Adversarial Test — Testing skill for Claude Code
Post-build adversarial review — a fresh agent stress-tests recent changes for bugs, regressions, conflicts, and missed edge cases.
How to install Adversarial Test
Installs to ~/.claude/skills/tomevault-io-companyos-adversarial-test/SKILL.md
mkdir -p ~/.claude/skills/tomevault-io-companyos-adversarial-test && curl -fsSL https://raw.githubusercontent.com/tomevault-io/companyos/HEAD/skills/adversarial-test.md -o ~/.claude/skills/tomevault-io-companyos-adversarial-test/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Adversarial Test does
name: adversarial-test description: Post-build adversarial review — a fresh agent stress-tests recent changes for bugs, regressions, conflicts, and missed edge cases. Different from pre-ship-adversary — that is self-attack before commit; this is third-party attack after build. Run after any non-trivial work where the cost of a missed bug is higher than the cost of the review. tier: universal
Adversarial build review
You are an adversarial reviewer. Your job is to find problems with t
Alternatives in Testing
- Adversarial Spec — A Claude Code plugin that iteratively refines product specifications by debating between multiple LLMs until a 514 ★
- PR Visual Diff — Post before/after stills + GIFs on a visual PR, captured headlessly with Playwright + ffmpeg 324 ★
- Integration Test — Test elixir plugin post-edit hooks by walking through fixture projects in test/integration/fixtures/ 174 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Prompt Test
Test LLM prompts against sample inputs. Shows outputs, checks for regressions when prompts change, and compare
Cfn Spec
SPARC Specification phase. Make testable acceptance criteria, edge cases, pre/post conditions, invariants BEFO
Scenario Generator Arken
Generate the Arken QA release scenarios document. Reads all stories and bugs in artifacts/, then creates artif
Pre Commit Review
Independent QA review of a working-tree diff before commit. Spawns a read-only reviewer agent to find correctn
Bug Record
Record a bug Aryan found during manual testing, with its screenshots, in docs/bugs.md and docs/screenshots/man
Plan Refine
Autonomously stress-test and harden a plan through 6 adversarial perspectives
Related Agents
Edge Case Adversary
Independently brainstorm the edge cases a builder likely MISSED for a given deliverable, countering the "bound
Reviewer Adversarial
Adversarial code review of a diff or branch by a DIFFERENT, stronger model than the one that wrote it. One tho
Rust Perf Engineer
Reviews diffs touching poly's per-file runner / discovery / cache / engine paths for hot-path regressions — ne