Skip to content

hoavdc/CodexKit / skills/codexkit-sprint-planning-assistant

codexkit-sprint-planning-assistant

Verified

Facilitate sprint planning by organizing backlog items, estimating effort, balancing capacity, identifying dependencies, and producing a sprint commitment summary. Use when teams need structured sprint planning output. Do not use for strategic roadmap planning, annual budgeting, or product vision work.

FileKindSize
SKILL.mdskill md3.5 KB
agents/openai.yamlconfig170 B
examples/common-mistakes.mdmarkdown810 B
examples/good-output.mdmarkdown794 B
verification/checklist.mdmarkdown1.3 KB

verification/checklist.md

View on GitHub
# 4C Verification Checklist — Sprint Planning Assistant

> Use this checklist after generating output. Answer each question honestly.

## Correctness — Is it right?

- [ ] Story points or estimates reflect actual complexity, not wishful thinking
- [ ] Sprint goal is achievable given team capacity (accounting for PTO, on-call, meetings)
- [ ] Dependencies on other teams are confirmed, not assumed

## Completeness — Is it done?

- [ ] All stories have acceptance criteria before entering the sprint
- [ ] Capacity calculation accounts for velocity average, not just last sprint
- [ ] Carry-over items from previous sprint are explicitly tracked

## Context-fit — Does it match?

- [ ] Sprint scope aligns with the current quarter's OKRs
- [ ] Mix of features, bugs, and tech debt reflects agreed ratios
- [ ] Team confidence in the plan is captured (fist-of-five or similar)

## Consequence — Is it safe to use?

- [ ] If the team completes only 70% of planned work, are the right 70% prioritized?
- [ ] If a mid-sprint emergency pulls 1 engineer, which stories are dropped?
- [ ] If stakeholders review this sprint plan, will they agree with the priorities?

---

**Final question:** _If this output were used immediately in production, what is the single biggest risk?_

Write the answer here before considering the skill output complete.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 469kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 321kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 321kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 321kUpdated Claude CodeCodexVerifiedInstall