Install
$ agentstack add skill-amey-thakur-ai-skills-quarterly-planning ✓ 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
Quarterly planning
Quarterly planning turns ambition into a set of commitments a team can actually keep. It fails in a predictable way: capacity is counted as if everyone codes five days a week, dependencies are assumed rather than agreed, and every proposed item is marked "must" so nothing is ever cut until it slips. A real plan is honest about how much fits and explicit about what does not.
Method
- Start capacity from real available days, not headcount. Take the calendar,
subtract holidays, planned leave, on-call rotations, interviews, and a standing tax for support and keeping the lights on. A six-person team rarely has six people of new work; plan against the number that remains after the known drains.
- Size work in ranges and discount your optimism. Estimate each item as a
band, not a point, and apply a haircut to the total because teams systematically underestimate. If last quarter you planned twelve items and finished eight, plan eight this time. History beats hope.
- Negotiate every cross-team dependency in writing, both directions. For each
thing you need from another team, get their owner to agree to the scope and the date, and confirm what they need from you. An assumed dependency is a first-week surprise. "Platform confirms the API by week 3" beats "assuming platform is ready."
- Rank the full list and draw the cut line. Force a stack rank, then draw a
visible line where capacity runs out. Everything above the line is committed; everything below is explicitly not this quarter. The line is the deliverable: it makes the tradeoff a decision instead of a slow disappointment.
- Separate commitments from stretch and say which is which. Commitments are
promises other teams can build on; stretch goals are what you attempt if things go well. Labeling all of it "committed" destroys the word. Downstream teams need to know which dates they can bet on.
- Write down what you are deliberately not doing. A short "not this quarter"
list stops the same requests from reopening in week two and gives you a clean answer when new work arrives: it goes below the line or something above it moves.
Checks
- Does planned work fit inside real available days, or inside a headcount fantasy?
- Has every cross-team dependency been confirmed by the team you depend on?
- Can you point to the cut line and name what is above it and below it?
Boundaries
This plans a quarter of delivery; it does not set the strategy or the annual bets that decide what a quarter should even contain. Ceremony varies widely: OKRs, sprint planning, and big-room planning are different wrappers on the same honesty, so match your organization's format rather than importing another team's ritual.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Amey-Thakur
- Source: Amey-Thakur/AI-SKILLS
- License: MIT
- Homepage: https://amey-thakur.github.io/AI-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.