Hybrid architecture combining Ralph's PRD format with Planning-with-Files' structured approach. Auto-generates PRDs from task descriptions, manages parallel story execution with…
프로젝트의 rules 구조에 새 규칙을 추가합니다. Progressive Disclosure 원칙에 따라 구조화된 규칙 파일을 생성합니다. "규칙 추가", "rule 추가", "새 규칙 만들기" 요청 시 활성화.
Agentic 시스템을 위한 TDD 전략을 수립한다. LLM 클라이언트 mock(VCR-style), golden dataset 기반 eval(최소 5건), hypothesis 기반 property-based test로 비결정성을 제어한다.
Answer data questions -- from quick lookups to full analyses. Use when looking up a single metric, investigating what's driving a trend or drop, comparing segments over time, or…
An example user-invoked skill that demonstrates frontmatter options and the skills/<name>/SKILL.md layout
Crear, probar y mejorar skills de forma iterativa. Usa cuando el usuario dice "crear skill", "crear habilidad", "build skill", "create a skill", "skill development", "desarrollar…
TypeScript SDK development with Node.js and browser support. Design SDK architecture, implement type-safe API clients, support ESM and CommonJS modules, and configure bundling for…
Claude Code hooks development guide. TRIGGERS - create hook, PostToolUse, PreToolUse, Stop hook, hook lifecycle, decision block.
Build autonomous AI agents with Claude Agent SDK. Structured outputs (v0.1.45, Nov 2025) guarantee JSON schema validation, plugins system, hooks for event-driven workflows.
Reconcile general ledger to subledger for a trade date or period — match at the position or transaction level, surface breaks, and classify each break by likely cause.
Claude Code ecosystem expertise. Modules: CLI tool (setup, slash commands, MCP servers, hooks, plugins, CI/CD), extensibility (agents, skills, output styles creation), CLAUDE.md…
Generate MCPB (MCP Bundle) packages for MCP server projects. Creates manifest.json, bundle directory structure, validates against the MCPB spec, and wires in CI/CD workflows.
Audits and optimizes websites for search engine visibility (SEO) and AI search citation (GEO), covering technical health, E-E-A-T content scoring, domain authority, structured…
Build with Claude Messages API using structured outputs for guaranteed JSON schema validation. Covers prompt caching (90% savings), streaming SSE, tool use, and model…
Use when debugging hook issues, working around known bugs (PreToolUse+AskUserQuestion), or configuring user hooks in settings.json.
Generate comprehensive equity research snapshots combining analyst consensus estimates, company fundamentals, historical prices, and macroeconomic context.
Investment banking presentation quality checker. Reviews a pitch deck or client-ready presentation for (1) number consistency across slides, (2) data-narrative alignment, (3)…
Maintain calendar of upcoming catalysts for portfolio positions and watchlist. Earnings dates, ex-div dates, regulatory events, macro releases.
Analyze the interest rate swap curve by pricing swaps at multiple tenors, overlaying government and inflation curves, and identifying curve trade opportunities.
Test local Jekyll build and visualize pages using Playwright MCP. Starts the development server, navigates through key pages, captures screenshots, and validates rendering.
Updates a presentation with new numbers — quarterly refreshes, earnings updates, comp rolls, rebased market data.
Provides information about how to create, structure, install, and audit Agent Skills, Plugins, Antigravity Workflows, and Sub-agents.
Design, review, and improve agent workflows & agent using SSOT, SRP, Fail Fast principles. Supports Prompt Chaining, Parallelization, Orchestrator-Workers patterns.
Multi-source research recipe via caveman-mcp — gather URLs/PDFs/PRs in parallel, compress each, synthesize with provenance. Pairs with knowledge-hygiene for conflict detection.
Produce a .xlsx file on disk (headless) instead of driving a live Excel workbook — for managed-agent sessions with no open Office app.
Use when adding allow/deny rules to Claude Code, granting project permissions, troubleshooting "permission denied" errors, "skill requires approval" prompts, or setting up shared…
Perform relative value analysis on bonds by combining pricing, yield curve context, credit spreads, and scenario stress testing.
Use when creating or editing Claude Code skills, agents (subagents), or slash commands. Provides complete YAML frontmatter property reference.
