phpunit-unit-test-debating

Included with Lifetime

$97 forever

Internal sub-skill. Do not auto-activate. Use only when explicitly invoked by name by another skill or agent.

AI Agents

What this skill does

# PHPUnit Test Review Debate

Peer-to-peer debate of review findings within a single Agent Teams wave. You debate directly with co-reviewers via SendMessage, then produce your final stance.

## Input

Provided in spawn prompt by team-lead:

- `own_findings`: your findings from Wave 0 (reviewing skill output)
- `peer_findings`: findings from co-reviewers on shared files
- `co_reviewers`: list of co-reviewer names and shared files

## Phase 1: Prepare Positions

Load references/debate-rules.md.

For each file, compare own findings against peer findings:

1. **Shared findings** (both you and peer reported) — prepare endorsement
2. **Peer-only findings** (peer reported, you didn't) — prepare challenge with detection algorithm citation, OR concession
3. **Own-only findings** (you reported, peer didn't) — prepare justification with code evidence

For challenges: call `mcp__plugin_test-writing_test-rules__get_rules(ids={rule_id})` to load the detection algorithm. Apply it against the code. If the peer is right, prepare concession instead.

## Phase 2: Debate (max 2 rounds)

### Round 1

For each co-reviewer, send ONE message via `SendMessage(to: "{co_reviewer_name}")` covering all shared files. Use the debate message format from references/output-format.md:

- Endorsements for shared findings
- Challenges with detection algorithm citations
- Justifications for own-only findings with code evidence
- Concessions where peer evidence is stronger
- Cross-file references where applicable (first-hand only)

After sending, wait for co-reviewer responses.

### Round 2 (if needed)

If you received challenges from co-reviewers in round 1:

1. Evaluate each challenge against the detection algorithm
2. Concede where their evidence is stronger
3. Defend where your evidence holds, citing specific code

Send ONE response per co-reviewer. Then proceed to Phase 3.

If no challenges were received, or all challenges are conceded, skip round 2.

### Convergence

- After round 2: proceed to Phase 3
- After round 1 with no open challenges: proceed to Phase 3
- If co-reviewer does not respond: proceed to Phase 3 with available input
- Do NOT send more than 2 debate messages per co-reviewer

## Phase 3: Final Stance

Produce final stance per file using the format from references/output-format.md:

- All findings you still stand by (with enforce level, location, current, suggested)
- Withdrawn findings with reasons (citing the peer's argument that convinced you)
- Cross-file references used during debate

This is your output. Return it to the lead.

## Troubleshooting

### Co-Reviewer Unresponsive

If a co-reviewer does not respond to your round 1 message, produce final stance from your own analysis and whatever peer findings you received in the input. Do not block.

### MCP Tool Unavailability

If `mcp__plugin_test-writing_test-rules__get_rules` is unavailable, you cannot verify detection algorithms. Concede peer findings you cannot verify and note the limitation in your final stance.

Files: 3

Size: 6.9 KB

Complexity: 25/100

Category: AI Agents

Source: https://github.com/shopwarelabs/ai-coding-tools/tree/main/plugins/test-writing/skills/phpunit-unit-test-debating

Related in AI Agents

skill-development

Included

Comprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.

AI Agentsscripts

reprompter

Included

Transform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.

AI Agentsscripts

adaptive-compaction

Included

Adaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.

AI Agentsscripts

agent-skill-creator

Included

Create cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.

AI Agentsscripts

llm-wiki

Included

Use when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.

AI Agentsscripts

skill-master

Included

Agent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.

AI Agentsscripts