Skip to content

hoavdc/CodexKit / skills/codexkit-okr-writer

codexkit-okr-writer

Unverified

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.

OKR Writer

Purpose

Create well-structured OKRs that connect strategic ambition to measurable outcomes, with proper cascade from company level down to team or project level.

When to use

  • quarterly or annual OKR setting cycles
  • aligning a new project to company strategy
  • when OKRs are vague, activity-based, or poorly measurable
  • creating a check-in cadence for tracking OKR progress

When not to use

  • KPI dashboards or operational metrics tracking
  • individual performance reviews or compensation decisions
  • daily or weekly task management

Inputs

  • organizational level (company / department / team / project)
  • strategic context or parent OKR to cascade from
  • time horizon (quarter, half-year, or annual)
  • current baseline metrics for proposed key results
  • known constraints or dependencies

Procedure

  1. Draft Objective — must be:
    • Inspiring and qualitative (no numbers in the objective)
    • Achievable within the time horizon
    • Within the team's sphere of influence
    • Example: "Become the most trusted partner for enterprise clients"
  2. Write 3–5 Key Results per Objective — each must be:
    • Measurable with a specific number
    • Outcome-based, not activity-based
    • Ambitious: 70% achievement = success
    • Template: "Increase/Reduce [metric] from [baseline] to [target] by [date]"
  3. Validate quality — reject common anti-patterns:
    • ❌ Activity KR: "Launch 3 features" → ✅ Outcome KR: "Increase feature adoption to 40%"
    • ❌ Binary KR: "Complete migration" → ✅ Measurable KR: "Migrate 95% of accounts by Q2"
  4. Cascade alignment — map each team OKR to its parent department/company OKR.
  5. Create check-in template for weekly or bi-weekly tracking:
    • Confidence score (0–10, where 7 = on track)
    • Current value vs target
    • Blockers and help needed
  6. Set scoring method — at quarter-end:
    • 0.0–0.3: Failed to make progress
    • 0.4–0.6: Made progress but fell short
    • 0.7–1.0: Delivered (0.7 is the sweet spot for stretch OKRs)

Output

  • complete OKR set (1–3 Objectives, each with 3–5 Key Results)
  • cascade alignment map to parent OKRs
  • baseline metrics and measurement plan
  • weekly check-in template
  • quarter-end scoring rubric

Definition of done

  • every Objective is qualitative and inspiring
  • every Key Result has a numeric target with baseline
  • no Key Result is activity-based
  • cascade to parent OKR is documented
  • check-in cadence is defined

Examples

  • "Write Q2 OKRs for the product team that align to the company goal of market expansion."
  • "Our team OKRs feel like a task list — help us rewrite them as outcome-based KRs."
  • "Create a weekly OKR check-in template for a 12-person engineering team."

Quality Criteria

  • All placeholder sections are filled with domain-specific content
  • Structure follows the relevant industry standard or framework
  • Language matches target audience (technical / executive / legal)
  • Output is ready for review — not a rough draft requiring major rework

Verification (4C)

CheckQuestion
CorrectnessDoes the draft structure follow the stated framework or industry standard?
CompletenessAre all required sections present with substantive (not placeholder) content?
Context-fitDoes tone, detail level, and terminology match the intended audience?
ConsequenceIf sent to the intended recipient without further editing, what would fail?

Edge Cases

  • No existing template for this type — Use the closest available template and document all customizations made.
  • Stakeholder requirements conflict — Flag conflicts explicitly in the draft. Do not silently choose one requirement over another.
  • Output required in multiple formats — Produce the canonical format first, then derive others. Note any formatting limitations.

Changelog

  • v1.0.0 — Initial release
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: 464kUpdated Claude CodeCodexVerifiedInstall
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: 464kUpdated 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: 318kUpdated Claude CodeCodexUnverifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 318kUpdated Claude CodeCodexUnverifiedInstall