Cekura Coordinator
Purpose
Route users to the right Cekura skill or command based on what they need. This is the "front desk" — it knows everything available across all Cekura plugins and helps users find the right tool.
Performing Platform Actions
When this skill suggests creating, listing, updating, or evaluating something on Cekura, prefer using available platform tools over describing API calls or dashboard steps. In Claude Code with the Cekura plugin installed, these tools are auto-configured and handle authentication, parameter validation, and error handling for you. Fall back to direct API endpoints or dashboard guidance only when no tools are available in the current session.
When This Skill Loads
- User just installed cekura-skills and asks "what can I do?"
- User asks for help or doesn't know which command to use
- User describes a task and you need to route them
Available Skills & Commands
Skills activate when the user describes a relevant task. Commands are slash commands available only in Claude Code with the plugin installed.
Skills
| Skill |
Use when |
cekura-onboarding |
New to Cekura, first-time setup, platform walkthrough |
cekura-create-agent |
Set up a voice AI agent — provider, mock tools, KB, dynamic vars |
cekura-self-improving-agent |
Auto-tune agent prompts from eval results — diagnose → propose → apply → re-validate |
cekura-metric-design |
Design new metrics, improve existing ones, metric best practices |
cekura-metric-improvement |
Improve metric accuracy through feedback cycle (labs workflow) |
cekura-predefined-metrics |
Catalog of built-in metrics — what each does, costs, constraints, configuration |
cekura-eval-design |
Design evaluators, test suites, coverage strategy, conditional actions |
cekura-personality-design |
Choose, fork or create a personality — the simulated caller's voice, accent, speed, interruption and idle behavior |
cekura-infra-test-suite |
Source-controlled JSON Tests-as-Code suite — repository discovery, deterministic CI coverage, safe dry-run validation |
cekura-bot-test-writer |
Keep that committed suite in step with the code — read a PR diff, edit the smallest thing that closes a real gap |
cekura-flag-call-log-failures |
Triage recent production call logs against KPIs — failure rates + outcome distribution |
cekura-generate-scenarios |
Turn flagged production failures into regression evaluator scenarios |
Commands
| Command |
Use when |
/cekura-onboarding |
Run the guided onboarding flow (state-aware, picks up where you left off) |
/setup-mcp |
Configure the Cekura MCP server (Claude Code only) |
/upgrade-skills |
Update all Cekura skills to the latest version |
/report-bug |
Report a bug — files a GitHub issue, optionally attempts a fix |
/create-metric |
Create or update a metric via API |
/list-metrics |
List metrics for an agent or project |
/evaluate-calls |
Run metrics on specific calls |
/improve-metric |
Full improvement cycle: collect feedback, run labs, auto-improve |
/manual-create-update-eval |
Create or update a single evaluator with full field walkthrough |
/autogen-eval |
Auto-generate evaluators (or bulk create from CSV/JSON) |
/list-evals |
List evaluators for an agent or project |
/run-evals |
Execute evaluators (run test scenarios) |
/eval-results |
Check results from a test run |
/cekura-report |
Full end-to-end quality report — generates 10 evals, runs them, produces structured analysis |
Routing Guide
When the user describes what they need, route them:
| User Need |
Route To |
| "I'm new to Cekura" / first-time setup |
cekura-onboarding skill |
| "Set up my agent" / "connect my voice agent" |
cekura-create-agent skill |
| "Configure MCP" / "MCP not working" |
/setup-mcp command |
| "Create metrics for my agent" |
cekura-metric-design skill |
| "My metrics are giving wrong results" |
/improve-metric command (or cekura-metric-improvement skill for full cycle) |
| "I need to test my agent" |
cekura-eval-design skill |
| "Generate test scenarios" / any batch or category-level request, either format |
cekura-eval-design skill (/autogen-eval for the walkthrough where slash commands exist) |
| "Create a specific test scenario" — scripted / deterministic / regression / IVR / DTMF / compliance flow |
cekura-eval-design skill (conditional actions: generated for a category, created directly for a dictated script), /manual-create-update-eval for the field walkthrough where slash commands exist |
| "Create a specific test scenario" — natural conversation, edge case, red-team |
cekura-eval-design skill: generate (num_scenarios: 1) for a category-level ask, create directly for a fully described case |
| "Update / duplicate an existing scenario" |
cekura-eval-design skill (§ Changing existing evaluators), /manual-create-update-eval for the walkthrough where slash commands exist |
| "Run my tests" |
/run-evals command |
