Agent Workflow Claude Skills

Track parallel work sessions and prevent confusion across multiple Claude Code instances. Every major step ends with a status line. Every question re-states project, branch, and task.

Market prediction skill using Kronos. Use when user needs finance market time-series forecasting or news-aware finance market adjustments.

Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.

Codex-local role pack for dialectic multi-agent reviews, designed to be compatible with the local vibe skill.

Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.

⚠️ CRITICAL USER EXPERIENCE-BASED SKILL - ALWAYS CONSULT BEFORE DATA PREPROCESSING ⚠️ Prevents catastrophic errors (88.9% error rate in V1.0 case study) through multi-level feature analysis, data leakage detection, and semantic validation. MANDATORY for: data preprocessing, feature engineering, standardization, normalization, interpolation, missing value handling, feature selection, or ANY data transformation task. Covers grouped time-series, cross-sectional, panel data. Detects: time travel leakage, causal inversion, ID misuse, semantic-numeric fallacies, distribution blindness. User's hard-won lessons from real project failures.

CLI-first web scraping & content extraction with optional MCP server. Use when you have target URLs and need clean, selector-based outputs (html/md/txt).

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 Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Use when serving NeMo Agent Toolkit workflows, exposing workflows through FastAPI, configuring MCP clients or servers, or troubleshooting transport and server setup.

Use when installing or configuring NVIDIA NeMo Agent Toolkit, verifying the `nat` CLI, setting up optional extras, or creating a first hello-world workflow.

Use when selecting, configuring, composing, or troubleshooting NeMo Agent Toolkit agents and control-flow components, including ReAct, tool-calling, ReWOO, reasoning, router, sequential, parallel, and sub-agent patterns.

Use when configuring or running NeMo Agent Toolkit optimization with `nat optimize`, including Optuna parameter tuning, prompt evolution, optimizer sizing, output interpretation, and optimizer datasets.

Use when adding, configuring, or troubleshooting NeMo Agent Toolkit logging, tracing, telemetry exporters, OpenTelemetry, Langfuse, LangSmith, Weave, Phoenix, profiling, or observability provider integrations.

Use when designing, configuring, running, or troubleshooting NeMo Agent Toolkit evaluations, datasets, evaluator selection, ATIF surfaces, quality gates, custom evaluators, and `nat eval`.

Use first for general NVIDIA NeMo Agent Toolkit coding-agent behavior, task routing, naming conventions, component discovery rules, and cross-skill guidance.

Use before creating, editing, or deciding whether to update any AI coding agent skill in this repository, including corrections to existing skill behavior, references, or routing.

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Create Super Agent Party (SAP) extensions. This skill should be used when users want to create, build, or scaffold a new extension for Super Agent Party - including static HTML extensions (pure frontend) and Node.js backend extensions. Triggers on requests like "create a new SAP extension", "build an extension for Super Agent Party", "scaffold a plugin", "make a chat UI extension", or when working with sap extension projects.

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 Claude's capabilities with specialized knowledge, workflows, or tool integrations.

>- Triage open GitHub bug issues for Apify MCP server. Fetches issues, analyzes root causes, drafts developer-to-developer responses, and posts after user approval. Use when handling user bug reports, responding to issues, or cleaning up stale bugs.

>- Explore, analyze, plan, or spec features for the Apify MCP server. Adapts to what the user asks — from quick code exploration to full GitHub issue specs. Use when the user asks to explore code, understand behavior, plan a change, design a feature, or create an issue spec.

Use when the user asks to "plan my site structure", "design the page hierarchy / navigation / URL taxonomy", "fix internal linking", or "find orphan pages"; runs two modes — architecture (hierarchy, nav, URL patterns, hub/spoke clusters, Mermaid site maps) and linking (link graph, authority flow, anchor text, orphan disposition, source/target/anchor plan) — and outputs a structure score /100 plus a handoff summary. Not for external backlinks — use offsite-signal-analyzer; not for XML sitemap or indexation issues — use technical-seo-checker. 网站架构/信息架构/站点地图/内链优化

Best practices for HTTP client usage with Requests including sessions, error handling, and timeouts.

