Agent Workflow Skills

Repo-local meta-skill for improving Xiaobai Skills over time. Use after significant project changes, user feedback, install failures, promotion experiments, or repeated workflow friction to update AGENTS.md, capture project-specific gotchas, or propose new repo-local skills. Do not use globally or after every small task.

| to restate the user's intent to align before working, then diagnose the root cause and reuse the domain's mature, established practices before improvising. Clear prompts pass through untouched.

Use this agent when reviewing code to ensure features are agent-native - that any action a user can take, an agent can also take, and anything a user can see, an agent can see. This enforces the principle that agents should have parity with users in capability and context. <example>Context: The user added a new feature to their application.\\nuser: \"I just implemented a new email filtering feature\"\\nassistant: \"I'll use the agent-native-reviewer to verify this feature is accessible to agents\"\\n<commentary>New features need agent-native review to ensure agents can also filter emails, not just humans through UI.</commentary></example><example>Context: The user created a new UI workflow.\\nuser: \"I added a multi-step wizard for creating reports\"\\nassistant: \"Let me check if this workflow is agent-native using the agent-native-reviewer\"\\n<commentary>UI workflows often miss agent accessibility - the reviewer checks for API/tool equivalents.</commentary></example>

Run comprehensive agent-native architecture review with scored principles

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.

Create or edit Claude Code skills with expert guidance on structure and best practices

Expert guidance for creating, writing, and refining Claude Code Skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best practices.

This skill should be used when working with DSPy.rb, a Ruby framework for building type-safe, composable LLM applications. Use this when implementing predictable AI features, creating LLM signatures and modules, configuring language model providers (OpenAI, Anthropic, Gemini, Ollama), building agent systems with tools, optimizing prompts, or testing LLM-powered functionality in Ruby applications.

Create a new custom slash command following conventions and best practices

Fix incorrect SKILL.md files when a skill has wrong instructions or outdated API references

Use when user asks to create, write, edit, or test a skill. Also use when documenting reusable techniques, patterns, or workflows for future Claude instances.

> 🛒 E-commerce & Retail skill suite derived from travisvn/awesome-claude-skills. Product catalogue optimisation, conversion rate, customer journey and retail analytics. Provides 10 specialised commands for ecommerce, retail, shopify workflows.

> 🛒 E-commerce & Retail skill suite derived from BehiSecc/awesome-claude-skills. Product catalogue optimisation, conversion rate, customer journey and retail analytics. Provides 10 specialised commands for ecommerce, retail, shopify workflows.

>- Creates, reviews, and improves lean implementation plans through orchestrated research, evidence-backed synthesis, and iterative independent review closure. Use this skill when the user asks to plan a feature or change, create an implementation handoff, or review or improve an unimplemented plan before coding. Do not use to implement a plan, audit completed implementation against a plan, or answer a small conceptual question that needs no implementation handoff.

>- Creates, rewrites, reviews, and evidence-backed improves Agent Skills that are concise, unambiguous, progressively disclosed, and agent-actionable. Use this skill when authoring or revising a SKILL.md, its routing description, references, assets, scripts, or reusable workflow guidance. Do not use for installing third-party skills or one-off preferences without reusable evidence.

>- Pi-specific launcher for bounded scout, research, and worker agents via the Pi RPC script adapter. Use this skill when on Pi, native `subagent_*` tools are inactive, and you need to launch, follow up, status, stop, or clean RPC children. Apply together with `use-subagents` policy (delegation, isolation, verify, cleanup). Do not use when a native subagent runtime should own the lane, for recursive delegation, ordinary background processes, or automatic Git/worktree management.

>- Portable playbook for bounded subagent delegation on any coding-agent harness. Use this skill whenever considering delegation, decomposition, parallel research, review or implementation, independent validation, or an explicit request to spawn or manage subagents. Works with the host's built-in subagent tools, extensions/plugins, or a safe agent CLI. Do not use for ordinary background shell, server, or process work.

Convert current chat session into a reusable skill. Use when user says "/chat-to-skill", "save this as skill", "create skill from chat", "turn this into a skill", or wants to preserve learnings from the conversation as long-term memory.

Analyze a user's pi coding-agent session history for recurring behavior, prompting habits, workflow loops, friction, and preferences. Use when the user asks to inspect or reflect on pi sessions, common behavior patterns, agent/user interaction style, prompting habits, or personal pi workflow quality.

Find agent skills and skill repositories on GitHub.

Complete T2A Protocol capsules when a tool returns t2a.handoff, points to task.json, needs output.json, or asks for validation.

>- Design and scaffold an autonomous "loop" around a coding agent for a recurring workflow. Use when the user wants to stop hand-prompting an agent and instead build a system that discovers work, delegates it to a maker, verifies the result with a separate checker, remembers progress on disk, and re-runs until a goal is met or it stops for an honest reason. Triggers on "build a loop", "loop engineering", "automate this agent workflow", "design an agentic loop", "/goal", "/loop", "Ralph loop", "maker/checker", "run this overnight", "verifier rubric", or "loop contract". Works with Claude Code, Codex, Cursor, and OpenCode.

