Skip to content

hoavdc/CodexKit / skills/codexkit-okr-writer

codexkit-okr-writer

Verified

Write and cascade OKRs (Objectives and Key Results) for company, department, team, or project level. Ensure objectives are inspiring and key results are measurable outcomes. Includes weekly check-in template. Use at the start of each quarter or when aligning strategy to execution. Do not use for KPI performance reviews or daily task tracking.

FileKindSize
SKILL.mdskill md4.3 KB
agents/openai.yamlconfig155 B
examples/common-mistakes.mdmarkdown722 B
examples/good-output.mdmarkdown801 B
verification/checklist.mdmarkdown1.3 KB

verification/checklist.md

View on GitHub
# 4C Verification Checklist — OKR Writer

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

## Correctness — Is it right?

- [ ] Objectives are outcomes (what changes), not activities (what we do)
- [ ] Key Results are measurable with current instrumentation
- [ ] Baseline and target values are specified for every Key Result

## Completeness — Is it done?

- [ ] 3-5 Objectives with 2-4 Key Results each — not too many, not too few
- [ ] Alignment map shows how team OKRs connect to company-level OKRs
- [ ] Each KR has a scoring method defined (binary, percentage, threshold)

## Context-fit — Does it match?

- [ ] OKRs reflect the team's actual sphere of influence
- [ ] Ambition level matches the organization's OKR scoring convention (0.7 = good?)
- [ ] Timeframe is realistic for the scope of change expected

## Consequence — Is it safe to use?

- [ ] If the team achieves 100% on all KRs, will the Objective actually be met?
- [ ] If we optimize for these KRs at the expense of everything else, what breaks?
- [ ] Would a new team member understand what to prioritize from reading these OKRs?

---

**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: 470kUpdated 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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated 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: 322kUpdated Claude CodeCodexVerifiedInstall