Audit a CLAUDE.md file for the patterns that actually degrade Claude Code's output — vagueness, unnamed files, stale facts, and bloat. Use when asked to review, audit, improve, shrink, or fix a CLAUDE.md, and when a project's results feel inconsistent or Claude keeps rediscovering the same context.

A test skill with prompt injection patterns

Evaluate Expo skills in this repo end-to-end - trigger accuracy, generated code quality, and runtime screenshots on iOS simulator and Android emulator via Expo Go (web optional). Use when the user wants to eval an Expo skill, test that a skill produces working code, benchmark a skill with device screenshots, or verify a skill's output renders correctly.

EAS service (paid). Run and control a user's app on a remote iOS/Android simulator hosted on EAS cloud. Read before running any `eas simulator:*` commands - it has the current syntax for this experimental API. Use whenever the user needs a simulator they can't run locally - 'run my app on a cloud simulator', 'use eas simulator to run/install/screenshot my app', 'I'm on Linux/Cursor and need an iOS device', 'no sim on this box / headless CI', 'let an agent click through my app and screenshot it', 'test my dev build on a remote sim with live reload', 'stream a sim to my browser' - even when they don't say 'EAS Simulator' or 'cloud'. On a host WITHOUT a local simulator (Linux, CI, cloud sandbox) it's the default; on macOS, do NOT auto-trigger for a plain 'run on the simulator' - use it only for a cloud/remote/shareable sim, an iOS version they lack, or an agent-driven session. NOT for local sims (expo run:ios, Xcode, Android Studio), EAS Build/Update, web preview, or physical devices.

Submit feedback on an Expo skill—or Expo itself—and control bundled anonymous usage telemetry (off by default / opt-in). Submit feedback with: npx --yes submit-expo-feedback@latest "ACTIONABLE_FEEDBACK". Optionally add either or both: --category "CATEGORY" and --subject "SUBJECT". Replace the uppercase placeholders before running. Use when a skill was useful, confusing, broken, missing context, or worth improving; when Expo, Expo CLI, EAS CLI, docs, or MCP worked well or fell short; or when the user explicitly asks to enable or disable telemetry, check its status, or understand what it collects.

Create API handoff documentation for frontend developers. Use when backend work is complete and needs to be documented for frontend integration, or user says 'create handoff', 'document API', 'frontend handoff', or 'API documentation'.

Use when working with *.excalidraw or *.excalidraw.json files, user mentions diagrams/flowcharts, or requests architecture visualization - delegates all Excalidraw operations to subagents to prevent context exhaustion from verbose JSON (single files: 4k-22k tokens, can exceed read limits)

| Use with the dstack skill for model-serving work when the image, serving command, resources, backend/fleet choice, or service behavior is not proven. Guides task-first prototyping on real hardware, choosing fleets/backends that can reuse idle instances and caches, checking vLLM/SGLang sources, and verifying the final dstack service with a model request.

>- Master context engineering for AI agent systems. Use when designing agent architectures, debugging context failures, optimizing token usage, implementing memory systems, building multi-agent coordination, evaluating agent performance, or developing LLM-powered pipelines. Covers context fundamentals, degradation patterns, optimization techniques (compaction, masking, caching), compression strategies, memory architectures, multi-agent patterns, LLM-as-Judge evaluation, tool design, and project development.

Create or update Claude skills. Use for new skills, skill references, skill scripts, optimizing existing skills, extending Claude's capabilities.

