Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From test-writing
Defends PHPUnit unit test review findings against adversary challenges in team review defense round, evaluating consensus challenges, resurrections, new findings, and producing updated stance.
npx claudepluginhub shopwarelabs/ai-coding-tools --plugin test-writingHow this skill is triggered — by the user, by Claude, or both
Slash command
/test-writing:phpunit-unit-test-defendingThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Defend your findings against adversary challenges. Evaluate each challenge on its merits, then produce your defense stance.
Performs adversarial review of PHPUnit unit test consensus: independently scans tests/source code first, then challenges weak findings, resurrects withdrawn ones, and uncovers missed violations.
Calibrates VCSDD Adversary agent for phase 3 adversarial reviews with strict principles, severity classification, leniency traps, and finding routing to phases.
Adversarially reviews any artifact (design docs, code, PRs, docs) by dispatching fresh Devil's Advocate subagents iteratively until clean.
Share bugs, ideas, or general feedback.
Defend your findings against adversary challenges. Evaluate each challenge on its merits, then produce your defense stance.
Provided in spawn prompt by team-lead:
own_final_stance: your final stance from Wave 1 (debating skill output)adversary_challenges: challenges from the adversary for your assigned filesLoad defense-rules.md.
For each file, evaluate every adversary challenge:
For each challenge:
mcp__plugin_test-writing_test-rules__get_rules(ids={rule_id}) to load the detection algorithmFor each resurrection of a finding you withdrew in round 1:
For each adversary-introduced finding:
Note endorsed findings. No action required.
Produce defense stance per file using the format from output-format.md:
adversary_impact: defended or unchanged)adversary_impact: resurrected)adversary_impact: overturned)adversary_impact: introduced)This is your output. Return it to the lead.
If mcp__plugin_test-writing_test-rules__get_rules is unavailable, you cannot verify detection algorithms. Maintain your round 1 positions and note the limitation.