CtrlK
BlogDocsLog inGet started
Tessl Logo

cekura-create-agent

Use when the user asks to "create an agent", "create a new agent", "set up an agent", "walk me through creating an agent", "connect my agent", "create a main agent", "set up a main agent", "add my main agent to Cekura", "configure my main agent", "connect my main agent", "import my agent from another platform", "create an agent from an exported config", "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 connect a voice AI agent to the Cekura platform for testing or observability. 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.

60

Quality

70%

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-create-agent/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

48%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-organized, disciplined execution protocol with excellent sequencing and error-recovery rules, but it is a router for a fleet of phase files that are missing from the bundle, which guts its actionability and breaks progressive disclosure. Redundant triple encoding of the phase-routing information also costs conciseness.

Suggestions

Ship the 11 phaseN-*.md files in the bundle (references/ or a phases/ directory) — the Execution Model mandates reading them for every phase, and their absence makes the skill non-executable as distributed.

Consolidate the three redundant representations of phase routing (the two ASCII flow diagrams, the 11-column table, and the 'All 11 phases are mandatory' prose paragraph) into the table alone.

Inline the per-phase gate conditions next to each table row instead of deferring them entirely to the phase files, so the sequence is verifiable even before the phase file is opened.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence and never explains known concepts, but phase routing is encoded three times (two ASCII diagrams, an 11-column table, and a prose paragraph) — genuinely redundant material that could be consolidated, matching the 'mostly efficient but could be tightened' anchor.

3 / 5

Actionability

The core directive "Read the phase file — open and follow the instructions in phaseN-*.md" delegates all executable content to 11 phase files that are absent from the bundle, so the actual steps, API calls, and field names are unreachable; only fragments like the X-CEKURA-API-KEY auth header and MCP-tool preference are concrete — high-level hints with the specific execution steps missing.

2 / 5

Workflow Clarity

Sequencing is explicit (numbered phases, skip rules for auto-import providers, a mandatory verify phase, and an error-recovery loop: "go back to the relevant phase, fix the issue, and retry the run"), but per-phase gate conditions are only referenced ('Satisfy the gate condition') without being stated, a minor validation gap versus the explicit-checkpoint anchor.

4 / 5

Progressive Disclosure

The Reference Files section is well-signaled and one level deep with all six references and the script present, but the primary navigation targets — the 11 phaseN-*.md links in the phase table — point to files that do not exist in the bundle, breaking the disclosure chain for the skill's main path.

3 / 5

Total

12

/

20

Passed

Description

91%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 description with near-exhaustive natural trigger phrasing, an explicit Use-when clause, and a concrete enumeration of the setup flow. Its only weaknesses are stage-name 'what' statements instead of action verbs and somewhat generic lead triggers ('create an agent') that could collide with other agent-creation skills.

DimensionReasoningScore

Specificity

Enumerates the full setup flow concretely ("project selection, provider selection, basics and connection type, description, main agent creation, mock tools, knowledge base, dynamic variables, and advanced configuration") — several specific items, but these are stage names rather than executable actions, leaving minor gaps versus the comprehensive-actions anchor.

4 / 5

Completeness

Explicitly answers 'when' with a long 'Use when…' clause of concrete trigger phrases and 'what' with "Covers the full agent setup flow: …" and "connect a voice AI agent to the Cekura platform for testing or observability" — both halves explicit and concrete.

5 / 5

Trigger Term Quality

Comprehensive synonym coverage ("create an agent", "create a new agent", "set up an agent", "walk me through creating an agent") plus provider-specific natural terms ("connect VAPI", "connect Retell", "connect LiveKit", "connect ElevenLabs") matches the full-synonym-coverage anchor; nothing a user would naturally say is missing.

5 / 5

Distinctiveness Conflict Risk

Clear Cekura/voice-AI niche with provider names as distinct triggers, but generic phrases like "create an agent" and "set up an agent" could plausibly trigger subagent-creation or other platform skills — minor overlap risk rather than the minimal-conflict anchor.

4 / 5

Total

18

/

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.

Validation — 15 / 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.