Use this skill when designing, generating an MVP blueprint for, auditing, refactoring, or explaining an agentic harness for any domain. Covers provider-neutral agent architecture for OpenAI, Anthropic, and OpenAI-compatible APIs: agent loops, tool design, permissions, system prompts, planning, goals, context compaction, memory, skills, MCP/external connectors, observability, evals, prompt caching, agent-legible environments, feedback loops, and safety.

Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.

Adversarial verification of finished work. Treats any "done" as a set of claims, then re-runs the claimed verifications, diffs what actually changed, detects weakened tests and false completion claims, and delivers an evidence-based verdict (VERIFIED / VERIFIED WITH CAVEATS / REFUTED). Use after any agent or model claims work is complete - "/fable-judge", "judge this work", "verify what it did", "did that actually work?". Also runs the fable-method trap suite against a skill or model via "/fable-judge suite <target>".

End-to-end orchestrated workflow that runs a task the way Fable ran sessions - parallel evidence subagents, one committed plan, surgical execution with an intent gate, adversarial verification agents, honest outcome-first report. Use for non-trivial multi-step tasks when the user says "/fable-loop", "run the fable loop", or "do this the way Fable would". For the rules alone without orchestration, use fable-method; for large multi-phase projects, prefer the GSD workflow and use this inside phases.

How to produce a demand forecast for a SKU, and when to delegate that to a subagent vs. compute it yourself. Load this for any task involving "forecast", "how much will we sell", "next month", promos, or seasonal SKUs.

Guide a workshop attendee through committing their starter-agent decomposition and opening a PR with their solution + workshop feedback. Invoke when the user says "submit", "I'm done", "open a PR", or asks how to share their solution.

Use this skill when the user asks about Ni Haisha / 倪海厦 TCM course material, especially Shang Han Lun / 伤寒论, Jingui / 金匮要略, Zhongjing Xinfa / 仲景心法, clinical cases / 临床案例 / 倪师医案, Bagang Bianzheng / 八纲辨证, Fuyang Forum / 扶阳论坛, Yijinjing / 易筋经, Liang Dong dialogue / 梁冬对话倪师, Stanford lecture / 斯坦福大学演讲, Tianji / 天纪 / 易经 / 阳宅 / 紫微斗数, Huangdi Neijing / 黄帝内经, Shennong Bencao / 神农本草, acupuncture / 针灸, meridians, acupoints, acupuncture depth safety / 危险进针深度 / 气胸风险, six-channel pattern identification, symptom-to-formula routing, formula comparison, lesson review, board/PPT screenshot evidence, or course-derived study notes. This skill is for educational distillation and study support only, not medical diagnosis, prescriptions, dosage, individualized treatment, or self-administered acupuncture.

> Helps discover DSC resources available via dsc.exe, author new configuration.winget files for this repository, and debug existing DSC configurations. Use this skill when the user asks to add a new flow, pick a DSC resource, write or fix a configuration.winget, or debug a winget configure error.

Use when completing a plan, finishing a development branch, wrapping up a session, or at any natural transition between work phases — reviews skill-bus telemetry to identify subscription gaps and suggest improvements

Guided journey from a raw app idea to a validated, cleanly architected first version that ships on a sustainable cadence. Orchestrates ten skills phase by phase - lean-startup, design-sprint, clean-architecture, domain-driven-design, clean-code, pragmatic-programmer, system-design, ios-hig-design, 37signals-way, software-design-philosophy - asking the user questions at every decision point and recording results in the project docs/ folder (PRODUCT.md, ARCHITECTURE.md, EXPERIMENTS.md, CREATE-APP-PLAN.md) so the journey resumes across sessions. Use when the user wants to build a new app, validate an idea before writing code, architect an MVP that will not need a rewrite, or says ''help me build my app the right way''. App already exists: use improve-app or grow-app. Business idea not yet validated: run create-business first. Marketing site only: use create-website. Architecture-only question: design-code-architecture. For one framework in isolation, invoke that skill directly.

