cekura-create-agent
Use when the user asks to "create an agent", "set up an agent", "add my agent to Cekura", "configure my voice agent", "connect my 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: collecting context, creating the agent, configuring the provider integration, setting up mock tools, uploading knowledge base files, and adding dynamic variables.
75
92%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Risky
Do not use without reviewing
Quality
Discovery
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.
This is a strong description that excels across all dimensions. It provides extensive explicit trigger phrases, clearly describes the full scope of capabilities, and is highly distinctive due to the specific platform and provider names. The only minor note is that the trigger phrase list is quite long, but it serves the purpose of comprehensive coverage well.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: collecting context, creating the agent, configuring provider integration, setting up mock tools, uploading knowledge base files, and adding dynamic variables. These are clear, actionable steps. | 3 / 3 |
Completeness | Clearly answers both 'what' (full agent setup flow including context collection, agent creation, provider integration, mock tools, knowledge base, dynamic variables) and 'when' (explicit 'Use when...' clause with extensive trigger phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger phrases users would say: 'create an agent', 'set up an agent', 'connect my agent', 'upload knowledge base', 'configure integration', plus specific provider names like VAPI, Retell, LiveKit, ElevenLabs. These are highly natural user phrases. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Cekura platform voice AI agent onboarding. The specific platform name (Cekura) and provider names (VAPI, Retell, LiveKit, ElevenLabs) make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-structured skill that guides Claude through a complex multi-phase agent onboarding flow with concrete API payloads, clear sequencing, and appropriate progressive disclosure to reference files. The actionability is excellent with real JSON examples and provider-specific details. Minor verbosity exists in explanatory sections (what KB files enable, what dynamic variables enable) that could be trimmed, but overall the content earns its token budget.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long but most content is necessary for the multi-phase workflow. Some unnecessary explanations exist (e.g., explaining what knowledge base files enable, what dynamic variables enable) that Claude could infer, and the purpose/description section at the top is somewhat redundant. However, the bulk of the content is actionable configuration details. | 2 / 3 |
Actionability | Provides concrete JSON payloads, curl commands, exact API endpoints, specific field names and formats, and provider-specific credential requirements. The mock tool setup includes realistic example data with phone format variants. Nearly every step has executable, copy-paste-ready guidance. | 3 / 3 |
Workflow Clarity | The 7-phase workflow is clearly sequenced with explicit validation in Phase 7, each phase builds on the previous one's output (agent ID flows through), and there's guidance on skipping completed steps. The verification checklist at the end provides a clear feedback loop, and the skill explicitly states 'validate each step before moving to the next.' | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-signaled references to deeper content: `references/integrations.md` for provider details, `references/mock-tool-design.md` for mock tool patterns, `references/api-reference.md` for full API schemas, and `scripts/upload-agent.sh` for large payloads. References are one level deep and clearly described, though bundle files weren't provided to verify their existence. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- cekura-ai/cekura-skills
- Commit
24ad1d0
- 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.