CtrlK
BlogDocsLog inGet started
Tessl Logo

okr-design

OKR design as actually shipped, not as conference-talk theory. Outcome statements that drive decisions, key results that measure the right thing, scoring discipline, mid-quarter recalibration, and the difference between sandbagged OKRs (always 100%) and aspirational OKRs (always 30%) and stretch OKRs (genuine ambition with quarterly accountability). Triggers on OKR design, OKR setting, key result design, OKR scoring, mid-quarter recalibration, OKR cascading, outcomes vs outputs, quarterly planning, goal setting. Also triggers when a team's OKRs are always hit and producing no learning, when OKRs are demoralizing because they were set as fantasy, or when the team uses OKR vocabulary but the practice has decayed.

58

Quality

67%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/okr-design/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Discovery

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is an excellent skill description that combines concrete capability listing with rich trigger coverage. It goes beyond standard 'what/when' structure by including situational triggers for common OKR dysfunctions, which helps Claude select this skill in nuanced scenarios. The description is detailed without being padded, and every sentence adds discriminative value.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: outcome statement design, key result measurement, scoring discipline, mid-quarter recalibration, distinguishing sandbagged vs aspirational vs stretch OKRs. Goes beyond naming the domain to describe specific practices and anti-patterns.

3 / 3

Completeness

Clearly answers both 'what' (OKR design covering outcome statements, key results, scoring, recalibration, distinguishing OKR types) and 'when' (explicit 'Triggers on...' clause with keyword triggers plus situational triggers for common OKR dysfunction patterns).

3 / 3

Trigger Term Quality

Excellent coverage of natural terms users would say: 'OKR design', 'OKR setting', 'key result design', 'OKR scoring', 'mid-quarter recalibration', 'OKR cascading', 'outcomes vs outputs', 'quarterly planning', 'goal setting'. Also includes situational triggers like 'OKRs are always hit' or 'OKRs are demoralizing'.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive niche focused specifically on OKR methodology with clear, domain-specific triggers. Unlikely to conflict with generic planning or goal-setting skills due to the specificity of OKR vocabulary and the detailed anti-pattern triggers.

3 / 3

Total

12

/

12

Passed

Implementation

35%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a knowledgeable, opinionated skill that covers OKR design comprehensively, but it suffers significantly from verbosity and repetition. The same core concepts (sandbagged vs stretch vs fantasy, outcomes vs outputs) are restated 3-4 times across different sections. The content reads more like a long-form essay or handbook chapter than a concise, actionable skill file. The progressive disclosure structure is well-conceived (9 reference files) but undermined by the main file retaining too much detail that should live in those references.

Suggestions

Cut the opening 3 paragraphs and closing section entirely — they repeat content from the body sections. Start with the sandbagged/aspirational/stretch framing directly.

Remove the 'What this skill is for' section listing other skills — Claude doesn't need a skill taxonomy to use this skill effectively.

Add a concrete step-by-step OKR design workflow with validation checkpoints, e.g., 'Step 1: Draft objectives → Step 2: Apply stretch litmus test → Step 3: Draft key results → Step 4: Verify each KR against the 4 characteristics → Step 5: Check total count (2-4 objectives, 3-5 KRs each)'.

Move detailed content (cascading trade-offs, full scoring discipline, review cadence details) into the reference files and keep only summary guidance in the main skill, since the reference files already exist for this purpose.

DimensionReasoningScore

Conciseness

Extremely verbose for an instruction-only skill. The opening three paragraphs repeat the same sandbagged/aspirational/stretch framing that appears again in its own section and again in the closing. Concepts like 'outcomes vs outputs' are explained multiple times. The 'What this skill is for' section explaining what other skills do is unnecessary context. Claude already understands OKR concepts; the skill should focus on the specific opinionated methodology, not re-explain the framework from scratch. The closing section largely restates what was already said. Easily 40-50% of tokens could be cut without losing actionable content.

1 / 3

Actionability

The skill provides worked examples (activation OKR with specific key results), the 12-consideration framework, and concrete failure mode diagnoses. However, it lacks executable templates or step-by-step procedures for actually designing OKRs in a session. The guidance is more descriptive ('strong objectives have these characteristics') than procedural ('here is how to draft an objective: step 1...'). The worked examples are good but limited to one domain (activation). No scoring worksheet, no OKR draft template, no concrete audit checklist format.

2 / 3

Workflow Clarity

The review cadence section provides a clear temporal sequence (weekly → mid-quarter → end-of-quarter → retrospective), and the 12-consideration framework provides a checklist. However, the actual OKR design workflow is not sequenced as a step-by-step process with validation checkpoints. There's no explicit 'draft → review → validate → finalize' workflow for creating OKRs. The recalibration section has good decision criteria but lacks a structured decision tree. For a skill involving quarterly accountability cycles, the absence of explicit validation steps (e.g., 'check your draft OKRs against the stretch litmus test before finalizing') is a gap.

2 / 3

Progressive Disclosure

The skill references 9 separate reference files with clear descriptions, which is good progressive disclosure structure. However, no bundle files were provided, so the references are unverifiable. The main SKILL.md itself is too long — much of the inline content (e.g., detailed cascading discussion, full scoring discipline section, full review cadence details) duplicates what the reference files presumably contain. The skill would benefit from being a leaner overview that delegates more aggressively to the reference files it already points to.

2 / 3

Total

7

/

12

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
rampstackco/claude-skills
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.