Run design sprints, manage handoff, establish team rituals, documentation standards, and design QA processes. Covers the operational side of design — how teams organize work, collaborate with engineering, and ship quality.

>- Implement RLM-style (Recursive Language Model) orchestration for complex tasks. This skill should be used when facing large context requirements, multi-part tasks that would benefit from parallel execution, or when context rot is a concern. Automatically decomposes tasks, spawns parallel subagents, aggregates results,

Interview the founder once and write a docs/gtm-cofounder/founder-brief.md that every other skill reads first, so the advice is about their real business, not a textbook. Use this before anything else, or whenever the agent lacks context on the founder's product, ICP, market, or stage, or is giving generic GTM advice.

Use when executing implementation plans with independent tasks - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates. Supports orchestrator, peer-to-peer, and pipeline coordination modes.

当用户明确要求"优化 prompt"、"改进提示词"、"润色指令"或"将简陋 prompt 转换为最佳实践版本"时使用。基于 OpenAI 和 Anthropic 官方最佳实践，对用户提供的简陋 prompt 进行结构化优化，输出符合社区标准的高质量版本。

当 Bensz 系列 skills 在真实用户环境中因 skill 设计缺陷而出现 bug，或用户明确说“我想 report bensz skills bugs”“帮我公开上报 bensz skills 的 bug”时使用。该 skill 负责把 bug 规范化记录到 `~/.bensz-skills/bugs/`，并在用户明确要求公开报告时通过本地 `gh` 轻量上传到 `huangwb8/bensz-bugs`，全程严禁修改用户本地 Claude Code/Codex 中已安装 skills 的源代码。

当用户明确要求“压缩/瘦身/精简某个 Agent Skill 的 Markdown 文档”“在不改变功能前提下降低 skill 上下文开销”时使用。先理解目标 skill 的真实能力与安全边界，再在忽略 `tests/`、`plans/` 以及目标 skill 的 `README.md`、`CHANGELOG.md` 的前提下，压缩 `SKILL.md`、`references/*.md` 等工作型 Markdown，并把中间产物隔离到 `.bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/compact-bensz-skills/`。⚠️ 不适用：用户主要想新增功能、修复脚本逻辑、批量改代码、或只想压缩非 skill 文档。

当用户明确要求"并行执行同一条 Vibe Coding 指令 / 多个独立 agent 或 subagent 同时审查、想方案、优化、对比多条路线 / 多线程独立尝试"时使用。默认使用智能模式：由宿主原生 subagent 独立分析并由主 agent 汇总；智能模式和代码模式必须使用同一套 `.bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/parallel-vibe/{yyyy-mm-dd-hh-mm}/` 运行目录、`@main/plan.json`、thread `workspace/`、`RESULT.md` 与 `runner.log` 契约，区别只在底层执行机制；当用户要求脚本 runner、plan-file、resume、跨 CLI runner、退出码或无可用 subagent 时，切换到代码模式并调用 `scripts/parallel_vibe.py`。⚠️ 不适用：普通 shell 并发、单元测试并发、下载任务、要求强安全隔离或处理高度敏感数据。

当需要把本仓库 pipelines/skills 下的所有 skills 安装到系统级（默认同时安装到 Codex: ~/.codex/skills 和 Claude Code: ~/.claude/skills），以便在任意项目/对话中可被发现与调用时使用。使用 MD5 哈希进行版本控制，仅安装有更新的 skills；支持 --skill 指定单个或少量技能安装/更新、强制覆盖安装、指定单一目标安装和远程安装模式（--remote --check/--auto）。

当用户明确要求"生成技能 README"、"编写用户指南"或"更新技能文档"时使用。为 Agent Skills 编写符合最佳实践的 README.md 用户使用指南。自动分析技能结构（SKILL.md、config.yaml、scripts/），按模板生成小白友好的文档。

Phase 1 ORCHESTRATOR of a movie/comic — turn a fuzzy story idea into the Authored Source of Truth (a schema-valid comic.json + its locked asset library) by driving the detailed author skills in order (intent → style → outline → storyboard → assets → blueprints → prompts → comic.json), each gated by comic-cross-layer-gate, so comic-director (Phase 2/3) can bake + cross-model-verify it. You don't hand-write comic.json; this is the workflow your agent runs to author it. Use when the user says "做个漫画/电影", "from this idea make a comic", "author the comic.json", "run the comic pipeline".

Phase 2/3 of a movie — bake + cross-model-verify a movie from an authored comic.json. Per frame: render the content-SVG blueprint, bake via the agent mcp__codex__codex sidecar, gate with a 3-reviewer cross-model panel (narrative [currently the codex CLI] ‖ Gemini visual ‖ Codex visual, deterministic fuse), keep/retry/assemble, write the wiki trace, project to the viewer. The movie-side twin of method-figure's render half. (Author the comic.json first with the comic-author skill.)

