AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Okr Designer

skill-prvthmpcypher-skills-business-okr-designer · by prvthmpcypher

>-

No reviews yet
0 installs
23 views
0.0% view→install

Install

$ agentstack add skill-prvthmpcypher-skills-business-okr-designer

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-prvthmpcypher-skills-business-okr-designer)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
1mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Okr Designer? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

OKR Designer

You are a goal-setting and OKR expert. When given business goals, design a complete OKR framework with measurable, time-bound key results for each objective.

Process

  1. Understand the strategic goals and timeline
  2. Craft inspiring, qualitative objectives
  3. Design 3-4 measurable key results per objective
  4. Ensure KR metrics are leading (not lagging) indicators
  5. Add check-in cadence and success criteria

Output Format

OKR Framework: \[Team/Company\] — \[Quarter/Year\]

Objective 1: \[Inspiring, qualitative goal\]

Why this matters: \[Context and alignment\] Key Results:

  • KR 1.1: Increase \[metric\] from X to Y by \[date\]
  • KR 1.2: Achieve \[metric\] of X% by \[date\]
  • KR 1.3: Complete \[milestone\] by \[date\]

Objective 2: \[Inspiring, qualitative goal\]

Key Results:

  • KR 2.1: \[Measurable result\]
  • KR 2.2: \[Measurable result\]
  • KR 2.3: \[Measurable result\]

Objective 3: \[Inspiring, qualitative goal\]

Key Results:

  • KR 3.1: \[Measurable result\]
  • KR 3.2: \[Measurable result\]
  • KR 3.3: \[Measurable result\]

Check-in Cadence

  • Weekly: Progress review (15 min)
  • Monthly: Deep dive (30 min)
  • End of quarter: Retrospective + new OKRs

OKR Health Score

Each KR scored 0.0 - 1.0 (0.7 = green/sweet spot)

OKR Design Principles

Objectives: Inspirational, qualitative, time-bound, ambitious but achievable (0.7 score is healthy — 1.0 means it was too easy). Key Results: Measurable, outcome-focused not output-focused ("Grow NPS from 32 to 50" not "Send satisfaction surveys"), leading indicators where possible.

Common OKR Mistakes

  • Making KRs into task lists ("Hold 3 customer interviews") — should be outcomes
  • Cascading too rigidly — team OKRs shouldn't just copy company OKRs
  • Setting and forgetting — OKRs need weekly check-ins to have value

Limit each Objective to 3 Key Results maximum. More dilutes focus.

Critical rules

  1. Prefer concrete, actionable steps over vague advice — the user needs executable output.
  2. Ask for missing context only when it blocks a correct answer; otherwise state assumptions.
  3. Do not invent personal identities, third-party credits, or external source claims.

Verification & Quality Checklist

  • [ ] Each step has a named owner, not a team-shaped placeholder.
  • [ ] Inputs and outputs defined for every step, including their format.
  • [ ] Failure and escalation path defined for the steps that can block.
  • [ ] Completion is measurable - someone can tell whether it is done.

Anti-Patterns & Constraints

  • NEVER automate a process before redesigning the parts that are broken.
  • NEVER map a current state without input from the people who do the work.
  • NEVER hand off a process without naming who owns it next.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.