Write flux commentary for every P&L and balance-sheet line over threshold — current vs prior period and vs budget, with the driver explained from underlying activity.
Socratic exploration of a non-Blender-user's 3D intent before scene planning. Use when the request is vague, has multiple plausible interpretations, or needs creative scoping.
Guide for creating custom slash commands for Claude Code. Use when adding new commands, defining command arguments, or implementing command workflows.
Analyze franchise and multi-location unit economics including per-location P&L construction, four-wall EBITDA margins, prime cost optimization, contribution margin analysis,…
Day 2: 나만의 Skill 만들기 — 도구에서 워크플로우까지 - 인터랙티브 강의 진행. Use when starting day 2 training, teaching skill creation, or building custom workflows.
Generate a concise 4-5 page equity research earnings preview for a single company. Analyzes the most recent earnings transcript, competitor landscape, valuation, and recent news…
Evaluate FX carry trade opportunities by combining spot rates, forward points, interest rate differentials, volatility surface analysis, and historical price trends.
Analyze option volatility by combining vol surface data, option pricing with Greeks, and historical price data to assess implied vs realized volatility.
Build high-quality Agent Skills for Claude following official Anthropic best practices. Covers SKILL.md structure, frontmatter, description writing, progressive disclosure,…
Analyze the bond futures basis by pricing futures, identifying the cheapest-to-deliver, and comparing with yield curves to assess delivery option value and basis trading…
Clean up messy spreadsheet data — trim whitespace, fix inconsistent casing, convert numbers-stored-as-text, standardize dates, remove duplicates, and flag mixed-type columns.
Use when researching Claude Code or Codex upstream releases, selecting adaptations, or preparing Harness upgrades. Local-only; not for distribution.
**UNIVERSAL TRIGGER**: Use when user wants to START/CONTINUE/MANAGE a long-running development project across multiple sessions.
CRITICAL: Comprehensive guide for CoWork Skills CLI tool. Triggers on: cowork, Skills.toml, skill management, plugin configuration, cowork init, cowork install, cowork config,…
Tie an LP statement to the fund's NAV pack — recompute the LP's capital account from the NAV components and flag any line that doesn't agree.
Build agentic systems using Claude CLI in headless mode or the Claude Agent SDK. Use when building automation pipelines, CI/CD integrations, multi-agent orchestration, or…
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files.
Automatically validate implementations in real browsers after code is written or when user says "test this".
Create distinctive, memorable UI for landing pages, portfolios, marketing sites, and one-off creative work.
Specialized skill for React component development, hooks patterns, state management, context API, performance optimization, and modern React best practices.
Review fixed income portfolios by pricing multiple bonds, retrieving reference data, analyzing cashflows, and running scenario analysis.
Current state of Claude's memory, context, and Skills architecture as of late 2025. LOAD THIS when discussing context engineering, Skills, userMemories, memory management, context…
Loaded when user builds multi-model pipelines (Haiku/Sonnet/Opus). Covers cost-optimized routing, escalation, sub-agent delegation, and fallback chains.
Build coding agents with the Claude Agent SDK. Use when creating agentic workflows, implementing todo tracking, monitoring agent progress, building multi-turn conversations,…
Track and update investment theses for portfolio positions and watchlist. Maintains scorecard of pillars, catalysts, and conviction level.
Use this agent when the user needs to upgrade Anthropic SDK packages. This includes: upgrading @anthropic-ai/sdk or @anthropic-ai/claude-agent-sdk to newer versions, migrating…
Root-cause a reconciliation break to its source transaction or posting — follow the audit trail from the break row back to the originating entry on each side and state what…
Safely introduce external Git repositories as reference materials. Responsible for managing the `_reference` directory, ensuring external code is read-only and does not pollute…
Creates event-driven email listeners that monitor for specific conditions (like urgent emails from boss, newsletters to archive, package tracking) and execute custom actions.
Advanced python-docx patterns for handling nested tables, complex cell structures, and content extraction beyond basic .text property.
Build a roll-forward schedule for a balance-sheet account — beginning balance plus activity less reversals equals ending balance, with each component tied to GL.
Audit a skill against Anthropic skill-creator standards