CtrlK
BlogDocsLog inGet started
Tessl Logo

cekura-create-agent

Use when the user asks to "create a new agent", "create a main agent", "set up a new 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.

The body is a well-sequenced, operationally tight orchestrator with strong workflow clarity and a real verification feedback loop. Its main weakness is progressive disclosure: the 11 phase files it directs Claude to read are not present in the bundle, so the core workflow cannot actually be navigated as written.

Suggestions

Include the 11 phaseN-*.md files in the bundle (or inline their essential steps) so the workflow's referenced paths resolve — currently every 'Read the phase file' instruction points to a missing file.

Remove the duplication between the ASCII flow diagrams and the phase table; keep one canonical view of the three paths to tighten conciseness.

Consolidate the repeated 'all phases are mandatory' guidance into a single authoritative statement to reduce token overhead.

DimensionReasoningScore

Conciseness

The body is operational and avoids explaining concepts Claude already knows, but the ASCII flow diagrams duplicate the phase table and the 'all phases mandatory' emphasis repeats across the table, execution model, and phase notes — minor trimming possible. Not a 5 because of this redundancy; not a 3 because nothing is padded concept-explanation.

4 / 5

Actionability

Concrete process guidance is present (use MCP tools not curl, 'X-CEKURA-API-KEY' auth header, 'POST v2', named reference files), but the executable per-phase steps are delegated to phaseN-*.md files, leaving minor gaps at the SKILL.md level. Not a 5 because the actual step-by-step execution lives in external files; not a 3 because what is written is concrete and executable, not pseudocode.

4 / 5

Workflow Clarity

A clear 11-phase sequence with explicit gate conditions, one-phase-at-a-time execution rules, and a Phase 11 verification feedback loop ('go back to the relevant phase, fix the issue, and retry the run') plus a checklist and handoff — matching the score-5 anchor with explicit validation and error-recovery loops.

5 / 5

Progressive Disclosure

SKILL.md is a clean overview and the references/ section lists six well-described one-level-deep files plus a script, but the body links 11 phase files (phase1-project.md ... phase11-verify.md) that are absent from the bundle, breaking navigation for the core workflow. Not a 4 because the missing phase files are a material gap, not a minor one; not a 2 because the present references are well-structured and signaled rather than buried.

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 a strong, trigger-rich 'Use when...' statement that covers both what the skill does and when to invoke it, with concrete provider names and task phrases. It is specific, comprehensive, and clearly distinct from generic skills.

DimensionReasoningScore

Specificity

Enumerates concrete actions spanning the full setup flow — 'project selection, provider selection, basics and connection type, description, main agent creation, mock tools, knowledge base, dynamic variables, and advanced configuration' — comprehensive coverage matching the score-5 anchor.

5 / 5

Completeness

Explicitly answers 'when' ('Use when the user asks to ... or needs to onboard a voice AI agent onto the Cekura platform') and 'what' ('Covers the full agent setup flow: ...') with concrete trigger phrases, matching the score-5 anchor.

5 / 5

Trigger Term Quality

Dense natural-language triggers with synonyms ('create a new agent', 'create a main agent', 'set up a new agent', 'set up a main agent') plus provider names (VAPI, Retell, LiveKit, ElevenLabs) and task phrases ('add dynamic variables', 'upload knowledge base'), matching the comprehensive-coverage anchor.

5 / 5

Distinctiveness Conflict Risk

Scoped to a clear niche — onboarding a voice AI agent onto the Cekura platform — with provider-specific triggers, 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.