| "Check test results" |
/eval-results command |
| "Create a metric that checks X" |
/create-metric command (or cekura-metric-design skill for complex metrics) |
| "Update this metric" |
/create-metric command (handles both create and update) |
| "Evaluate calls against metrics" |
/evaluate-calls command |
| "Update my skills" |
/upgrade-skills command |
| "What metrics should I have?" |
cekura-metric-design skill (baseline metrics section) |
| "Help me improve this metric" |
/improve-metric command |
| "Leave feedback on a metric result" |
/improve-metric command (Phase 1: feedback collection) |
| "Set up production monitoring" |
cekura-onboarding skill (Phase 6) + observability docs |
| "Add mock tools" / "set up tools" — defining the tools on the agent |
cekura-create-agent skill (Phase 7) |
| "Mock tool data for a test" / "add a mock entry" / "create the test profile" — data an evaluator will use |
cekura-eval-design skill (§ Test data) |
| "Upload knowledge base" |
cekura-create-agent skill (Phase 8) |
| "Something's broken" / "file a bug" |
/report-bug command |
| "Improve my agent" / "auto-tune from eval results" |
cekura-self-improving-agent skill |
| "Which built-in metrics are available?" / "what does Hallucination Detection cost?" |
cekura-predefined-metrics skill |
| "Fix this prod call bug" / "reproduce and test a fix" |
cekura-self-improving-agent |
| "CI/CD tests for my voice bot" / "commit a JSON test suite" / "Tests-as-Code for my voice repo" |
cekura-infra-test-suite skill |
| "Update the tests for this PR" / "does this diff need new voice tests" / "keep my suite in sync" / "run a test writer on every PR" |
cekura-bot-test-writer skill |
| "What % of calls have " / "analyze my recent calls" |
cekura-flag-call-log-failures skill |
| "Create scenarios from failed calls" / "replay prod failures as tests" |
cekura-generate-scenarios skill |
| "Run a full quality report" / "generate evals and run them end-to-end" |
/cekura-report command |
Typical User Journeys
Journey 1: Brand New User
/setup-mcp → Configure MCP server for API access (Claude Code plugin users)- cekura-onboarding → Set up account and project
- cekura-create-agent → Add agent with provider, mock tools, KB, dynamic vars
- cekura-onboarding → Enable pre-defined metrics, generate first evaluators
- cekura-onboarding → Run first tests, review results
- cekura-metric-design → Create custom metrics based on what they learned
- cekura-eval-design → Build targeted test suites
Journey 2: Has Agent, Needs Testing
- cekura-eval-design → Design test suite
/autogen-eval → Auto-generate evaluators/run-evals → Execute tests/eval-results → Review results
Journey 3: Has Metrics, Needs Improvement
/improve-metric → Full cycle: collect feedback, check readiness, auto-improve/evaluate-calls → Validate changes
Journey 4: Production Monitoring
- cekura-metric-design → Design observability metrics
/create-metric → Deploy metrics (create or update)/evaluate-calls → Validate on sample calls
API Access
For Claude Code plugin users: each plugin auto-configures access to the Cekura API. If commands or platform operations aren't working, run /setup-mcp to configure the connection.
For other clients (Cursor, Codex, npx skills installs, etc.): use the Cekura dashboard at https://dashboard.cekura.ai or call the API directly using your API key.
Next Steps
This skill routes — it doesn't perform tasks itself. After confirming the user's need, invoke the matching skill:
- New to Cekura → cekura-onboarding
- Connecting an agent → cekura-create-agent
- Auto-tuning an agent prompt from eval results → cekura-self-improving-agent
- Designing metrics → cekura-metric-design
- Improving metric accuracy → cekura-metric-improvement
- Picking which built-in metrics to use → cekura-predefined-metrics
- Designing test scenarios → cekura-eval-design
- Fixing a production call bug end-to-end → cekura-self-improving-agent
- Repository-owned JSON CI/CD test suite → cekura-infra-test-suite
- Updating that suite for a pull request → cekura-bot-test-writer
- Triaging production call logs → cekura-flag-call-log-failures
- Turning prod failures into scenarios → cekura-generate-scenarios
Documentation
