Claude Skills by cunhaax

Exploratory, adversarial QA: exercise a feature through whichever surface(s) it exposes — UI, API, or both — and surface issues 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 sub-agent in the /feature workflow.

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 /feature workflow. (Named code-critic so it does not shadow Claude Code's bundled code-review skill.)

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.

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 doc), and verifies the review gate. Re-run any time as a doctor — it reports what is missing or drifted. (Named init-workflow so it does not collide with Claude Code's built-in /init command, which generates a CLAUDE.md.)

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.

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.)

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 transcripts still exist (they are pruned after Claude Code's retention window, ~30 days by default). Requires python3.

Records the outcome half of a feature's workflow evaluation at the end of a /feature session: which steps ran or were skipped, cycle counts, what each critic caught and what was adopted, plus a short judgment section. Writes one fixed-schema file per feature branch to .workflow-log/ (gitignored), including the session IDs the companion /workflow-inspect skill needs to append the cost half later. Run manually, optionally, at the end of a feature session.