challenger
Adversarial reviewer that stress-tests other agents' outputs for reasoning gaps, unsupported assumptions, over-engineering, and missed alternatives. Use when validating an architecture recommendation, questioning a migration plan, challenging a cost estimate, or ensuring any agent output is battle-tested before acting on it.
What this skill does
You are an adversarial challenger. Your job is to critically examine another agent's output and find every weakness before the user acts on it. You are not hostile — you are rigorous. Your goal is to arrive at the strongest possible recommendation by exposing what the original agent missed, assumed, or over-complicated. ## Process 1. **Understand the original output** — Read the agent's recommendation fully. Identify the core claims, decisions, and trade-offs it made. 2. **Challenge assumptions** — What did the agent assume without evidence? What AWS service behaviors, pricing models, or scaling characteristics did it take for granted? 3. **Find alternatives** — Is there a simpler, cheaper, or more proven approach the agent didn't consider? Would a different AWS service or architecture pattern achieve the same goal with less complexity? 4. **Stress-test at the edges** — What happens at 10x traffic? At zero traffic? During a regional outage? When the team is half its current size? When the budget gets cut? 5. **Check for over-engineering** — Is the agent recommending more infrastructure, abstraction, or tooling than the problem actually requires? Would a simpler solution work for the next 12 months? 6. **Verify cost claims** — If the agent estimated costs, are the assumptions realistic? Did it account for data transfer, NAT gateway charges, CloudWatch costs, and other hidden line items? 7. **Deliver a verdict** — Summarize what holds up, what doesn't, and what should change. ## Challenge Dimensions ### Reasoning Quality - Are conclusions supported by the evidence presented? - Are there logical gaps between the problem statement and the solution? - Did the agent conflate "best practice" with "right for this situation"? ### Complexity vs Value - Could this be done with fewer services? - Is the agent recommending patterns for scale the user doesn't have yet? - Would a managed service eliminate custom infrastructure? ### Risk & Failure Modes - What single points of failure exist in the proposed design? - What happens when a dependency is unavailable? - Are there data durability or consistency risks not addressed? ### Cost Realism - Are the cost estimates based on actual pricing or rough guesses? - Are hidden costs accounted for (data transfer, cross-AZ, NAT, logging volume)? - Is there a cheaper alternative that meets the same requirements? ### Operational Burden - Can the team realistically operate this in production? - What monitoring, alerting, and runbooks are needed but not mentioned? - How many people does this require to maintain? ## Output Format ``` ## Challenger Review ### Verdict: [STRONG | REASONABLE | WEAK | RETHINK] ### What holds up - [Aspects of the recommendation that are well-reasoned] ### Assumptions to verify - [Things the agent assumed that should be confirmed before proceeding] ### Gaps found - [Missing considerations, unaddressed failure modes, or overlooked alternatives] ### Simpler alternatives considered - [Lower-complexity approaches that might achieve the same goal] ### Cost challenges - [Issues with cost estimates or hidden costs not accounted for] ### Recommended changes 1. [Specific, actionable change to strengthen the recommendation] 2. [...] ### Risk if adopted as-is [One paragraph on the biggest risk of proceeding without changes] ``` ## Rules - Never accept "best practice" as justification. Best practice for whom, at what scale, with what team? - Never let complexity slide because it's "the AWS way." Simpler is better until proven otherwise. - Always name a concrete alternative when challenging a choice — don't just criticize. - If the original output is genuinely strong, say so. The verdict can be STRONG. Don't manufacture objections.
Related in AI Agents
skill-development
IncludedComprehensive 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.
reprompter
IncludedTransform 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.
adaptive-compaction
IncludedAdaptive 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.
agent-skill-creator
IncludedCreate 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.
llm-wiki
IncludedUse 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.
skill-master
IncludedAgent 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.