1---2name: cekura-coordinator3description: Use when the user asks "what can Cekura do", "what commands are available", "help me with Cekura", "what skills do I have", "show me Cekura features", "what's available", "how do I use Cekura", or needs guidance on which Cekura skill to use for their task. Also relevant as the entry point when a user has just installed cekura-skills for the first time.4license: MIT5---67# Cekura Coordinator89## Purpose1011Route users to the right Cekura skill or command based on what they need. This is the "front desk" — it knows everything available across all Cekura plugins and helps users find the right tool.1213## Performing Platform Actions1415When this skill suggests creating, listing, updating, or evaluating something on Cekura, **prefer using available platform tools over describing API calls or dashboard steps**. In Claude Code with the Cekura plugin installed, these tools are auto-configured and handle authentication, parameter validation, and error handling for you. Fall back to direct API endpoints or dashboard guidance only when no tools are available in the current session.1617## When This Skill Loads1819- User just installed cekura-skills and asks "what can I do?"20- User asks for help or doesn't know which command to use21- User describes a task and you need to route them2223## Available Skills & Commands2425Skills activate when the user describes a relevant task. Commands are slash commands available only in Claude Code with the plugin installed.2627### Skills2829| Skill | Use when |30|-------|----------|31| `cekura-onboarding` | New to Cekura, first-time setup, platform walkthrough |32| `cekura-create-agent` | Set up a voice AI agent — provider, mock tools, KB, dynamic vars |33| `cekura-self-improving-agent` | Auto-tune agent prompts from eval results — diagnose → propose → apply → re-validate |34| `cekura-metric-design` | Design new metrics, improve existing ones, metric best practices |35| `cekura-metric-improvement` | Improve metric accuracy through feedback cycle (labs workflow) |36| `cekura-predefined-metrics` | Catalog of built-in metrics — what each does, costs, constraints, configuration |37| `cekura-eval-design` | Design evaluators, test suites, coverage strategy, conditional actions |38| `cekura-personality-design` | Choose, fork or create a personality — the simulated caller's voice, accent, speed, interruption and idle behavior |39| `cekura-infra-test-suite` | Source-controlled JSON Tests-as-Code suite — repository discovery, deterministic CI coverage, safe dry-run validation |40| `cekura-bot-test-writer` | Keep that committed suite in step with the code — read a PR diff, edit the smallest thing that closes a real gap |41| `cekura-flag-call-log-failures` | Triage recent production call logs against KPIs — failure rates + outcome distribution |42| `cekura-generate-scenarios` | Turn flagged production failures into regression evaluator scenarios |4344### Commands4546| Command | Use when |47|---------|----------|48| `/cekura-onboarding` | Run the guided onboarding flow (state-aware, picks up where you left off) |49| `/setup-mcp` | Configure the Cekura MCP server (Claude Code only) |50| `/upgrade-skills` | Update all Cekura skills to the latest version |51| `/report-bug` | Report a bug — files a GitHub issue, optionally attempts a fix |52| `/create-metric` | Create or update a metric via API |53| `/list-metrics` | List metrics for an agent or project |54| `/evaluate-calls` | Run metrics on specific calls |55| `/improve-metric` | Full improvement cycle: collect feedback, run labs, auto-improve |56| `/manual-create-update-eval` | Create or update a single evaluator with full field walkthrough |57| `/autogen-eval` | Auto-generate evaluators (or bulk create from CSV/JSON) |58| `/list-evals` | List evaluators for an agent or project |59| `/run-evals` | Execute evaluators (run test scenarios) |60| `/eval-results` | Check results from a test run |61| `/cekura-report` | Full end-to-end quality report — generates 10 evals, runs them, produces structured analysis |6263## Routing Guide6465When the user describes what they need, route them:6667| User Need | Route To |68|-----------|----------|69| "I'm new to Cekura" / first-time setup | **cekura-onboarding** skill |70| "Set up my agent" / "connect my voice agent" | **cekura-create-agent** skill |71| "Configure MCP" / "MCP not working" | `/setup-mcp` command |72| "Create metrics for my agent" | **cekura-metric-design** skill |73| "My metrics are giving wrong results" | `/improve-metric` command (or **cekura-metric-improvement** skill for full cycle) |74| "I need to test my agent" | **cekura-eval-design** skill |75| "Generate test scenarios" / any batch or category-level request, either format | **cekura-eval-design** skill (`/autogen-eval` for the walkthrough where slash commands exist) |76| "Create a specific test scenario" — scripted / deterministic / regression / IVR / DTMF / compliance flow | **cekura-eval-design** skill (conditional actions: generated for a category, created directly for a dictated script), `/manual-create-update-eval` for the field walkthrough where slash commands exist |77| "Create a specific test scenario" — natural conversation, edge case, red-team | **cekura-eval-design** skill: generate (`num_scenarios: 1`) for a category-level ask, create directly for a fully described case |78| "Update / duplicate an existing scenario" | **cekura-eval-design** skill (§ Changing existing evaluators), `/manual-create-update-eval` for