🎯

OKR Draft Critiquer

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

Critique draft OKRs for measurable outcomes and controllable scope.

Get issue-by-issue feedback and proposed measurable rewrites.

Download skill ZIP See the worked example

Free · 2 KB · SKILL.md, instructions and example files. Provide the draft, time period, business context and available baselines.

A worked example

A small example to try before using your own data.

Input

{
  "objective": "Improve onboarding",
  "key_result": "Ship three tutorials",
  "baseline": "Activation is 40%",
  "period": "Q4"
}

Expected result

Issue: shipping tutorials measures output, not onboarding success. Proposed KR: increase the defined activation rate from 40% to [agreed target] by Q4 end, measured in [source], while monitoring support burden. Keep tutorial delivery as an initiative.

What to check: Do not invent the target or measurement source. Preserve the known 40% baseline.

Limits: The critique does not choose business priorities or guarantee that a metric causes the desired outcome.

Worked example included. Model-specific performance and vendor compatibility have not been benchmarked.

Installation options and other formats

Install this skill

An agent skill starts with SKILL.md. The ZIP also includes its examples and any helper scripts. Drop the file into your tool of choice — or pick a different format if you use Cursor, Windsurf, Copilot, or something else.

Format Download SKILL.md

Quick install — paste into your terminal

python3 - <<'ADF_SKILL_INSTALL'
import hashlib, io, os, stat, tempfile, urllib.request, zipfile
from pathlib import Path, PurePosixPath
folder = "okr-draft-critiquer"
root = Path(os.environ.get('ADF_SKILL_ROOT', str(Path.home() / '.claude' / 'skills'))).expanduser()
destination = root / folder
if destination.exists() or destination.is_symlink():
    raise SystemExit('An installation already exists. Back it up and merge the ZIP deliberately.')
root.mkdir(parents=True, exist_ok=True)
request = urllib.request.Request("https://aidiveforge.com/skill/okr-draft-critiquer.zip", headers={'User-Agent': 'AIDiveForge-Resource-Installer/1.0 (+https://aidiveforge.com/skills/)'})
with urllib.request.urlopen(request, timeout=30) as response:
    data = response.read(8 * 1024 * 1024 + 1)
if len(data) > 8 * 1024 * 1024 or hashlib.sha256(data).hexdigest() != "c1089bf85dccf659129456413f9aede783a5f8d13f5d124a05f92af5f8999968":
    raise SystemExit('The download did not match this reviewed bundle. No files were installed.')
with zipfile.ZipFile(io.BytesIO(data)) as archive, tempfile.TemporaryDirectory(prefix='.adf-skill-', dir=root) as temporary:
    members = archive.infolist()
    if len(members) > 100 or sum(m.file_size for m in members) > 16 * 1024 * 1024:
        raise SystemExit('Unexpected archive size')
    for member in members:
        name = PurePosixPath(member.filename)
        if name.is_absolute() or '..' in name.parts or not name.parts or name.parts[0] != folder or '\\' in member.filename or stat.S_ISLNK(member.external_attr >> 16):
            raise SystemExit('Unsafe archive entry; nothing was installed')
        target = Path(temporary).joinpath(*name.parts)
        if member.is_dir():
            target.mkdir(parents=True, exist_ok=True)
        else:
            target.parent.mkdir(parents=True, exist_ok=True)
            with target.open('xb') as stream:
                stream.write(archive.read(member))
    staged = Path(temporary) / folder
    if not (staged / 'SKILL.md').is_file() or destination.exists() or destination.is_symlink():
        raise SystemExit('The skill could not be installed without replacing existing data')
    os.rename(staged, destination)
print('Installed the complete skill folder:', destination)
ADF_SKILL_INSTALL

Claude Code: ~/.claude/skills/okr-draft-critiquer/SKILL.md. Codex: ~/.codex/skills/okr-draft-critiquer/SKILL.md. Keep the complete ZIP folder when helper scripts are included.

🧠 Why it works

Do not invent the target or measurement source. Preserve the known 40% baseline.

⚙️ How it works

Separate each objective from its key results and identify the desired user or business outcome.

Check that each key result has a metric, baseline, target, deadline and a clear measurement source.

Flag activities presented as outcomes and targets that rely on unverified baselines.

Propose a rewrite using supplied numbers; leave placeholders where evidence is missing.

Identify possible gaming or tradeoffs and the guardrail metric that would expose them.

Description

Get issue-by-issue feedback and proposed measurable rewrites.

Provide the draft, time period, business context and available baselines.

Limits: The critique does not choose business priorities or guarantee that a metric causes the desired outcome.

A worked example

Input

Expected result

Install this skill

🧠 Why it works

⚙️ How it works

Description

Recommended Use

Forge Auto-recommended matches

Tools

Report compatibility

Suggest a pairing