japboy
- 13 skills
- 0 followers
- 6 hours ago last updated
- ▌ Agent Memory · japboy bundleBuild and use Git-repository-shared agent memory across branches and worktrees. Use when a task needs session memory, work logs, handoff recall, SQLite-backed agent logs, artifact-aware repository memory, or idempotent memory setup across agent sessions.
- ▌ Git Commit Creation · japboy bundleCreate authorized, atomic Git commits with repository-compliant messages and current-agent attribution. Use only when the user explicitly asks to create a commit or to commit already-scoped changes. Do not use for requests limited to staging, status inspection, commit planning, or drafting a message.
- ▌ Agent Skill Authoring · japboy bundleCreate, update, validate, and review Agent Skills for Codex and Claude Code. Use when the user asks to "create a skill", "make a new skill", "define a skill", "write SKILL.md", "improve a skill description", "set up skill directories", "add Codex openai.yaml metadata", "validate skill structure", apply SkillOpt-style evaluation, or distinguish standard Agent Skills requirements from Codex- or Claude Code-specific practices.
- ▌ Japanese Naturalization · japboy bundleNaturalize the current or explicitly referenced assistant output into context-appropriate Japanese while preserving meaning. Use when the user asks to rewrite an existing assistant response so it sounds natural, removes AI-like Japanese or translationese, or fits a different register. For standalone evidence-backed term selection, use term-translation-research.
- ▌ Term Translation Research · japboy bundleResearch evidence-backed translations and established terms across domain-specific, industry, and general usage. Use when selecting English/Japanese terminology, validating standard translations, resolving product wording collisions, or proposing audience-specific term usage with citations.
- ▌ Xstate Architecture Review · japboy bundleEvaluate and apply XState architectural patterns and best practices. Use when the user asks to "review XState implementation", "evaluate state machine architecture", "check XState conventions", "audit actor model design", "review state chart structure", or mentions XState architectural patterns and best practices.
- ▌ Web Design Standards Review · japboy bundleEvaluate and apply web UI design and implementation principles using W3C/WHATWG standards and authoritative guidance from MDN, web.dev, and WAI. Use when defining or reviewing responsive layout, CSS capability detection, progressive enhancement, accessibility, internationalization, semantics, or performance-oriented UX; do not use for purely subjective visual styling without a standards or compatibility question.
- ▌ Github Issue Plan Refinement · japboy bundleIteratively refine a GitHub issue body that holds an execution plan by running one or more external review agents (Codex CLI or Claude Code CLI) against it, classifying the feedback by severity, applying deterministic fixes automatically, surfacing ambiguous choices to the user, and updating the issue body via `gh issue edit`. Each batch consumes `concurrency` consecutive round numbers; about 30% of the workers in a batch use a dissenting reviewer for model diversity. Each batch uses one explicit low, medium, or high reasoning-effort value. Use when the user asks to "iterate on issue #NNN", "refine the plan in #NNN", "run a review round on #NNN", "run N parallel reviews on #NNN", "loop reviewer feedback on #NNN", or wants to repeat reviewer rounds against a GitHub issue until no blockers remain.
- ▌ Github Pull Request Creation · japboy bundleCreate GitHub pull requests or draft their titles and descriptions from the final diff, change rationale, and verification evidence. Use when asked to open a PR, prepare a PR description, or rewrite an existing PR description. Do not use for commit-only tasks, code reviews, or issue plan refinement.
- ▌ Frontend Test Value Assessment · japboy bundleEvaluate whether frontend implementation tests deliver meaningful defect-prevention value using the Testing Trophy as the primary decision model. Use when asked to assess frontend test strategy, static vs unit vs integration vs end-to-end layer placement, mock-heavy suites, browser/device realism, accessibility semantics, visual regression value, existing mutation reports, or flaky test risk.
- ▌ Handoff Context Summarization · japboy bundleSummarize current conversation context using Model-First-Reasoning (MFR) methodology for seamless handoff to subsequent agents. Use when ending a session, switching agents, or when the user asks to "summarize context", "save session state", "prepare handoff", or "document current progress".
- ▌ Design System Reverse Engineering · japboy bundleReverse-engineers existing implementations, design files, and documentation into a reusable design system while preserving Adobe Spectrum's Principles/Foundation/Content structure. Use when users ask to derive design rules from legacy projects, normalize heterogeneous inputs, and produce evidence-based design system documentation.
- ▌ Architecture Pattern Application · japboy bundleApply documented architecture patterns to design and review decisions. Use for monorepo or workspace directory layout, package placement and topology, or route-state product analytics, URL-state contracts, measurement manifests, and warehouse semantic models. Select only matching catalogue patterns; unrelated architecture and build-tool configuration are outside this skill.