/adversarial-qa
Exploratory, adversarial QA: drive the running feature in a browser and surface UX issues and edge cases the plan and committed tests did not anticipate — not a re-verification of the spec. Invoked as /adversarial-qa for an ad-hoc session, or applied by the adversarial-qa
$ npx -y skills add cunhaax/ai-workflow --skill adversarial-qa --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/adversarial-qa
Context preview
The summary Claude sees to decide when to auto-load this skill.
Exploratory, adversarial QA: drive the running feature in a browser and surface UX issues and edge cases the plan and committed tests did not anticipate — not a re-verification of the spec. Invoked as /adversarial-qa for an ad-hoc session, or applied by the adversarial-qa
Turns Claude Code into a small development team instead of one agent guessing alone — with a git-level gate that keeps the humans in charge of what actually ships.
Other skills on ai-workflow.
- /code-critic
Code review checklist and coding standards, extended per project by whatever file AGENTS.md's Review & Planning Guidance section names (defaulting to docs/agent-rules/code-critic.md). Invoked as /code-critic for an ad-hoc review, or applied by the code-critic sub-agent in the
Open skill - /feature
Runs the full feature workflow: plan, critique, implement, review, QA. Use this when starting a new feature. Guides you through each phase with explicit gates between steps.
Open skill - /init-workflow
Bootstraps and validates the AI workflow in a project that has this plugin installed: scaffolds whichever project-owned files are missing, detects the project's commands, fills AGENTS.md, points it at review/planning guidance (seeding docs/agent-rules/ or reusing an existing
Open skill - /plan-critic
Critiques an implementation plan using pre-mortem, inversion, load-bearing assumption analysis, and consistency checks. Invoked as /plan-critic for ad-hoc plan critique, or used by the plan-critic sub-agent in the /feature workflow.
Open skill - /plan-draft
Planning rules and plan template for drafting implementation plans. Invoked as /plan-draft for an ad-hoc planning session, or used by the planner sub-agent in the /feature workflow. (Named plan-draft so it does not collide with Claude Code's built-in plan-mode /plan command.)
Open skill - /workflow-inspect
Appends the cost half to a workflow-retro record: parses the feature session's Claude Code transcripts with a bundled read-only script (tokens per agent, wall-clock, handoff tax) and writes the result into the record's Cost section. Companion of /workflow-retro; run it while the
Open skill