the walkthrough where slash commands exist |79| "Run my tests" | `/run-evals` command |80| "Check test results" | `/eval-results` command |81| "Create a metric that checks X" | `/create-metric` command (or **cekura-metric-design** skill for complex metrics) |82| "Update this metric" | `/create-metric` command (handles both create and update) |83| "Evaluate calls against metrics" | `/evaluate-calls` command |84| "Update my skills" | `/upgrade-skills` command |85| "What metrics should I have?" | **cekura-metric-design** skill (baseline metrics section) |86| "Help me improve this metric" | `/improve-metric` command |87| "Leave feedback on a metric result" | `/improve-metric` command (Phase 1: feedback collection) |88| "Set up production monitoring" | **cekura-onboarding** skill (Phase 6) + observability docs |89| "Add mock tools" / "set up tools" — defining the tools on the agent | **cekura-create-agent** skill (Phase 7) |90| "Mock tool data for a test" / "add a mock entry" / "create the test profile" — data an evaluator will use | **cekura-eval-design** skill (§ Test data) |91| "Upload knowledge base" | **cekura-create-agent** skill (Phase 8) |92| "Something's broken" / "file a bug" | `/report-bug` command |93| "Improve my agent" / "auto-tune from eval results" | **cekura-self-improving-agent** skill |94| "Which built-in metrics are available?" / "what does Hallucination Detection cost?" | **cekura-predefined-metrics** skill |95| "Fix this prod call bug" / "reproduce and test a fix" | **cekura-self-improving-agent** |96| "CI/CD tests for my voice bot" / "commit a JSON test suite" / "Tests-as-Code for my voice repo" | **cekura-infra-test-suite** skill |97| "Update the tests for this PR" / "does this diff need new voice tests" / "keep my suite in sync" / "run a test writer on every PR" | **cekura-bot-test-writer** skill |98| "What % of calls have <problem>" / "analyze my recent calls" | **cekura-flag-call-log-failures** skill |99| "Create scenarios from failed calls" / "replay prod failures as tests" | **cekura-generate-scenarios** skill |100| "Run a full quality report" / "generate evals and run them end-to-end" | `/cekura-report` command |101102## Typical User Journeys103104### Journey 1: Brand New User1051. `/setup-mcp` → Configure MCP server for API access (Claude Code plugin users)1062. **cekura-onboarding** → Set up account and project1073. **cekura-create-agent** → Add agent with provider, mock tools, KB, dynamic vars1084. **cekura-onboarding** → Enable pre-defined metrics, generate first evaluators1095. **cekura-onboarding** → Run first tests, review results1106. **cekura-metric-design** → Create custom metrics based on what they learned1117. **cekura-eval-design** → Build targeted test suites112113### Journey 2: Has Agent, Needs Testing1141. **cekura-eval-design** → Design test suite1152. `/autogen-eval` → Auto-generate evaluators1163. `/run-evals` → Execute tests1174. `/eval-results` → Review results118119### Journey 3: Has Metrics, Needs Improvement1201. `/improve-metric` → Full cycle: collect feedback, check readiness, auto-improve1212. `/evaluate-calls` → Validate changes122123### Journey 4: Production Monitoring1241. **cekura-metric-design** → Design observability metrics1252. `/create-metric` → Deploy metrics (create or update)1263. `/evaluate-calls` → Validate on sample calls127128## API Access129130For Claude Code plugin users: each plugin auto-configures access to the Cekura API. If commands or platform operations aren't working, run `/setup-mcp` to configure the connection.131132For other clients (Cursor, Codex, npx skills installs, etc.): use the Cekura dashboard at https://dashboard.cekura.ai or call the API directly using your API key.133134## Next Steps135136This skill routes — it doesn't perform tasks itself. After confirming the user's need, **invoke the matching skill**:137138- New to Cekura → **cekura-onboarding**139- Connecting an agent → **cekura-create-agent**140- Auto-tuning an agent prompt from eval results → **cekura-self-improving-agent**141- Designing metrics → **cekura-metric-design**142- Improving metric accuracy → **cekura-metric-improvement**143- Picking which built-in metrics to use → **cekura-predefined-metrics**144- Designing test scenarios → **cekura-eval-design**145- Fixing a production call bug end-to-end → **cekura-self-improving-agent**146- Repository-owned JSON CI/CD test suite → **cekura-infra-test-suite**147- Updating that suite for a pull request → **cekura-bot-test-writer**148- Triaging production call logs → **cekura-flag-call-log-failures**149- Turning prod failures into scenarios → **cekura-generate-scenarios**150151## Documentation152153- Full API docs: https://docs.cekura.ai/api-reference154- LLM-friendly index: https://docs.cekura.ai/llms.txt155- Concepts: https://docs.cekura.ai/documentation/key-concepts/
cekura-ai