framework/deno/skills/flowai-deno-cli/SKILL.md
Manage all Deno capabilities via CLI (run, test, fmt, lint, task, add, etc.). Use this skill when you need to execute Deno commands, manage dependencies, run tests, or handle local development workflows.
npx skillsauth add korchasa/flow flowai-deno-cliInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This skill provides instructions for effective use of the Deno CLI for development, testing, and dependency management.
deno run [OPTIONS] <FILE>: Run a script. Always consider permission flags, e.g., --allow-net, --allow-read, --allow-env.deno task <TASK>: Run a task defined in deno.json. This is the preferred way to run project scripts.deno serve [OPTIONS] <FILE>: Run an HTTP server.deno repl: Start an interactive Read-Eval-Print Loop (REPL).deno eval: Evaluate a script from the command line.deno add <PACKAGE>: Add dependencies (e.g., deno add jsr:@std/assert or deno add npm:express).deno install: Install project dependencies.deno outdated: Check for outdated dependencies.deno remove <PACKAGE>: Remove a dependency.deno uninstall: Uninstall a dependency or a globally installed script.deno approve-scripts: Approve npm lifecycle scripts.deno test [OPTIONS]: Run tests. Use --watch for development mode.deno fmt: Format source files.deno lint: Lint source files.deno check: Type-check dependencies.deno bench: Run benchmarks.deno doc: Generate and show documentation.deno compile: Compile a script into a self-contained executable.deno coverage: Print coverage reports.deno info: Show info about cache or source files.deno init: Initialize a new project.deno publish: Publish the current package to JSR or npm.deno upgrade: Upgrade the Deno executable.deno clean: Remove the cache directory.deno jupyter: Deno kernel for Jupyter notebooks.Deno is secure by default. When using deno run or deno test, you must explicitly grant permissions if the script needs access to the network, files, or environment:
--allow-read: Read access.--allow-write: Write access.--allow-net: Network access.--allow-env: Environment variable access.-A or --allow-all: Allow everything (use with caution).Some Deno APIs require explicit opt-in via --unstable-* flags or deno.json config:
Deno.openKv() → --unstable-kv or "unstable": ["kv"] in deno.jsonDeno.cron() → --unstable-cron or "unstable": ["cron"] in deno.jsonnew Deno.UnsafeWindowSurface() → --unstable-webgpuWhen reviewing code, check for unstable API usage and ensure the corresponding flag is set.
deno.json)Always check for deno.json or deno.jsonc in the project root to understand imports, tasks, and lint/fmt settings.
deno test --allow-read --allow-env
deno add jsr:@std/http
deno fmt
deno help <command> for detailed information on any subcommand.deno compile to create standalone binaries.flowai-deno-deploy skill.tools
Delegate a task to another AI IDE's CLI (codex / claude / opencode / cursor-agent) through an isolated-context subagent. Triggers on "delegate to <ide>", "have <ide> do <task>", "execute <task> in <ide>", "offload to <ide>". For one-shot relay or fan-out comparison use `ai-ide-runner` instead.
tools
Run prompts in Claude Code, OpenCode, Cursor, or Codex CLIs from the current session — pick one IDE, fan out across several, or compare models. You are a courier that relays the other runtime's stdout verbatim, do not synthesise your own answer. Use on "run in <ide>", "compare <ide> vs <ide>", "try on <model>", "which IDE handles X better", "run across models".
tools
Recommend which LLM model to use for a task. Use when asked "which model / best LLM for X", "pick a model for this task", or for a model shortlist ranked by live leaderboard evidence (coding, reasoning, agentic, tool-use, price, speed). Live-fetches public leaderboards and ranks models with per-axis rationale and citations.
development
Produce a comprehensive Product Requirements Document (PRD). Use when the user asks to write a PRD or formalize a feature's scope, goals, and success metrics.