🛠️ Dev Kit — lifecycle-driven Agent Skill for structured development workflows. Brainstorm, plan, implement, debug, fix, test & adversarial code review. Java/Spring Boot + TypeScript/React/Vue rules included. Compatible with Claude Code, Cursor, Kiro, and 40+ agentic clients.
SaferSkills independently audited dev-kit (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Structured development workflows — from ideation to production, with adversarial review and root cause analysis at every stage.
brainstorm → plan → cook (implement) → test → code-review → ship
↕
debug ↔ fixWhen the user says something, route to the correct skill:
| User Intent | Skill | Reference |
|---|---|---|
| Brainstorm ideas, evaluate approaches | brainstorm | references/brainstorm/SKILL.md |
| Plan implementation, design architecture | plan | references/plan/SKILL.md |
| Implement feature, execute plan | cook | references/cook/SKILL.md |
| Fix bug, resolve error | fix | references/fix/SKILL.md |
| Debug issue, investigate root cause | debug | references/debug/SKILL.md |
| Run tests, check coverage | test | references/test/SKILL.md |
| Review code, audit PR | code-review | references/code-review/SKILL.md |
| Find files, explore codebase | scout | references/scout/SKILL.md |
Priority when ambiguous:
fix if user mentions a concrete error or failing testdebug if user mentions investigation, root cause, or "why"cook if user mentions implementing or building something newbrainstorm if user says "should we", "what if", or "how about"plan if user mentions architecture, roadmap, or phasesEvery skill MUST scan the codebase before:
Implementation and fixes are NOT done until verified side-effect-free:
Every code change gets 3-stage review:
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE. Run command → Read output → Confirm pass → Then claim result.
Structured ideation with scout-first, exact requirements gates, and trade-off analysis. Ends with design doc + handoff to /plan.
Implementation planning with research phase, codebase understanding, solution design, and phase-by-phase output. Creates actionable plans for /cook.
End-to-end feature implementation. Modes: --interactive (default), --fast, --auto, --parallel, --no-test, --tdd. Full pipeline: scout → research → plan → implement → test → review → finalize.
Bug fixing with intelligent routing. Modes: --auto (default), --review, --quick, --parallel. Pipeline: scout → diagnose → assess complexity → fix → verify+prevent → finalize.
Systematic debugging framework. Techniques: systematic debugging, root cause tracing, defense-in-depth, verification, investigation methodology, log/CI analysis, performance diagnostics, frontend verification.
Comprehensive testing. Supports: unit/integration/e2e (Jest/Vitest/pytest/Go/Rust/Flutter), UI testing via browser automation, coverage analysis, structured QA reports.
Adversarial review with input modes: #PR, commit hash, --pending, codebase, codebase parallel. Three-stage protocol + task-managed review pipelines for multi-file features.
Fast codebase scouting using parallel agents. Supports internal (Explore subagents) and external (Gemini/OpenCode) modes. Divides codebase into segments for maximum coverage.
Load the appropriate reference when working with a specific language/framework:
| Language | Reference | When to Load |
|---|---|---|
| Java (core) | references/languages/java/core-rules.md | Any Java code — bans, musts, style, error handling |
| Java (Spring Boot) | references/languages/java/spring-boot.md | Spring controllers, services, repos, config, exceptions |
| Java (Clean Arch) | references/languages/java/clean-architecture.md | Layer structure, dependency rules, anti-patterns |
| Java (Testing) | references/languages/java/testing.md | JUnit 5, Testcontainers, Mockito, JPA testing |
| TypeScript (core) | references/languages/typescript/core-rules.md | Any TS/frontend code — bans, type safety, a11y, security |
| TypeScript (React/Next.js) | references/languages/typescript/react-nextjs.md | React components, Zustand, TanStack Query, App Router |
| TypeScript (Vue/Nuxt) | references/languages/typescript/vue-nuxt.md | Vue 3 Composition API, Pinia, Nuxt patterns |
| TypeScript (API) | references/languages/typescript/api-patterns.md | Fetch wrapper, BFF, response validation, optimistic updates |
| TypeScript (Forms) | references/languages/typescript/forms.md | React Hook Form, VeeValidate, Zod schemas, Server Actions |
references/_shared/workflow-artifacts.md — Review artifact schema and validator contractLanguage/framework agnostic. Works with any:
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.