FuZhiyu

Requires `superRA:using-superra` loaded first. Use when dispatching agents in the superRA workflow. Triggers include "dispatch N agents", "run these in parallel", "who should do the review", a multi-step workflow that needs coordination across roles, or a session handoff where workflow state must survive. Usable in any phase of the superRA workflow (PLAN / IMPLEMENT / INTEGRATE).

Use PROACTIVELY whenever performing data analysis on economic, financial, or panel datasets — importing raw data, cleaning, merging, filtering, constructing variables, aggregating, computing summary statistics, producing regression inputs, building figures, or writing analysis scripts. Triggers include panel data, "merge these datasets", "run regression", "clean this data", "construct variable X", "check the summary stats", or any data file with unknown structure. Language-agnostic (Python, Julia, R, Stata).

Use whenever creating a PLAN.md / RESULTS.md from scratch, maturing RESULTS.md into its permanent record at INTEGRATE, or when you need the full editing discipline for a task-block-structured handoff document. Carries the four document principles, the inline-edit rule, the stale-content checklist, and pointers to full PLAN.md / RESULTS.md anatomy templates. Usable standalone by a single author with no subagents — the author plays all roles and reads this skill directly. Doc-creation call sites: `superplan` Phase 2 (new plan + RESULTS.md skeleton) and `superintegrate` Step 3 doc-writer (Stage 2 maturation).

Utility skill (any phase). Use when refactoring analysis code for codebase integration, reviewing post-sync branch quality, auditing project docs, pruning a governing diff to minimum net diff, or using task-local Sync impact context as justification evidence. Carries the Codebase Integration checklist shared by implementer (self-check before commit) and reviewer (verification). Standalone-invokable outside the full integration workflow for any refactor that needs consistent quality gates.

Markdown style guide for agents writing PLAN.md, RESULTS.md, status reports, or standalone markdown reports, with optional references for figures, LaTeX math, and tables.

Use when about to run `git merge`, `git rebase`, or `git cherry-pick`; when syncing a feature, analysis, or work branch with a current base branch before integration; or when incoming changes may touch results-bearing files, source scripts, PLAN.md, RESULTS.md, drift tests, or domain-discipline artifacts. Triggers include: bare `git merge` / `git rebase` / `git cherry-pick` (the merge-guard hook flags these automatically), "sync with main", "pull main into this branch", "rebase onto main", "cherry-pick commit X", or any branch integration where conflict resolution must preserve the intent behind each side. Invoked by `superintegrate` during Sync and usable standalone by any agent or human doing an intent-aware branch integration.

Requires `superRA:using-superra` loaded first. Use when you have a PLAN.md in the superRA task-block format and are ready to implement its tasks; when a plan has been approved and you need per-task implementation with an implementer-reviewer pair; when resuming work on a plan where some tasks are `IMPLEMENTED`, some `REVISE`, and some not started; when an analysis is code-complete and you want to verify reproducibility and present completion options (merge / PR / keep / discard). Triggers include "execute the plan", "run task N", "implement this PLAN.md", "finish this analysis", a branch with an APPROVED plan but no code yet, or a REVISE state that needs orchestrator adjudication before re-dispatch.

Requires `superRA:using-superra` loaded first. Use when a plan is code-complete and reproducibility-verified and the user has chosen to finish, PR, or land the work; when key results need protection before they touch the base branch; when the branch must be synced with the current base and then refactored for codebase fit; when RESULTS.md needs to mature into its permanent record; when PLAN.md needs final disposition; or when final PR/publish/cleanup still needs to happen. Triggers include "integrate", "prepare this for PR", "finish this analysis", "protect key results", "write drift tests for the key results", "sync with main and refactor", "consolidate RESULTS.md", "mature the results document", "update project docs for this analysis", "open the PR", or the transition from `superimplement`'s completion menu.

Guide for rigorous economic data analysis. Use PROACTIVELY whenever performing data analysis on economic or financial datasets — importing, cleaning, merging, constructing variables, or producing summary statistics. Three core principles: (1) describe before and after every transformation, (2) document in jupytext percent format with interleaved code/narrative/outputs, (3) validate against economic intuition, literature, and cross-variable relationships. Includes pitfall checklists for merges, aggregations, filtering, and variable construction. Language-agnostic (Python, Julia). Trigger: any data analysis task involving economic, financial, or panel data.

Search and download financial data from WRDS (Wharton Research Data Services). Use when asked to "download from WRDS", "search WRDS", "get CRSP data", "download Compustat", "find WRDS table", "get stock returns", "download IBES", or any WRDS/financial database task involving CRSP, Compustat, IBES, TAQ, OptionMetrics, Fama-French, BoardEx, DealScan, or other WRDS datasets.

Comprehensive academic paper review covering mathematical correctness, writing clarity, consistency, argumentation, proofreading, and citations. Use when user asks to 'review draft', 'check paper', 'proofread manuscript', or requests feedback on academic writing. Can also verify code-paper consistency when source code is available. Defaults to comprehensive + standard review, with optional deep parallel review when Codex multi-agent support is available.

Convert PDFs to Markdown using Mistral OCR API with image extraction. Use when you need to extract structured text and images from PDFs, especially for scanned documents or documents with complex formatting. Outputs Markdown with embedded images.

Create new academic research projects with two-folder architecture. Use when user wants to create a new research project, start a new paper, set up a new analysis project, or mentions needing a project structure for research.

Create formal, fact-checked work journal entries after completing analysis work. Use when user asks to "summarize work", "document results", or "create work journal entry". Ensures code is committed, copies figures to attachments, and creates objective summaries with mandatory citations plus a report-quality verification pass. For quick reports without fact-checking, use the `report-in-markdown` skill.

Sync non-git data between existing git worktrees. Supports seed, diff, and apply modes using explicit --from/--to endpoints. Does not create/remove worktrees or manage sandbox settings.

Read and analyze academic papers from Zotero library. Use when the user requests to read, access, or analyze a paper by title, author, or topic from their Zotero library. Searches Zotero when Zotero tools are available, converts PDFs to Markdown, saves to Notes/PaperInMarkdown, and provides analysis.

Convert PDFs to Markdown using Mistral OCR API with image extraction. Use when you need to extract structured text and images from PDFs, especially for scanned documents or documents with complex formatting. Outputs Markdown with embedded images.

Create factual working journal entries in Notes/WorkingJournal/ after completing analysis work. Use when user asks to "summarize work", "document results", or "create working journal entry". Ensures code is committed, copies figures to attachments, and creates objective summaries with citations.

Read and analyze academic papers from Zotero library. Use when the user requests to read, access, or analyze a paper by title, author, or topic from their Zotero library. Automatically searches Zotero, converts PDFs to markdown, saves to Notes/PaperInMarkdown, and provides analysis.