skills/codex/brainstorm-okrs/SKILL.md
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: brainstorm-okrs description: Generate team-level OKRs aligned with company strategy. Use when planning quarterly objectives, setting team goals, or translating strategy into measurable key results. --- # Brainstorm OKRs Generate well-structured, outcome-focused OKRs (Objectives and Key Results) for product teams — aligned with company strategy and grounded in what the team can actually influence. --- ## Purpose Most OKRs fa
npx skillsauth add frank-luongt/faos-skills-marketplace skills/codex/brainstorm-okrsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Generate well-structured, outcome-focused OKRs (Objectives and Key Results) for product teams — aligned with company strategy and grounded in what the team can actually influence.
Most OKRs fail because they're either disguised task lists ("launch feature X") or unmeasurable aspirations ("delight customers"). This skill produces OKRs that are outcome-focused, measurable, and achievable — following Christina Wodtke's Radical Focus framework.
Good: "Make onboarding so smooth that new users reach value in their first session" Bad: "Increase retention" (too vague), "Launch onboarding v2" (output, not outcome)
Good: "Reduce time-to-first-value from 14 days to 3 days" Bad: "Ship 5 features" (output), "Improve NPS" (no target), "Increase everything" (unfocused)
These are complementary, not competing:
| Concept | Scope | Purpose | | --- | --- | --- | | North Star Metric | Company | Single metric that captures core value delivery | | OKRs | Team / Quarter | Focus areas and measurable targets for the period | | KPIs | Ongoing | Health metrics monitored continuously |
OKRs tell you what to improve this quarter. KPIs tell you what to monitor always.
Review the company's strategy, annual goals, or North Star Metric. Identify:
For the team's scope, brainstorm areas where improvement would most impact the company goal.
Example impact areas for a product team:
Produce 3 distinct OKR sets, each taking a different strategic angle. This prevents anchoring on the first idea.
For each set, provide:
Show all 3 sets side by side with trade-offs:
## OKR Option A: [Strategic Theme]
**Objective 1:** [Qualitative, inspirational objective]
- KR1: [Metric] from [baseline] to [target]
- KR2: [Metric] from [baseline] to [target]
- KR3: [Metric] from [baseline] to [target]
**Rationale:** [Why this matters]
**Risk:** [What could go wrong]
**Confidence:** [60–70% recommended]
---
## OKR Option B: [Different Strategic Theme]
...
## OKR Option C: [Yet Another Angle]
...
Once the team selects a direction:
# Team OKRs — Q[N] [Year]
**Team:** [team name]
**Aligned to:** [company objective or strategy]
**Quarter:** [Q1/Q2/Q3/Q4 Year]
---
## Objective 1: [Qualitative objective]
| Key Result | Baseline | Target | Confidence |
| --- | --- | --- | --- |
| [KR1 description] | [current] | [target] | 65% |
| [KR2 description] | [current] | [target] | 70% |
| [KR3 description] | [current] | [target] | 60% |
**Leading indicators (weekly check):**
- [metric to watch]
- [metric to watch]
---
## Objective 2: [Qualitative objective]
| Key Result | Baseline | Target | Confidence |
| --- | --- | --- | --- |
| [KR1 description] | [current] | [target] | 65% |
| [KR2 description] | [current] | [target] | 70% |
---
## Health Metrics (Monitor, Don't Optimize)
| Metric | Current | Guardrail |
| --- | --- | --- |
| [metric you must not degrade] | [current] | [minimum acceptable] |
| Avoid | Why | Instead | | --- | --- | --- | | Output-based KRs ("launch X") | Measures activity, not impact | Reframe: "Users who [behavior] increases from X to Y" | | Too many OKRs (>3 objectives) | Diffuses focus | Pick 1–2 objectives, 2–3 KRs each | | 100% confidence targets | Sandbagging — no stretch | Aim for 60–70% confidence | | Individual OKRs | Creates perverse incentives | OKRs are for teams | | Binary KRs ("ship/don't ship") | No gradient of success | Use continuous metrics | | Changing OKRs mid-quarter | Destroys accountability | Lock OKRs, adjust tactics |
development
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: grpo-rl-training description: GRPO reinforcement learning training with TRL. Use when applying Group Relative Policy Optimization for reasoning and task-specific model training. --- # GRPO/RL Training with TRL Expert-level guidance for implementing Group Relative Policy Optimization (GRPO) using the Transformer Reinforcement Learning (TRL) library. This skill provides battle-tested patterns, critical insights, and production-r
tools
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: graphql-architect description: Master modern GraphQL with federation, performance optimization, --- ## Use this skill when - Working on graphql architect tasks or workflows - Needing guidance, best practices, or checklists for graphql architect ## Do not use this skill when - The task is unrelated to graphql architect - You need a different domain or tool outside this scope ## Instructions - Clarify goals, constraints, and
development
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: grafana-dashboards description: Create and manage production Grafana dashboards for real-time visualization of system and application metrics. Use when building monitoring dashboards, visualizing metrics, or creating operational observability interfaces. --- # Grafana Dashboards Create and manage production-ready Grafana dashboards for comprehensive system observability. ## Do not use this skill when - The task is unrelated
development
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: gptq description: GPTQ post-training quantization for generative models. Use when quantizing large models to 4-bit with calibration-based weight compression. --- # GPTQ (Generative Pre-trained Transformer Quantization) Post-training quantization method that compresses LLMs to 4-bit with minimal accuracy loss using group-wise quantization. ## When to use GPTQ **Use GPTQ when:** - Need to fit large models (70B+) on limited GPU