adversarial testing skills

0xSanei/darwinia

Skill Claude CodeCodex

Evolve trading strategies through genetic algorithms and adversarial combat. No API keys, no cloud — pure Python + numpy.

0xSanei/darwinia

Skill Claude CodeCodex

Evolve trading strategies through genetic algorithms and adversarial combat. Run Darwinian selection on BTC data to discover battle-tested strategies. No API keys, no cloud.

smshahbaj/crucible

Skill Claude CodeCodex

Pressure-test important decisions, plans, proposals, strategies, architectures, and recommendations before acting. Use when trade-offs, uncertainty, meaningful downside, or an important second opinion could change the outcome. Stay lightweight for routine or trivial work.

alejandrosaenz117/bonfires-marketplace

Skill Claude CodeCodex

This skill should be used when the user asks for "an adversarial review", "security review", "devil's advocate", "what could go wrong", "find the vulnerability", "threat analysis", "penetration test this", or "challenge this design". Use this skill when the user wants to identify security threats and architectural…

alejandrosaenz117/bonfires-marketplace

Skill Claude CodeCodex

Prioritize any workload using the Eisenhower Matrix. Use this skill whenever a user provides a brain dump of work—Jira summaries, meeting notes, sprint dumps, task lists, or prose descriptions of their workload. This skill categorizes tasks into four quadrants: Q1 (Urgent+Important: do now), Q2 (Important+NotUrgent…

alejandrosaenz117/bonfires-marketplace

Skill Claude CodeCodex

This skill should be triggered when the user asks about dependency security, vulnerability scanning, or package safety. Examples: "check my dependencies for vulnerabilities", "scan my packages", "are my dependencies safe", "dependency audit", "check for CVEs", "security audit", "vulnerable packages", "scan…

CodedRichy/food-chain-ideation

Skill Claude CodeCodex

Adversarial architecture stress-tester. Selects attacker agents from a code-specific behavioral DNA library matched to the technical decision. Each attacks under strict role-lock. Weakest eliminated, survivor absorbs and evolves. Tests architecture decisions before a line of code is written. Works in Claude.ai, Claude…

CodedRichy/food-chain-ideation

Skill Claude CodeCodex

10-minute pre-ship stress-test. Run this before you ship, not instead of shipping. Dynamically selects animal agents from a behavioral DNA library matched to the specific problem, each attacking under strict role-lock with zero shared context. Weakest eliminated each round, survivor absorbs the insight and evolves…

CodedRichy/food-chain-ideation

Skill Claude CodeCodex

Investor pitch stress-tester. Spawns adversarial agents from a pitch-specific behavioral DNA library. Each attacks the pitch narrative, financial model, or due diligence surface under strict role-lock. Elimination rounds harden the pitch. Works in Claude.ai, Claude Code, Cursor, Windsurf, Copilot with no dependencies.

tasumermaf/the-adversary

Skill Claude CodeCodex

Run The Adversary v2 — the three-stage adversarial audit (CHECK deterministic, FIND independent lenses, VERIFY reproduce-or-demote) over an artifact at a pinned commit. Use when the user says "run the adversary", "adversarial audit", "audit this paper/repo", "release gate", or "gate this before I ship". Picks the…

yogsoth-ai/stress-test

Skill Claude CodeCodex

Strategy: Lewis Possible Worlds — find the minimal change to reality that would flip the conclusion, measuring how close the nearest world where the conclusion fails.

yogsoth-ai/stress-test

Skill Claude CodeCodex

Strategy: Legal adversarial structure — prosecution presents case, defense responds, evidence is cross-examined, judge delivers verdict. Emphasizes evidence quality and procedural rigor.

yogsoth-ai/stress-test

Skill Claude CodeCodex

Strategy: Research design-level FMEA — function analysis, failure mode identification, severity/occurrence/detection scoring per AIAG-VDA 2019.

sanjoy1234/gauntlex

Skill Claude CodeCodex

Full GAUNTLEX environment health check — model reachable, ChromaDB writable, AVF fixtures pass, no unexpected outbound network (air-gap verification). Use before first run or when debugging failures.

sanjoy1234/gauntlex

Skill Claude CodeCodex

Run a full GAUNTLEX adversarial session on a spec file or GitHub issue URL. Invokes the Gauntlex (Builder + Breaker concurrent) and outputs an Adversarial Resilience Score (ARS) with a Resilience Report.

sanjoy1234/gauntlex

Skill Claude CodeCodex

Dry-run GAUNTLEX validation — parses the spec, resolves policy playbooks, checks model availability, and runs the AVF golden fixture gate. No attacks are fired. Exit 1 if any check fails.

alextverdyy/tournament-judge

Skill Claude CodeCodex

Runs a domain-neutral, evidence-based tournament in which independent candidates are reviewed, anonymized, and scored by a blind judge against a rubric fixed before judging. Use when comparing competing plans, designs, implementations, documents, tools, vendors, strategies, or other substantial options; when the user…