Skip to main content
AIDiveForge AIDiveForge
🎯

OKR Draft Critiquer

Productivity & Ops · by AIDiveForge · Apr 20, 2026 · Advanced

Score draft OKRs against SMART criteria and the outcome-not-output rule, with suggested rewrites for each failing key result.

🧠 Why it works

OKR review meetings degenerate into 'I'm not sure this is quite right' without a shared rubric. Forcing each KR through a fixed rubric with a rewritten alternative makes the conversation concrete: 'do we accept the original or the rewrite' is a much sharper question than 'is this good.'

⚙️ How it works

  1. Parse the input into (objective, key_result) pairs. 2. For each KR, run four independent checks with justification quotes: is it measurable (has a number and a target), is it ambitious (would you be comfortable hitting it at 70 percent), is it specific (names a user, a metric, and a direction), is it an outcome (measures user behavior not team activity). 3. For any failing check, generate a rewritten KR that fixes the failure while preserving intent. 4. Emit a per-KR scorecard plus the original vs rewritten in a side-by-side markdown table.

Description

Input: a set of proposed OKRs in any format. Output: per-objective and per-key-result scorecards across four axes — Specific, Measurable, Ambitious, Outcome (vs Output). Each failing KR gets a rewritten version that fixes the failure, so the reviewer has a concrete before/after to discuss.

Install this skill

A Claude skill is a skill.md file with YAML frontmatter and a markdown body. Drop the file into your tool of choice — or pick a different format if you use Cursor, Windsurf, Copilot, or something else.

Download skill.md
mkdir -p ~/.claude/skills/okr-draft-critiquer \
  && curl -L https://aidiveforge.com/skill/okr-draft-critiquer.skill-md \
       -o ~/.claude/skills/okr-draft-critiquer/skill.md

Save to ~/.claude/skills/okr-draft-critiquer/skill.md

Recommended Use

Tools and workflow packs this skill pairs well with. Forge picks are auto-generated from category + capability signals; Community picks are added by people who've used the pairing.