Okr drafting
Curated, auditable, benchmark-ready Agent Skills library for Claude Code, Codex, OpenCode, Cursor, and more.
npx -y skills add shinzoxD/knackbox --skill okr-draftingAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 29 days oldThe repository was created 29 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Draft OKRs and goal cascades that are measurable and non-vanity. Use whenever the user asks for OKRs, quarterly objectives, key results, goal setting, or how to turn a strategy into measurable objectives and key results.
The file declares its own license as Apache-2.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
1.7 KB, 304 tokens by cl100k_base, as published. Nobody here has run it
OKR Drafting
Objectives are qualitative and motivating. Key results are measurable outcomes, not a task list. Fewer OKRs beat a wall of metrics.
Patterns
Objective: memorable outcome direction (not "be world class"). Key results: 2–4 metrics or binary milestones with starting point → target.
Bad KR: "Launch dashboard" (task). Better KR: "Raise weekly active teams using dashboard from 12% to 30%".
Output format
## OKRs — <team> — <quarter>
### O1: …
- KR1: from X to Y by date (source of metric)
- KR2: …
- KR3: …
### Notes
- scoring: …
- dependencies: …
- non-goals: …
Rules
- KRs need baseline and target when numbers exist; else mark metric TBD.
- Avoid vanity metrics disconnected from user/business value.
- Cascade: company → team without cloning identical KRs everywhere.
- Commit vs stretch: label if useful.
- Do not invent company strategy; use provided context.
- Cap at ~3 objectives per team per cycle unless asked otherwise.
Edge cases
- Platform teams: KRs via customer team outcomes + reliability SLOs.
- Early startup: shorter cycle; learning KRs ok if measurable.
- Individual OKRs: align to team; avoid HR-only busywork.
Gives 0 of the 12 instructions most roadmap strategy skills give in 304 tokens
Counted across 591 of the 672 authors here whose files we hold, read 2026-08-07
- read product marketing context before asking questionsin 21 of 591, across 10 files
- base price on perceived value, not costin 15 of 591, across 4 files
- compact after finalizing a planin 14 of 591, across 9 files
- differentiate tiers using features, limits, or supportin 14 of 591, across 3 files
- use Van Westendorp to find acceptable price rangein 13 of 591, across 2 files
- use MaxDiff to identify highly valued featuresin 13 of 591, across 2 files
- map topics to buyer journey stagesin 12 of 591, across 6 files
- Extract domain capabilities and classify subdomainsin 11 of 591, across 1 file
- Define bounded contexts around consistency and ownershipin 11 of 591, across 1 file
- Establish a ubiquitous language glossary and anti-termsin 11 of 591, across 1 file
- Capture context boundaries in ADRs before implementationin 11 of 591, across 1 file
- Open the strategic design template if neededin 11 of 591, across 1 file
Said here and by no other author read
- Use qualitative and motivating objectives.
- Limit key results to 2-4 metrics.
- Mark metrics TBD when lacking numbers.
- Cap at three objectives per team per cycle.
- Label key results as commit or stretch if useful.
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.