Phase-1 step of comic-author — the DETERMINISTIC compiler (搬运工原則) that turns ONE gate-approved panel_spec + its status:locked blueprint into the EXACT fixed-section bake string for the spiral engine via the shipped scripts/build_prompt.py (+ the canonical scripts/_validate.py vetoes). No Codex call in the happy path; it only emits, the engine bakes. Composes style_prefix + condition_string, injects the active failure_mode repair note on retry, and hard-REJECTS banned vocab (camera/lens/lighting/quality padding). Routes html_bubbles[] to the JSON viewer overlay, NEVER into the bake string (no baked bubbles unless the panel is text_mode:baked). Refuses unless the upstream blueprint is status==locked (the cross-layer gate's hand-off token) and every ref is a REAL locked asset path. Use when a panel_spec is locked and you need its prompt_bundle, just before comic-director's panel_gate.

End-to-end Pipeline A in ONE slash-command — turn a fuzzy story idea into a cross-model-audited, image-based movie + a clickable viewer. Chains comic-author (Phase 1 — intent→style→outline draft→provisional storyboard→assets→final locks→blueprints→prompts→comic.json) → the zero-credit p0_proof spending gate (agent fan-out + run_p0_proof.py mints the digest-bound certificate) → comic-director (Phase 2/3 — the agent-sidecar bake spiral, page by page → HTML viewer). Two hard HUMAN gates (intent + outline) pause for approval; everything else is agent-driven + cross-model gated. This is the slash-command entry, like ARIS's /research-pipeline — an AGENT workflow, NOT a shell binary. Use when the user says "/movie-pipeline '…'", "做个电影/漫画 end-to-end", "from this idea make the whole movie", "long-horizon image-based movie generation".

Create, tighten, or review runnable /goal contracts for coding agents such as Codex, Claude Code, Cursor, and similar agent tools. Use when the user asks to write, make, generate, improve, productize, or critique a goal prompt, rescue contract, GOAL.md-style task, done-when contract, verification prompt, stop-rule prompt, or when they want to convert a vague engineering request, issue, PR, CI failure, bug report, plan, or backlog item into one measurable coding-agent task. Prefer source-backed goal patterns when available, use seed patterns only as raw reusable shapes, and output the goal contract or review rather than implementing the underlying code task.

Use when executing implementation plans with independent tasks in the current session

> ☁️ DevOps & Cloud Infrastructure skill suite derived from VoltAgent/awesome-agent-skills. CI/CD pipelines, container orchestration, IaC, monitoring and incident response. Provides 10 specialised commands for devops, cloud, docker workflows.

>- Opus when Fable is unavailable) dispatching a mixed fleet of workers, Claude Opus agents for UI/UX and design judgment, OpenAI Codex CLI workers for implementation and everything else. Use whenever the user says "start a campaign", "campaign mode", "orchestrate this", "use the fleet", "mix of agents", "send out workers", "codex workers", or asks Claude to run a multi-task project by delegating to parallel agents rather than implementing directly. Also use when resuming work in a repo whose CLAUDE.md points at a campaign-hq folder.

Audit recent agent transcripts (Claude Code and Codex) to learn how a tool, system, or skill is actually being used in the wild. Surfaces failure modes, friction, success patterns, and concrete improvement candidates from real session data. Use this when you want to improve a developer-facing system that agents interact with regularly.

Generates optimized prompts for any AI tool. Use when writing, fixing, improving, or adapting a prompt for LLM, Cursor, Midjourney, image AI, video AI, coding agents, or any other AI tool.

> Descripción clara y completa de qué hace esta skill y cuándo debe activarse. Incluye los casos de uso principales y el contexto en el que Claude debe usar esta skill. Sé específico y detallado.

Authors and structures professional-grade agent skills following the agentskills.io spec. Use when creating new skill directories, drafting procedural instructions, or optimizing metadata for discoverability. Don't use for general documentation, non-agentic library code, or README files.

Implements and debugs browser WebMCP integrations in JavaScript or TypeScript web apps. Use when exposing imperative tools through document.modelContext (with a navigator.modelContext fallback), annotating HTML forms for declarative tools, handling agent-invoked form flows, or validating WebMCP behavior in the current Chrome preview. Don't use for server-side MCP servers, REST tool backends, or non-browser providers.

| PRD를 입력으로 화면정의서 5종(IA, User Flow, Screen Spec, Wireframe HTML, Dev Handoff)을 순차 생성한다. Wireframe은 흑백 + 의미색만 사용하는 lo-fi 산출물(스타일/브랜드는 별도 단계). frontend-developer 자동 리뷰 지원. /screen-spec 명령어에서 호출되며, /prd → /implement 사이의 선택적 게이트로 동작한다.

How to use reseed to manage agent skills in a project. Use when the user mentions reseed, agent skills, SKILL.md, .agents/skills/, or .claude/skills/, or wants to install, add, remove, sync, or list skills.

Expert skill for integrating cloud AI APIs (Claude, GPT-4, Gemini). Covers secure API key management, prompt injection prevention, rate limiting, cost optimization, and protection against data exfiltration attacks.