@katanemo
Organization
Intelligent infrastructure primitives for GenAI
17 skills1 repository 7.1K
Design advanced Plano architectures for distinct listeners and layered orchestration. Tighten prompt target schemas, reduce ambiguity in tool calls, and shape migration-safe recommendations with scenarios to check the design.
Review Plano filter chains for MCP setup, clear guardrail rejection messages, and safe ordering. The skill places safety checks before rewriting and enrichment, helping prevent costly processing of unsafe requests while preserving checks on allowed outputs.
Make Plano routing and latency behavior easier to inspect through tracing. The skill guides sampling choices, useful span attributes, and trace queries to investigate routing or latency issues, using trace evidence and reproducible commands.
Builds the Envoy WASM plugins for llm_gateway and prompt_gateway after code changes. If the build fails, it diagnoses and fixes the errors so the plugins can be compiled for the wasm32-wasip1 target.
Check Rust changes by running formatting validation, Clippy linting, and library unit tests in order. It can fix formatting issues, asks for warnings to be resolved, and reports which checks passed or failed.
Adds an AI provider to hermesllm by updating provider identifiers, parsing, request and response types when needed, model lists, and API mappings. It then runs the library tests to check that the changes compile and pass.
Improve Plano multi-agent orchestration by checking agent registration and listener wiring, refining capability-focused descriptions, and defining fallback behavior. Get example prompts for validating that requests reach the intended agent.
Handle operational Plano CLI tasks with an ordered startup troubleshooting flow, guidance for routing coding-agent traffic through `cli_agent`, and template-based project setup. The skill provides a compact runbook with specific commands.
Prepare Plano deployments for production by reviewing Docker networking, conversation state storage, readiness checks, and environment-based secrets. Get deployment checks with diagnostics that help explain likely failure modes.
Improve how Plano chooses and routes requests to models. Review provider defaults, stable model aliases, passthrough authentication for proxy providers, and concrete routing preferences, then check behavior with traces.
Build and install the `planoai` Python CLI locally after changes to its `cli/` code. It syncs the project dependencies, installs the package in editable mode, and checks that the command starts and displays its help.
Create a feature branch from the current changes, commit and push the work, then open a concise pull request targeting main. The workflow also checks Rust formatting and linting before submission.
Prepare a Plano release by choosing a version number or calculating the next patch version, then updating the version strings in the specified project files. It also refreshes the Python CLI lock file and reports the changed files and version transition.
Run the Python CLI test suite after changes to the `cli/` code. The skill syncs dependencies with `uv`, runs `pytest` in verbose mode, and diagnoses and fixes issues when tests fail.
Guide broad work on Plano agent applications, from configuration and model routing to orchestration, filters, tracing, CLI workflows, and deployment readiness. Use it to make focused changes while preserving security and reliability defaults.
Builds the brightstaff native binary in release mode after code changes. If compilation fails, it diagnoses the build errors and fixes them so the binary can be produced.
Checks Plano’s config.yaml for the required version, listener types, provider registration, and secret handling. It helps resolve startup schema validation failures and returns a minimal configuration patch with a plan to verify it using planoai up.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)