Battle Test
Run a fail-closed end-to-end project hardening cycle: static audit, exhaustive real-browser validation, semantic screenshot review, multi-role/security/visual-regression probes, isolated remediation, and re-verification. Use when the user asks to battle-test or prove production readiness. Default is the full cycle; --quick runs a clearly weaker smoke/readiness check and can never emit a battle-tested verdict. Main integration requires --push-main; deployment is never automatic. --ux curates only UX/UI and ends with its own verdict (UX SCOPE VERIFIED or UX SCOPE FAILED), never battle-tested.
Install
npx skills add wolverin0/claude-skills --skill battle-testgit clone --depth 1 https://github.com/wolverin0/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/skills/battle-test ~/.claude/skills/battle-testPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Battle Test `/battle-test [project-path-or-name]` runs the full quality loop end-to-end and produces one report: **diagnose → runtime-verify → harden → re-verify**. It does not reimplement those capabilities — it conducts four existing skills (`audit-orchestrator`, `validation`, `visual-route-sweep`, `quality-loop`; `--quick` adds `vibe-to-prod`) and gates between them. ``` /battle-test # current project /battle-test ../crm # a specific project path /battle-test --resume # continue a paused run /battle-test --audit-only # stop after diagnose (no fixes) /battle-test --quick # vibe-to-prod + validation smoke; no "battle-tested" verdict /battle-test --push-main # explicitly authorize integration after all gates pass /battle-test --ux # curate only UX/UI: own verdict, no integration (combine only with --resume) ``` ## What it conducts (each is a separately-proven skill) | Stage | Skill | Produces / signal to read | | --- | --- | --- | | 1. Diagnose | `audit-orchestrator` (the `/audit` pipeline) | `<repo>/audit-report.md` + `AUDIT VERDICT` block + `[AUDIT COMPLETE: ...]` token |
Details
- Skill name
battle-test- Repository
- wolverin0/claude-skills
- Path
skills/battle-test/SKILL.md- Repo updated
- 17 November 2026
FAQ
What does the Battle Test skill do?
Run a fail-closed end-to-end project hardening cycle: static audit, exhaustive real-browser validation, semantic screenshot review, multi-role/security/visual-regression probes, isolated remediation, and re-verification. Use when the user asks to battle-test or prove production readiness. Default is the full cycle; --quick runs a clearly weaker smoke/readiness check and can never emit a battle-tested verdict. Main integration requires --push-main; deployment is never automatic. --ux curates only UX/UI and ends with its own verdict (UX SCOPE VERIFIED or UX SCOPE FAILED), never battle-tested.
How do I install the Battle Test skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add wolverin0/claude-skills --skill battle-test. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Battle Test popular?
It lives in wolverin0/claude-skills, which has 41 GitHub stars and 1 forks.
Related skills
UI UX Pro Max
41wolverin0/claude-skills
UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, and check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, and mobile app. Elements: button, modal, navbar, sidebar, card, table, form, and chart. Styles: glassmorphism,
Audit Blind Spots
41wolverin0/claude-skills
Walk the B1-B19 AI-to-AI blind-spot catalog systematically. Use during the audit pipeline AFTER hard-stops and Tambon hunt and BEFORE the 13 domain audits. Output: PRESENT / NOT PRESENT for each B-class with evidence. Findings flow into the appropriate domains.
Audit Decisions
41wolverin0/claude-skills
Standardize remediation decisions, baseline-policy entries, and legal-review banners for accepted, deferred, or policy-blocked audit findings.
Forage Plants
45pjt222/agent-almanac
Identify and safely gather edible and useful wild plants. Covers safety rules and deadly plant recognition, habitat reading, multi-feature identification methodology, the universal edibility test, sustainable harvesting practices, preparation methods, reaction monitoring, and building knowledge with beginner-friendly universal species. Use when supplementing food supply in a wilderness or survival setting, needing medicinal or utility plants, identifying plants around camp for safety, or in long-term scenarios where foraging extends available rations.
Autoqa
41wolverin0/claude-skills
Self-QA a repo's running application end-to-end — discover how it runs, build a feature×modality test plan, execute it against a live instance, and produce a witnessed pass/fail report. Use when the user says "autoqa", "QA this repo/branch", "verify every feature works", "release readiness check", "test this like a QA engineer would", or another skill needs an automated QA pass before sign-off.
Generate Puzzle
45pjt222/agent-almanac
Generate jigsaw puzzles via generate_puzzle() or geom_puzzle_*() with parameter validation against inst/config.yml. Supports rectangular, hexagonal, concentric, voronoi, and snic puzzle types with configurable grid, size, seed, offset, and layout parameters. Use when creating puzzle SVG files for a specific type and configuration, testing generation with different parameters, generating sample output for documentation or demos, or creating ggplot2 puzzle visualizations.
Browse the most popular Claude skills, all testing & qa skills, or write your own with the skills generator.