use the live time for decisions, feedback, and growth
- [ ] Do not avoid the hard topic — name it, framed constructively; the 1:1 is the safest place to raise it
- [ ] Do not arrive without an ask — "anything you need?" wastes the leverage
- [ ] Do not let career/growth fall off when things are busy — it's the first thing dropped and the most costly
- [ ] Do not over-pack — 3 real topics beat 10 skimmed
Based On
1:1 management practice (Andy Grove, High Output Management; manager-tools 1:1 cadence) — outcome-led agendas, managing up and down.
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.