By TheStack-ai
Defend AI coding agents against cognitive biases like hallucination, anchoring, and optimism by deploying 6 skills: clarify ambiguous tasks with targeted questions, pre-mortem project risks, generate probability-weighted options, cross-verify deep research, conduct adversarial code reviews, and expose auditable reasoning traces.
Prevents premature execution on ambiguous requests. Analyzes request clarity using 5W1H decomposition, surfaces hidden assumptions, and generates structured clarifying questions before work begins. Use at the start of any non-trivial task, or when a request could be interpreted multiple ways. Triggers on "뭘 원하는건지", "요구사항 정리", "clarify", "what exactly", "scope", "requirements", "정확히 뭘", "before we start".
Prospective failure analysis using Gary Klein's pre-mortem technique. Assumes complete failure, works backward to identify risks, leading indicators, and circuit breakers. Counters optimism bias by forcing systematic exploration of failure modes before they materialize. Use for project plans, architecture decisions, technology adoption, business strategy, or feature launches. Triggers on "리스크", "위험", "실패하면", "swing-mortem", "뭐가 잘못될 수 있어", "risk", "what could go wrong", "걱정되는 점", "failure modes", "리스크 분석", "위험 분석".
Generate probability-weighted alternative options that challenge default thinking. Forces unconventional alternatives and exposes hidden assumptions behind the "obvious" choice. For decision-point analysis, NOT full design exploration. Triggers on "대안", "alternatives", "옵션 뽑아", "options", "어떤 방법이", "아이디어", "다른 방법", "선택지".
Deep research with cross-verification and source tiering. Use when investigating technologies, comparing tools, fact-checking claims, evaluating architectures, or any task requiring verified information. Triggers on "조사해줘", "리서치", "research", "investigate", "fact-check", "비교 분석", "검증해줘".
Devil's Advocate stress-testing for code, architecture, PRs, and decisions. Surfaces hidden flaws through structured adversarial analysis with metacognitive depth. Use for high-stakes review, stress-testing choices, or when the user wants problems found deliberately. NOT for routine code review. Triggers on "스트레스 테스트", "stress test", "devil's advocate", "반론", "이거 괜찮아", "문제 없을까", "깊은 리뷰", "critical review", "adversarial".
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Your AI is not swinging at all.
It picks the safe default, agrees when it should push back, cites no sources, hides its reasoning, and assumes everything will work. Six cognitive failures. Six firewalls. Make it swing.
npx skills add thestack-ai/swing-skills --all
Built for Claude Code | Compatible with AI agents via Agent Skills open standard Created by @thestack_ai
You: Is SQLite viable for an app with 1000 concurrent users?
AI: No, SQLite is not suitable for high-concurrency applications. Use PostgreSQL or MySQL instead for production workloads.
swing-researchYou: /swing-research Is SQLite viable for an app with 1000 concurrent users?
AI: Yes, with caveats. 1000 concurrent users ≠ 1000 concurrent writes. Typical web apps generate ~30 concurrent write transactions at this scale. SQLite handles ~120 write transactions/sec in WAL mode (verified: sqlite.org benchmarks + Expensify production case study serving 10M+ users on SQLite). The real constraint is write contention above ~100 concurrent writers, not user count.
Sources: 🏛️ sqlite.org WAL documentation, 🛡️ Expensify engineering blog (2024), ⚠️ HN discussion (corroborated)
The baseline gave a wrong answer confidently. The skill forced source verification and reached the opposite — correct — conclusion.
You: Review this JWT auth module
AI: The code looks well-structured. Consider adding more comments and using TypeScript for better type safety. Variable naming could be improved in some places.
swing-reviewYou: /swing-review Review this JWT auth module
AI: Steel-man: JWT-based stateless auth was chosen for horizontal scaling. The 15-min access + 7-day refresh split balances security and UX.
🔴 Critical: No refresh token rotation. A stolen token grants persistent 7-day access with no detection. Fix: implement token family chain rotation.
🟠 Major: Rate limiting uses in-memory Map(). Resets on restart, bypassed in multi-instance deploys. Fix: move to Redis with TTL.
Verdict: PASS WITH CONDITIONS — must fix token rotation before deploy.
The baseline found nothing. The skill found a Critical security vulnerability.
npx claudepluginhub thestack-ai/swing-skillsMindful AI coding framework — discipline over cleverness. Skill + 21 slash commands + 8 specialist agents + 5 runtime hooks + 15 default checklists + Master Orchestrator + Gravity hub. Works on any model tier (Opus/Sonnet/Haiku). Integrates Claude Design for visual work.
Automatic code review, adversarial review, and rescue via Codex.
Personal Claude Code + Codex dev stack: security hooks, AI-first code conventions, /security-review, /repo-map, /stack-check, portable statusline. Designed to complement other skills-based plugins, not replace them.
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code.
Consult external AIs (Gemini 2.5 Pro, OpenAI Codex, Claude) for second opinions. Use for debugging failures, architectural decisions, security validation, or need fresh perspective with synthesis.
Verification-first engineering toolkit for Claude Code. 15 skills across a 5-phase spine (Investigate → Design → Implement → Verify → Ship), 8 specialist agents, an interactive setup wizard. Every skill has rationalizations + evidence requirements. Built for senior ICs and tech leads.