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

83%

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

71%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.

The body is a well-structured, actionable reference: a clear workflow with validation, concrete config examples, and excellent progressive disclosure into real reference files. The main weakness is redundancy — the Cost & Credits and Key Constraints summary sections duplicate information already in the catalog tables.

Suggestions

Remove or compress the 'Cost & Credits Quick Reference' and 'Key Constraints' sections, or convert them to short cross-references to the catalog tables, to eliminate the duplicated cost/constraint information.

Tighten the workflow's validation step (step 6) to specify what to inspect in results (e.g. which metric outputs to sanity-check and what 'off' looks like) rather than the generic 'review results'.

The opening verification-tag and mcp__cekura__cekura_skill_started call block is product boilerplate; if it must stay, consider moving the longer explanatory paragraph into a reference so the skill opens on substantive guidance.

Dimension	Reasoning	Score
Conciseness	The body is data-dense and avoids explaining concepts Claude already knows, but the 'Cost & Credits Quick Reference' and 'Key Constraints' sections substantially restate per-metric cost and constraint notes already present in the catalog tables, which could be tightened.	3 / 5
Actionability	Provides concrete config payloads (e.g. [{"word": "Cekura", "phoneme": "sɛˈkjʊrə"}]), a specific endpoint (GET /test_framework/v1/predefined-metrics/), tool names, and a baseline set; minor gaps remain since full API payloads and use-case sets are deferred to reference files.	4 / 5
Workflow Clarity	The 6-step Predefined Metrics Workflow is clearly sequenced and includes an explicit validation step (step 6: 'Validate by running') with a feedback loop into Common Pitfalls, satisfying the batch-operation validation requirement; checkpoints are present though the validation check itself is somewhat light on what specifically to inspect.	4 / 5
Progressive Disclosure	SKILL.md serves as a clear overview with the catalog inline, while detailed payloads, full API, and use-case sets are split into three real one-level-deep reference files (configuration-guide.md, api-reference.md, selection-by-use-case.md), each clearly signaled both inline and in a dedicated Additional Resources section.	5 / 5
	Total	16 / 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.

The description is excellent: it pairs an explicit 'Use when...' trigger list rich with natural user phrasings and specific metric names, with a clear statement of what the skill covers. Minor room to sharpen the 'what' from scope areas into discrete actions, but conflict risk and trigger quality are top-tier.

Dimension	Reasoning	Score
Specificity	Names the domain and lists several concrete coverage areas ("what each does, costs, constraints, configuration options, and when to use each one"), but these describe scope more than discrete executable actions, so it stops short of the comprehensive concrete-action anchor at 5.	4 / 5
Completeness	Explicitly answers both what ("Covers the full catalog of predefined metrics — what each does, costs, constraints, configuration options") and when ("Use when the user asks... or any question about Cekura's out-of-the-box metrics") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases users would actually say, including specific metric names ("what does CSAT measure", "what's the difference between Interruption Score and AI Interrupting User", "configure silence threshold") plus a catch-all, matching the comprehensive-coverage anchor.	5 / 5
Distinctiveness Conflict Risk	Clear niche scoped to Cekura's out-of-the-box metrics with distinctive triggers naming specific metrics, minimal overlap with sibling skills like cekura-metric-design or cekura-eval-design.	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: af2ceb6

Reviewed: 4 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.