Foundation Okr Writer
Point this at a planning cycle and it will draft or audit an OKR set, but the part worth your attention is how strict it is. It runs five modes (Guided by default, One-Shot via --oneshot, Sustained Coach, Audit Only, and Rewrite), and it pushes back on the usual failure modes: feature lists dressed up as key results, invented baselines, and targets with no evidence source. It also refuses to tie OKR scores to compensation and will add a disclosure section when the team is working from committed features rather than real outcome ownership. My honest take is that the empowered-team diagnostic is the most useful piece, since it forces a conversation most teams skip. The tradeoff is that it will feel slow if you just want a quick draft, so use --oneshot when you're in a hurry.
- skills.sh installs
- 776
- GitHub stars
- 794
- last updated
- Aug 4, 2026
Install
$ npx -y skills add product-on-purpose/pm-skills --skill foundation-okr-writer --agent claude-codeInstalls into .claude/skills of the current project.
Files
OKR Writer
An OKR (Objectives and Key Results) set is a quarterly artifact that translates strategy into measurable outcomes a team commits to drive. OKRs are a focus and learning system, not a project plan, KPI dashboard, performance review device, or roadmap wrapper. Done well, they make priorities explicit, force tradeoffs, enable cross-team alignment, and create visible evidence of progress. Done poorly, they generate roadmap theater, compensation gaming, and false precision.
This skill is a coach, not a template filler. It drafts, reviews, rewrites, and audits OKR sets against the empirical consensus drawn from Doerr (Measure What Matters), Wodtke (Radical Focus), Cagan (SVPG team objectives), Castro (outcome-vs-output), Grove (High Output Management), Torres (continuous discovery), and Gothelf and Seiden (Outcomes Over Output).
Supported Modes
Five entry modes support different engagement levels. Mode is detected from user phrasing; default to Guided when ambiguous. State the detected mode at the start of the response.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/product-on-purpose/pm-skills
- Categories
- Code Review & Quality, Productivity & Planning
- License
- Apache-2.0
- First seen
- Aug 4, 2026
More from product-on-purpose/pm-skills
All 68- Develop Spike Summary774
- Iterate Lessons Log767
- Iterate Pivot Decision767
- Utility Slideshow Creator764
- Foundation Lean Canvas762
- Iterate Refinement Notes753
- Utility Pm Skill Builder751
- Foundation Meeting Agenda749
- Foundation Stakeholder Update742
- Foundation Meeting Recap737
- Utility Pm Skill Validate736
- Foundation Meeting Synthesize735
- Utility Pm Skill Iterate734
- Foundation Meeting Brief733
- Utility Update Pm Skills731
- Measure Okr Grader723
- Define Prioritization Framework692
- Discover Journey Map690
- Measure Survey Analysis685
- Utility Pm Critic679
- Tool Note And Vote673
- Tool Foundation Sprint Approach Options667
- Tool Foundation Sprint Brief667
- Tool Foundation Sprint Differentiation667
Recommended
More Code Review & Quality
social-media-content-repurposeronewave-ai/claude-skillsConvert content between platforms (blog to Twitter thread, article to LinkedIn post, etc.). Optimize for each platform's format, tone, and best practices. Use w775skills.sh installs
develop-spike-summaryproduct-on-purpose/pm-skillsDocuments the results of a completed technical or design spike, capturing the original question, approach, evidence-backed findings, and a clear proceed-or-not 774skills.sh installs
atlas-cloudatlascloudai/atlas-cloud-skillsAtlas Cloud API integration skill — quickly call 300+ AI image generation, video generation, audio (TTS, music, speech-to-text), 3D generation, and LLM models t772skills.sh installs
terraform-diagramseraserlabs/eraser-ioGenerates architecture diagrams from Terraform code. Use when user has .tf files or asks to visualize Terraform infrastructure.765skills.sh installs
auth0-angularauth0/agent-skillsUse when adding Auth0 login, logout, route guards, or HTTP interceptors to an Angular application. Integrates @auth0/auth0-angular for SPAs — use even if the us762skills.sh installs
playtest-reportdonchitos/claude-code-game-studiosGenerates a structured playtest report template or analyzes existing playtest notes into a structured format. Use this to standardize playtest feedback collecti760skills.sh installs