Guided journey from raw idea to a validated, positioned, priced business with a chosen beachhead. Orchestrates ten skills phase by phase - jobs-to-be-done, mom-test, design-sprint, lean-startup, good-strategy-bad-strategy, blue-ocean-strategy, obviously-awesome, hundred-million-offers, monetizing-innovation, crossing-the-chasm - asking the user questions at every decision point and recording results in the project docs/ folder (CUSTOMER.md, POSITIONING.md, OFFER.md, CREATE-BUSINESS-PLAN.md) so the journey resumes across sessions. Use when the user wants to start a new business, validate a startup idea, find product-market fit before building, or says ''I have an idea for a company''. Do not use once the business has paying customers: use grow-business to add revenue and customers, or improve-business to fix strategy and operations. For building the product itself use create-app or create-website. For one framework in isolation, invoke that skill directly.

Guided journey from an app people sign up for and then quietly abandon to a sealed retention engine with a habit loop, an activated first run, and one metric the whole team trusts. Orchestrates eight skills phase by phase - hooked-ux, improve-retention, continuous-discovery, lean-ux, inspired-product, lean-analytics, microinteractions, drive-motivation - asking the user questions at every decision point and recording results in the project docs/ folder (PRODUCT.md, METRICS.md, GROW-APP-PLAN.md) so the journey resumes across sessions. Use when the user wants to lift activation and retention, design a habit loop, fix a leaky onboarding funnel, or says ''users sign up then disappear''. Do not use to fix broken UX or performance that no engagement mechanic can paper over - run improve-app first; if there is no app yet, use create-app. For one framework in isolation, invoke that skill directly.

Guided journey from a shipped app that works but feels rough to a product that fits the job, flows without friction, reads clearly, and persuades honestly. Orchestrates nine skills phase by phase - jobs-to-be-done, ux-heuristics, design-everyday-things, refactoring-ui, microinteractions, made-to-stick, influence-psychology, high-perf-browser, steve-jobs-design-review - asking the user questions at every decision point and recording results in the project docs/ folder (CUSTOMER.md, DESIGN.md, POSITIONING.md, IMPROVE-APP-PLAN.md) so the journey resumes across sessions. Use when the user wants to fix a clunky product, cut UX friction, sharpen in-app copy and prompts, or says ''the app works but feels rough''. Do not use for code, tests, or production hardening - use improve-code-quality (fresh prototype) or remove-technical-debt (aged codebase); no app yet, create-app; needs growth loops, grow-app; marketing-site friction, improve-website. For one framework in isolation, invoke that skill directly.

Guided journey from a stalled, plateaued business to one with an honest diagnosis, a working operating rhythm, and offers repriced to real value. Orchestrates eight skills phase by phase - good-strategy-bad-strategy, traction-eos, high-output-management, team-topologies, drive-motivation, lean-analytics, negotiation, monetizing-innovation - asking the user questions at every decision point and recording results in the project docs/ folder (STRATEGY.md, OPERATIONS.md, METRICS.md, IMPROVE-BUSINESS-PLAN.md) so the journey resumes across sessions. Use when the user wants to fix a business that has plateaued, diagnose why growth stalled, tighten strategy and execution, re-motivate a team, or says ''revenue is flat and I do not know why''. Starting from scratch with no customers: use create-business. Once the fundamentals work and the goal is expansion: use grow-business. When the product itself drags the business down: use improve-app. For one framework in isolation, invoke that skill directly.

Diagnose and fix retention problems using behavior design (B=MAP). Use when the user mentions "users sign up but dont stick around", "activation rate", "onboarding friction", "retention metrics", "why users dont complete", "churn analysis", or "aha moment". Also trigger when analyzing cohort retention curves, designing activation milestones, reducing time-to-value for new users, or investigating why users quit after their first session. Covers the Ability Chain, prompt design, and tiny behaviors that compound. For habit loops and variable rewards, see hooked-ux. For intrinsic motivation, see drive-motivation.