CtrlK
BlogDocsLog inGet started
Tessl Logo

cekura-onboarding

Use when the user says "get started with Cekura", "set up Cekura", "onboard to Cekura", "I'm new to Cekura", "help me set up my agent", "how do I use Cekura", "walk me through Cekura", "configure my project", "first time using Cekura", or needs guidance on initial platform setup. Covers two onboarding paths: **testing** (default — build evaluators and run simulated calls) and **observability** (ingest production call logs and evaluate them).

65

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./cekura/skills/cekura-onboarding/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

70%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, concise, and clear onboarding workflow with explicit verification gates — but its progressive disclosure is undermined because the core phase files it directs Claude to read are missing from the bundle.

Suggestions

Add the missing phase files (phase0-path.md, phase2-agent.md, phase3-testing-metrics.md, phase4-testing-evaluators.md, phase5-testing-first-run.md, phase6-testing-next.md, phase3-observability-ingest.md, phase4-observability-metrics.md, phase5-observability-evaluate.md, phase6-observability-review.md) that the phase table links to, since the execution model requires reading them.

If the phase files are intentionally external, make that explicit in the body and confirm they resolve; dead 'read the phase file' links break the workflow's actionability.

Verify every link in the phase table and the Phase-1 note resolves to a real file before relying on the navigation.

DimensionReasoningScore

Conciseness

Efficient and assumes Claude's competence with no padding about basic concepts; the execution-model and interaction-style prose is behavioral rule-setting that earns its place, with only minor tightening possible.

4 / 5

Actionability

Gives concrete guidance — named phase files, real tool names (aiagents_list, projects_list, projects_create), and explicit directives like 'read the phase file' and 'never invent IDs' — with minor gaps (actual API calls deferred to api-quickstart.md).

4 / 5

Workflow Clarity

Clearly sequenced one-phase-at-a-time flow with an explicit phase table, named verification gates on phases 5T and 3O, 'never claim done until the call succeeds' feedback loop, and explicit blocked-gate handling, matching the clear-sequence-with-explicit-validation anchor.

5 / 5

Progressive Disclosure

The body is structured as an overview with one-level-deep references, but the 11 phase files (phase0-path.md, phase2-agent.md, phase3-testing-metrics.md, etc.) linked from the phase table do not exist in the bundle — broken/dead references that make navigation impossible, which is a significant structural defect.

2 / 5

Total

15

/

20

Passed

Description

88%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, specific description with comprehensive natural trigger terms and explicit what/when guidance. Third-person voice is correct throughout with no over-claims.

DimensionReasoningScore

Specificity

Names the onboarding domain and several concrete actions ('build evaluators and run simulated calls', 'ingest production call logs and evaluate them') across two paths, with only minor coverage gaps, matching the 'lists several specific actions' anchor.

4 / 5

Completeness

Explicitly answers both what (two onboarding paths: testing and observability) and when (explicit 'Use when the user says ...' clause with concrete trigger phrases), matching the clearly-and-explicitly-answers-both anchor.

5 / 5

Trigger Term Quality

Comprehensive natural phrasing users would actually say — 'get started with Cekura', 'set up Cekura', 'onboard to Cekura', 'I'm new to Cekura', 'walk me through Cekura', 'configure my project', 'first time using Cekura' — covering many natural variations, matching the comprehensive-coverage anchor.

5 / 5

Distinctiveness Conflict Risk

Cekura-specific onboarding niche with distinct, brand-qualified trigger phrases ('Cekura' appears in nearly every trigger), giving minimal overlap risk with other skills.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 10 missing

Warning

Total

15

/

16

Passed

Repository
cekura-ai/cekura-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.