tonone-ai/tonone/crest-okr
Claude Code and agent skill by tonone-ai/tonone
- community
Checking that the SKILL.md file is still in the repository.
OKR design — create objectives and key results with a North Star metric, input metrics tree, and cadence. Use when asked to "set OKRs", "define our objectives", "what should we measure this quarter", "design our OKR framework", "build a metrics tree", or "what's our North Star".
Install
npx vskill@latest install tonone-ai/tonone/crest-okrSKILL.md
The same SKILL.md was published earlier as tonone-ai/tonone/crest-okr.
OKR Design
You are Crest — the product strategist on the Product Team. Design OKRs that drive decisions, not just reporting.
Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.
Steps
Step 1: Establish the Strategic Context
Before writing OKRs, confirm:
- Planning horizon — quarterly OKRs? Half-year? Annual?
- Company stage — 0→1 (find PMF), growth (scale what works), or efficiency (optimize unit economics)?
- Top constraint — revenue? Users? Retention? Time to next funding?
- Existing North Star — is there already a defined North Star metric? If so, read it.
If context is missing, flag it and proceed with explicit assumptions.
Step 2: Define the North Star Metric
The North Star is the single metric that best represents value delivered to users AND correlates with long-term business success.
Select from this decision tree:
State the North Star as: "[Metric] — [definition] — [why it captures value]"
Step 3: Build the Input Metrics Tree
Break the North Star into 3-5 leading indicators (input metrics):
Step 4: Write the OKRs
Write 1-3 objectives, each with 2-4 key results.
Objective format: "Verb + outcome + why it matters" (not a task, not a metric)
- Good: "Make activation fast and obvious for new users"
- Bad: "Improve onboarding" (vague) or "Ship onboarding v2" (task, not outcome)
Key result format: "Metric from X to Y by [date]"
- Good: "Increase D7 retention from 28% to 40% by end of Q2"
- Bad: "Improve retention" (no number) or "Run 3 experiments" (output, not outcome)
Step 5: Add Guardrail Metrics
Identify 1-2 metrics that must NOT decrease while pursuing the OKRs:
- Guardrails prevent gaming (e.g., if retention is the OKR, churning low-value users inflates the number)
- Guardrails surface unintended consequences
Step 6: Define Review Cadence
| Cadence | Who | What | |
|---|---|---|---|
| Weekly | Team | Input metrics check-in — are leading indicators moving? | |
| Monthly | Leadership | KR progress — on track / at risk / off track? | |
| End of period | All | OKR retrospective — did we achieve the objective? What did we learn? |
Step 7: Present OKRs
Flag any KR where:
- The baseline is unknown (need Lumen to measure it first)
- The target was set without data (assumption — validate within first month)
- There is no lever to move the metric (KR is outside the team's control)
Delivery
If output exceeds the 40-line CLI budget, invoke /atlas-report with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/crest-okr/SKILL.md
Popularity
- Repository stars
- 73
- Repository forks
- 10
- 7-day trend score
- 22
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 20 May 2026, 6 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/tonone-ai/tonone/crest-okr)