CtrlK
BlogDocsLog inGet started
Tessl Logo

cekura-create-agent

Use when the user asks to "create a main agent", "set up a main agent", "add my main agent to Cekura", "configure my main agent", "connect my main agent", "set up mock tools", "add tools to my agent", "upload knowledge base", "configure integration", "connect VAPI", "connect Retell", "connect LiveKit", "connect ElevenLabs", "add dynamic variables", or needs to onboard a voice AI agent onto the Cekura platform. Covers the full agent setup flow: project selection, provider selection, basics and connection type, description, main agent creation, mock tools, knowledge base, dynamic variables, and advanced configuration.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

77%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 orchestration skill with excellent workflow sequencing and an explicit verify-and-retry feedback loop, plus lean mostly-padded-free prose. Its main weakness is progressive disclosure: the body links to 11 phase files that do not exist in the bundle, so the navigation it promises is non-functional.

Suggestions

Add the 11 phaseN-*.md files referenced by the phase table (phase1-project.md through phase11-verify.md) to the bundle, or remove the dead links and inline the essential per-phase instructions.

Trim the repeated 'all 11 phases are mandatory' enforcement to a single statement to tighten conciseness.

Inline one or two concrete API call examples (e.g. a sample POST v2 create-agent body) so the body is executable without requiring the missing phase files.

DimensionReasoningScore

Conciseness

Largely lean and free of concepts Claude already knows, but the 'Never do this' list and repeated enforcement lines (e.g. mandatory-phases restated several times) could be tightened slightly. Not a 5 because minor padding remains; not a 3 because the bulk is efficient.

4 / 5

Actionability

Gives concrete executable guidance (explicit phase announcements, 'Use MCP tools, not raw API calls', the specific X-CEKURA-API-KEY auth header, /setup-mcp), but most API call detail and code live in the referenced phase/reference files rather than inline. Not a 5 because the body itself defers most executable specifics to references; not a 3 because the inline directives are specific and actionable.

4 / 5

Workflow Clarity

The 11-phase process is clearly sequenced with a flow diagram and per-phase table, and includes an explicit validation checkpoint with a feedback loop (Phase 11 verify run → 'go back to the relevant phase, fix the issue, and retry'). Matches the anchor for clear sequence + explicit validation + error-recovery feedback loop.

5 / 5

Progressive Disclosure

Structure and signaling are good (an overview body plus a clear 'Reference Files' section, and the reference files exist), but all 11 phase-file links (phase1-project.md ... phase11-verify.md) point to files absent from the bundle — only SKILL.md is present at root, so the one-level-deep references are broken navigation targets. Not a 4 because the missing targets are a real gap; not a 2 because structure and signaling are present and the references/ files do exist.

3 / 5

Total

16

/

20

Passed

Description

100%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 exemplary: it pairs an explicit 'Use when...' trigger clause loaded with natural phrases users would say against a concrete enumeration of the full setup flow. Specificity, completeness, and distinctiveness are all fully satisfied with no vague fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ("create a main agent", "set up mock tools", "upload knowledge base", "add dynamic variables") plus an enumerated full setup flow, giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both 'what' ("Covers the full agent setup flow: project selection, provider selection...") and 'when' ("Use when the user asks to...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Extensive natural trigger phrases users would actually say ("create a main agent", "connect VAPI", "connect LiveKit", "set up mock tools") with provider-name synonyms included, matching comprehensive natural-term coverage.

5 / 5

Distinctiveness Conflict Risk

Clear niche (Cekura platform onboarding) with distinct triggers tied to specific providers (VAPI, Retell, LiveKit, ElevenLabs), giving minimal conflict risk with other skills.

5 / 5

Total

20

/

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: 11 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.