Skip to content

Full-flow orchestration

These two skills are meta-skills: they don't do the work themselves; instead, they chain several of the atomic skills described in the rest of this reference, in a fixed order, to handle an end-to-end flow in a single invocation and without intermediate human pauses.


lippia-neo-meta-run-user-story-e2e

When to use it

It runs the full 6-step flow on a user story (read story → plan → explore → generate suite → run and repair → report), for FE, BE, or hybrid stories, in any configured framework. It's used when someone asks to run the full QA workflow end to end, or when a story needs to go from spec to a green, reported suite in a single pass. It runs all 6 steps in a row, without pausing to ask for confirmation between steps; it only stops on an unrecoverable blocking error (adapter not implemented, missing qa-stack.yaml, missing acceptance criteria), returning overall_status: blocked instead of asking whether to continue.

Invocation example
{
  "input": {
    "user_story_path": "user-stories/PA-US-02.md"
  },
  "config": {
    "test_framework": "playwright",
    "app_type": "web"
  }
}
Input Type Description
input.user_story_path Required path to the story's .md file.
config.test_framework Required from qa-stack.yaml (playwright | lippia | pytest).
config.app_type Required from qa-stack.yaml (web | api | hybrid); input for the FE/BE/hybrid router.
config.paths Required from qa-stack.yaml: test_plans_dir, tests_dir, reports_dir.

Performance frameworks

With test_framework: k6 or jmeter this skill doesn't apply: it doesn't continue, with the reason framework_not_supported_by_this_skill. Those frameworks are handled with the performance skills.

Output

Field Description
us_id real id of the story.
story_type the router's classification: frontend / backend / hybrid.
artifacts test_plan_path, manual_execution_report_path, generated_files, report_path.
heal_summary iterations, initial/final count, non-repairable tests.
overall_status passed / failed / blocked.
Chains with

Orchestrates, in strict order, lippia-neo-read-user-story → lippia-neo-create-test-plan → lippia-neo-run-manual-testing → lippia-neo-generate-test-suite → lippia-neo-run-and-heal → lippia-neo-write-test-report. Before starting, it requires a pre-check of qa-stack.yaml and redirects to lippia-neo-bootstrap-stack if it doesn't exist.


lippia-neo-meta-run-exploratory-testing

When to use it

To run a broad exploratory testing portfolio end to end in a single autonomous pass: discover areas → create a bounded set of charters with the available context → run each charter with resumable SBTM sessions → consolidate a portfolio report. It's used to explore the whole app or a broad scope, or for a broad exploratory regression/smoke test. It's the autonomous equivalent (without human checkpoints) of the exploratory portfolio playbook; it doesn't reimplement the internal logic of any exploratory skill, it only chains their real outputs. It doesn't assume a fixed risk catalog or mandatory scoring: if the project provides priorities, changes, or criticality, they're used; if not, it carries on without making them up.

Invocation example
{
  "input": {
    "request": "Thoroughly explore the payments module before the release"
  },
  "config": {
    "environment": { "base_url": "https://staging.miapp.com" },
    "paths": { "exploratory_dir": "exploration/" }
  }
}
Input Type Description
input.request Required the broad exploration request.
config.paths.exploratory_dir Required root directory for artifacts.
config.environment.base_url / config.environment.entry_point Optional base URL / entry point of the app; if there isn't enough information to discover a real scope, the flow ends as blocked.
input.artifact_scope_id, input.max_charters, input.time_box_minutes, input.report_language, input.allow_persistent_mutations, input.max_resume_iterations Optional Defaults: max_charters 5, time_box_minutes 60, report_language es, allow_persistent_mutations false, max_resume_iterations 8.
input.selection_context, input.business_priorities, input.changed_areas, input.known_constraints Optional context for selecting and ordering the charters.
config.environment.app_version / config.environment.os, config.auth, config.paths.env_file, config.paths.user_stories_storage.local_path, config.paths.test_plans_dir Optional

Output

Field Description
artifact_scope_id, discovery_path, portfolio_manifest_path, charter_paths, session_reports, final_report_path, summary
overall_status completed / partial / blocked.
Chains with

Orchestrates, in a fixed order, lippia-neo-discover-exploratory-areas → lippia-neo-create-exploratory-charters → lippia-neo-run-exploratory-session (once per charter, sequentially; if a session stays in_progress it resumes it, capped at max_resume_iterations and cutting it off as blocked if two consecutive resumes show no progress) → lippia-neo-write-exploratory-testing-report. On a global block (target or authentication unavailable) it aborts the rest of the sessions; a block on a specific area is recorded and it moves on.