Changhochien

Use when financial-services work requires processes an earnings event end to end — reads the call transcript and filings, updates the coverage model, and drafts the post-earnings note. Use when a covered name reports; for a single name interactively, or fanned out across a coverage list as a managed agent..

Use when financial-services work requires reconciles general ledger to subledger across asset classes for a trade date — finds breaks, traces root cause, and routes the exception report for sign-off. Use for daily or month-end recon runs; not for journal-entry posting (use month-end-closer for that)..

Use when financial-services work requires parses an onboarding document packet, runs the firm's KYC/AML rules engine, screens against sanctions and PEP lists, and flags gaps for escalation. Use for new-client onboarding or periodic refresh — not for transaction monitoring..

Use when financial-services work requires produces sector or thematic market research — industry overview, competitive landscape, trading-comps spread of the peer set, and a thematic ideas shortlist — packaged as a research note with optional slides. Use when an analyst or PM asks for a primer on a sector or theme; not for single-name coverage updates (use earnings-reviewer for that)..

Use when financial-services work requires builds a briefing pack before a client or prospect meeting — relationship history from CRM, holdings and recent activity, market context, and a suggested agenda. Use ahead of any client meeting; pairs with a calendar event..

Use when financial-services work requires builds DCF, LBO, three-statement, and trading-comps models live in Excel from a ticker and assumption set. Use when you need a clean model from scratch — not for updating an existing coverage model (use earnings-reviewer for that)..

Use when financial-services work requires runs the month-end close for an entity — accruals, roll-forwards, and variance commentary — and stages the close package for controller sign-off. Use for period-end close; not for daily reconciliation (use gl-reconciler for that)..

Use when financial-services work requires end-to-end investment banking pitch agent. Given a target company and a strategic situation (e.g., "exploring strategic alternatives"), autonomously pulls comps and precedents from market data, builds a DCF and football-field valuation in Excel, and generates a branded pitch deck on the bank's PowerPoint template. Use when an MD or senior banker asks for a first-draft pitch on a name — not for editing an existing deck (use the pitch-deck skill directly for that)..

Earnings Preview

Model Update

Morning Note

Idea Generation

Sector Overview

Client Report

Client Review Prep

Investment Proposal

AI film director for scene blocking, shot composition, visual storytelling. Use when: directing, blocking, shot design, coverage, cinematography. Generates image prompts for scenes. Keywords: film, directing, blocking, shots, visuals.

AI film editor for post-production, footage organization, pacing, video editing workflows. Use when: editing, post-production, cuts, assembly, rough cuts, final cuts, color, sound. Integrates with video generation. Keywords: film, editing, post, cuts, video.

AI 1st AD for call sheets, daily scheduling, crew coordination, production logistics. Use when: creating call sheets, scheduling shoots, coordinating talent, managing daily logistics, production calls. Keywords: film, first AD, call sheet, scheduling, production.

AI image generator for film scenes, concept art, storyboards, visual references. Use when: generating images, concept art, storyboards, visual references, scene visualization. Uses MiniMax for image generation. Keywords: image, art, concept, storyboard, visual, generate.

AI film producer for budget management, production oversight, scheduling coordination, team management. Use when: producing films, budget decisions, production planning, team coordination, greenlighting. Keywords: film, producing, budget, production, management.

AI screenplay/script writer for film and video. Use when: writing scripts, screenplays, dialogue, scenes, story beats, character development. Generates production-ready scripts. Keywords: script, screenplay, writing, dialogue, scenes.

AI film production pipeline orchestrator for end-to-end content creation. Use when: coordinating production pipeline, generating scripts to film, orchestrating team, production planning, full workflow from concept to final edit. Keywords: film, pipeline, orchestrator, production, workflow.

AI video generator for film scenes, motion clips, visual sequences. Use when: generating video, motion clips, scene animations, video sequences, film content. Uses MiniMax for video generation. Keywords: video, film, clip, motion, generate, scene.

Multi-agent orchestration for PI: team coordination, autonomous execution, persistence loops, and requirements gathering. USE FOR: multi-agent development, parallel execution, code implementation, architecture design, security review, test automation, project planning. Commands: /skill:team, /skill:autopilot, /skill:ralph, /skill:deep-interview, /skill:plan, /skill:verify

Reactive team orchestration. Spawn workers, monitor completions, dynamically spawn newly unblocked tasks until all complete.

Full autonomous execution from idea to working code. Use when you want end-to-end autonomous development.

Cancel active execution modes and clean up state.

Socratic requirements gathering with ambiguity scoring. Use for clarifying vague ideas before building.

tmux-based multi-agent orchestration using pi-team CLI. Spawn multiple AI agents (PI, Claude, Codex, Gemini) in parallel tmux sessions. USE FOR: parallel implementation, multi-provider coordination, large-scale tasks, distributed work. Commands: /skill:pi-team spawn N:provider "task", /skill:pi-team status, /skill:pi-team aggregate, /skill:pi-team shutdown

Strategic planning with task breakdown and risk assessment. Use before starting complex work.

Persistence loop until task completion. Use when work must be verified complete.

MiniMax Token Plan CLI for image generation, speech synthesis, video generation, and music generation. Use when asked to "generate an image", "create a product photo", "synthesize speech", "generate a video", "create music", "make a song", or "text to speech".

Generate images, speech, video, or music via MiniMax Token Plan APIs. Activates the appropriate minimax CLI subcommand based on modality. Use when asked to "generate an image", "create a product photo", "synthesize speech", "generate a video", or "create music". For detailed options, see reference/<modality>.md for the relevant modality.

Integrate with Hermes multi-agent Kanban board. Use when creating tasks for Hermes workers, monitoring board state, or coordinating multi-agent workflows.

Karpathy's LLM Wiki — build and maintain a persistent, compounding markdown knowledge base across sessions. Use proactively whenever valuable knowledge could be saved for later — do NOT let insights disappear between sessions. Use whenever the user wants to create a wiki, ingest sources, query compiled knowledge, build a knowledge base, or maintain project memory that persists between sessions. Activate on: wiki, create a wiki, ingest into wiki, query wiki, wiki lint, build a knowledge base, remember this, save this to my wiki, I learned something about X, this should be in my wiki.

Web search and image understanding via MiniMax Token Plan APIs. Use when asked to "search the web", "look up", "find information online", "analyze an image", "describe this image", or "understand what's in this picture".

Break large coding tasks into self-contained micro-edits with code examples, constraints, and validation so smaller subagents can execute them safely. Use when the user says "micro-edit", "small changes", "break into tasks", "parallel micro-tasks", or wants to split a large change into reviewable pieces.

Simplifies, cleans up, and refactors code for clarity, consistency, maintainability, and modest efficiency while preserving behavior. Use when the user asks to simplify code, clean up a file or diff, reduce complexity, remove duplication, improve naming, or refactor for readability.

Use when delegating simple research, review, mapping, verification, or planning tasks to multiple Pi coding agents without edits, worktrees, dispatch JSON, or merges.

Orchestrate pi coding agents with DAG-aware dependency resolution, git worktree isolation, automatic retry, and structured JSON output. Use this skill when: - spawning pi agents for any subtask - tasks have dependency ordering (A must finish before B starts) - parallel agents need isolated git workspaces - you need structured output + automatic revert on failure