CtrlK
BlogDocsLog inGet started
Tessl Logo

design-kpis

Design KPI frameworks, metric definitions, targets, guardrails, and measurement plans for product or business decisions. Use when success metrics, drivers, guardrails, targets, or the measurement approach need to be defined or improved.

75

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

A well-structured, actionable KPI-design workflow with clear sequencing and verification gates, appropriately scoped to a single organized SKILL.md. The main weakness is conciseness: several paragraphs are wordier than they need to be.

Suggestions

Tighten the verbose target-setting paragraph (line 78) and the "Gather Evidence" opener — trim conditional hedging and merge redundant clauses to reclaim tokens without losing meaning.

Consider compressing the six selection-criteria bullets into a tighter checklist format so the decision rules scan faster at a glance.

The "When To Use Data Quality First" section could be shortened to a one-line routing rule; the distinction is already captured in the description's scope.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence (it does not explain what a KPI is) and is mostly efficient, but several passages are wordy and could be tightened — e.g., the long target-setting paragraph at line 78 and hedging openers like "When the prompt does not already provide enough context to know what success means". Not a 3 because not every token earns its place; not a 1 because it is not padded with concepts Claude already knows.

2 / 3

Actionability

Gives concrete, copy-ready decision rules — the six selection-criteria bullets, explicit counts ("1-3 primary KPIs, 1-2 driver metrics ... 1-2 guardrails"), per-metric detail requirements, and named top-down/bottom-up target approaches — rather than vague direction, matching the fully-actionable anchor.

3 / 3

Workflow Clarity

A clear 6-step sequence with explicit checkpoints: the source-access guardrail that stops a path when a required source is missing, live-read verification before concluding, and target-setting confidence/assumption gates. Not a 2 because validation and decision gates are explicit, not merely listed.

3 / 3

Progressive Disclosure

No bundle files exist and none are needed; the single SKILL.md is organized into clear sections (Configuration, numbered Workflow, Example Metric Shapes), and cross-skill references ($analyze-data-quality, $gather-business-context) are clearly signaled routing rather than nested references, satisfying the well-organized-no-external-refs allowance.

3 / 3

Total

11

/

12

Passed

Description

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.

The description is specific, complete, and well-scoped: it enumerates concrete KPI-design actions and pairs them with an explicit, natural "Use when" trigger clause. Trigger terms cover the vocabulary a user would actually use when requesting KPI work.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Design KPI frameworks, metric definitions, targets, guardrails, and measurement plans" — matching the multi-action anchor rather than the partial-coverage anchor at 2.

3 / 3

Completeness

Explicitly answers both what (design KPI frameworks, definitions, targets, guardrails, measurement plans) and when ("Use when ... need to be defined or improved"), satisfying the full what-and-when anchor.

3 / 3

Trigger Term Quality

Natural trigger terms a user would say — "success metrics, drivers, guardrails, targets, or the measurement approach" — give good coverage rather than the sparse keyword set at 2.

3 / 3

Distinctiveness Conflict Risk

Scoped to defining or improving metrics rather than reconciling existing data, giving it a clear niche unlikely to conflict; not generic enough to fall to 2.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
XiaomiMiMo/MiMo-Code
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.