cekura-predefined-metrics

Use when the user asks "what predefined metrics are available", "which built-in metrics should I use", "what does CSAT measure", "how does hallucination detection work", "what's the difference between Interruption Score and AI Interrupting User", "which metrics are free", "which metrics need audio", "configure silence threshold", "set up sentiment metric", or any question about Cekura's out-of-the-box metrics. Covers the full catalog of predefined metrics — what each does, costs, constraints, configuration options, and when to use each one.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

78%Weight 40%Scale 1-5

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

A well-structured reference skill with clear catalog tables, a sequenced workflow with validation, and exemplary progressive disclosure to three real reference files. The main weaknesses are minor redundancy (cost quick-reference, re-listed enabling steps) and advisory rather than gated validation.

Suggestions

Collapse the 'Cost & Credits Quick Reference' table or remove it — its content is already present in each catalog table's Cost column, so it is pure redundancy.

Make the workflow's validation step a hard gate: rephrase step 6 as 'Only proceed to broader rollout when the validation batch looks correct; otherwise check Common Pitfalls' to push workflow_clarity toward the top anchor.

Trim the standalone 'Enabling Predefined Metrics' section since it restates workflow steps 3–4; cross-reference the workflow instead to remove the duplication.

Dimension	Reasoning	Score
Conciseness	Tabular catalog format is token-efficient and assumes Claude's competence, but the 'Cost & Credits Quick Reference' duplicates per-table cost info and the 'Enabling Predefined Metrics' section re-lists workflow steps 3–4 — minor instances that could be trimmed, fitting the efficient-with-minor-overexplanation anchor.	4 / 5
Actionability	Gives a concrete endpoint (GET /test_framework/v1/predefined-metrics/), config keys with types/defaults, an IPA phoneme example, and a named baseline set; full payload examples are deferred to references, leaving minor gaps versus copy-paste-ready completeness.	4 / 5
Workflow Clarity	The 6-step workflow is clearly sequenced with an explicit 'Validate by running' checkpoint and a Common Pitfalls recovery pointer, but validation is advisory rather than a hard gate ('only proceed when valid'), so it sits below the top anchor.	4 / 5
Progressive Disclosure	SKILL.md is a concise overview pointing to three well-signaled, one-level-deep references (configuration-guide.md, api-reference.md, selection-by-use-case.md), all verified to exist, with content appropriately split between overview and detail files.	5 / 5
	Total	17 / 20 Passed

Description

95%Weight 40%Scale 1-5

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

A strong, third-person description with comprehensive natural trigger phrases and an explicit what/when structure scoped to a distinct Cekura niche. The only minor gap is that capability coverage is stated as facets of the catalog rather than enumerated concrete actions.

Dimension	Reasoning	Score
Specificity	Names the domain (predefined metrics catalog) and lists several concrete facets — 'what each does, costs, constraints, configuration options, and when to use each one' — but describes coverage areas rather than discrete concrete actions, so it sits just below the comprehensive anchor 5.	4 / 5
Completeness	Explicitly answers both 'what' (catalog of predefined metrics — what each does, costs, constraints, configuration) and 'when' ('Use when the user asks...') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Nine natural quoted triggers span synonyms and specific metric names ('what predefined metrics are available', 'which built-in metrics should I use', 'what does CSAT measure', 'which metrics are free', 'configure silence threshold'), matching the comprehensive-coverage anchor.	5 / 5
Distinctiveness Conflict Risk	Cekura-specific niche with named metrics (CSAT, Interruption Score, AI Interrupting User) gives it a clear distinct trigger surface with minimal conflict risk against other skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: cekura-ai/cekura-skills
Path: cekura/skills/cekura-predefined-metrics/SKILL.md
Commit: caa6544

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.