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.

67

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Risky

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

62%

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

A well-sequenced, highly clear orchestration skill with strong workflow clarity and real reference files, weakened by missing phase-file bundles and some redundant emphasis. Fixing the absent phase files and tightening repetition would raise the lower dimensions.

Suggestions

Ship the 11 phaseN-*.md files referenced in the body and phase table; their absence breaks progressive disclosure and leaves the body's executable steps unresolvable.

Consolidate the repeated mandates ('Never do this' list, 'Do it yourself', 'All 11 phases are mandatory') into a single concise rules block to reduce redundancy.

Inline at least one concrete API call or MCP invocation example in the body so it is actionable without first opening a phase file.

DimensionReasoningScore

Conciseness

Mostly efficient and directive, but restates the same mandates multiple times ('Never do this' list, 'Do it yourself. Do not instruct.', 'All 11 phases are mandatory...') and re-explains agent identity already covered by the phase table, so it could be tightened.

2 / 3

Actionability

Concrete guidance exists (exact auth header X-CEKURA-API-KEY, MCP-vs-curl rule, announce/complete phrasing), but the executable per-phase detail is delegated to phase1..phase11 files that are not present in the bundle, so the body itself lacks copy-paste-ready steps.

2 / 3

Workflow Clarity

Clear 11-phase sequence with three labeled path variants, per-phase gate conditions, a partial-completion resume rule, and an explicit verify->fix->retry feedback loop in Phase 11.

3 / 3

Progressive Disclosure

The six reference files and the upload script are real and one-level-deep, but the 11 phaseN-*.md files referenced throughout the body and table are missing from the bundle, so the core navigation is broken.

2 / 3

Total

9

/

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.

A strong, highly specific description with explicit triggers covering both what the skill does and when to use it, scoped to a distinct niche. No vague fluff or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'create a main agent', 'set up mock tools', 'upload knowledge base', 'add dynamic variables' — plus an enumerated setup flow (project, provider, basics, description, mock tools, KB, dynamic variables, advanced config).

3 / 3

Completeness

Explicit 'Use when the user asks to...' trigger clause and an explicit 'Covers the full agent setup flow: ...' what-it-does clause — both what and when are clearly answered.

3 / 3

Trigger Term Quality

Extensive natural phrasings a user would actually say ('connect VAPI', 'connect Retell', 'connect LiveKit', 'connect ElevenLabs', 'add my main agent to Cekura') with good variation coverage.

3 / 3

Distinctiveness Conflict Risk

Narrow Cekura-platform niche with named-provider triggers (VAPI, Retell, LiveKit, ElevenLabs) makes it clearly distinguishable and unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

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.