cli-anything-web

Generate a complete agent-native CLI for any web app by recording and analyzing network traffic via playwright-cli. Runs the full pipeline with site assessment, capture, implementation, testing, and verification.

List all available CLI-Anything-Web CLIs (installed and generated).

Record network traffic from a web app without generating a CLI. Useful for initial exploration or adding more coverage data.

Refine an existing cli-anything-web CLI by recording additional traffic and expanding command coverage. Performs gap analysis and implements missing endpoints.

Run tests for a cli-anything-web CLI and update TEST.md with results.

Audit all cli-web-* CLIs for convention drift against current HARNESS.md. Reports PASS/FAIL per check per CLI in a matrix format. Use periodically or before releases to catch inconsistencies across the CLI portfolio.

Review a cli-web-* CLI for HARNESS.md convention compliance. Checks exception hierarchy, auth patterns, client architecture, CLI patterns (UTF-8, shlex, handle_errors), and JSON output format. Returns scored findings. Use during Phase 4 standards review.

Review a cli-web-* CLI from the end-user perspective. Checks --help completeness, REPL help sync, JSON output quality, protocol leak detection, and entry point correctness. Returns scored findings. Use during Phase 4 standards review.

Review a cli-web-* CLI implementation against its <APP>.md API map. Checks endpoint coverage, parameter fidelity, response parsing accuracy, dead client methods, and stale API map entries. Returns scored findings. Use during Phase 4 standards review — dispatched by the standards skill.

Generate core/ module scaffolds for cli-web-* CLIs. Produces exceptions.py, client.py, helpers.py, config.py, output.py, and (for batchexecute) the rpc/ subpackage. All files use placeholder syntax that the methodology skill fills in.

Capture HTTP traffic from web apps using playwright-cli. Includes site fingerprinting (framework detection, protection checks, iframe detection, auth detection, API discovery) and full traffic recording with tracing and optional HAR output. TRIGGER when: "record traffic from", "capture API calls from", "start Phase 1 for", "analyze traffic from URL", "assess site", "site fingerprint", "start capture for", "open browser for", or any URL is given as the first step of CLI generation. DO NOT trigger for: Phase 2 implementation, test writing, or quality validation.

Compare implemented CLI commands against <APP>.md API map to find missing endpoints, incomplete CRUD, dead client methods, and priority gaps. TRIGGER when: "gap analysis", "what's missing", "coverage report", "what endpoints are not implemented", or as a sub-step of the refine workflow. DO NOT trigger for: "refine" alone (use the /cli-anything-web:refine command).

Analyze captured HTTP traffic, design CLI architecture, and implement the Python CLI package. Covers Phase 2 of the pipeline: parse raw-traffic.json, identify protocol type, map endpoints, design Click command groups, implement with parallel subagents. TRIGGER when: "analyze traffic", "design CLI", "implement CLI", "build CLI from network traffic", "generate API wrapper", "reverse engineer web API", "start Phase 2", raw-traffic.json exists and capture is complete, or after the capture skill finishes. DO NOT trigger for: traffic recording (use capture), test writing (use testing), or quality checks (use standards).

Quality standards and Phase 4 review/publish/verify for cli-web-* CLIs. Covers implementation review (3 parallel agents), the 75-check quality checklist, package publishing (pip install -e .), and end-user smoke testing (READ + WRITE). TRIGGER when: "validate CLI", "publish CLI", "review CLI", "pip install -e .", "smoke test", "quality check", "start Phase 4", "75-check", "generate Claude skill", "check if implementation is complete", "verify implementation quality", or after testing skill completes. DO NOT trigger for: traffic capture, implementation, or test writing.