Migrates ResearchFlow's architecture to a new professional domain (e.g. frontend development, accounting, journalism). Interactive session with the user to map research concepts to domain equivalents, then generates a complete set of adapted skills and folder structure. Explicit trigger only.

Guides research ideation from broad thoughts to a focused, testable plan with explicit scope cuts, prioritized hypotheses, and immediate next experiments. Use when the user wants co-creation and step-by-step narrowing, not review verdicts.

Converts internal research notes into shareable Obsidian-friendly Markdown files. Use when the user explicitly asks to make a share version, export a note for sharing, hide knowledge base traces, replace internal wiki links with public paper links, rewrite internal wording for external readers, or generate a content-driven share filename.

Analyzes academic PDFs into structured Markdown under `paperAnalysis/`. Reads local PDFs only (no network, no image generation). Use when the user asks to analyze one PDF or a folder of PDFs, or to run paper analysis for the local knowledge base. Handles path resolution so that if the PDF is already under `paperPDFs/<Category>/<Venue_Year>/`, the `.md` is written to `paperAnalysis/` in the same structure; otherwise infers category and venue (e.g. `CVPR_2025`), copies the PDF into `paperPDFs/`, and writes the `.md` to `paperAnalysis/`.

Runs a unified metadata consistency audit across paperAnalysis logs and analysis notes, checking title/venue/year/category consistency, link/pdf_ref completeness, duplicates, and structure anomalies; writes quality_report_*.md under paperAnalysis.

Builds/refreshes `paperCollection/` index notes from `paperAnalysis/` frontmatter. Use when the user asks to update/rebuild `paperCollection`, regenerate indexes (by task/technique/venue), or after adding/editing analysis notes and PDF refs.

Collects paper candidates from web URLs by fetching and storing pages locally, then appending rows to `paperAnalysis/analysis_log.csv`. Use when the user provides URLs + keyword constraints + venue/year and wants candidates added to the unified log.

Uses colocated paper download tools to download, verify, and repair local PDFs according to triage logs (e.g., ICLR_2026.txt) so that `paperPDFs/` stays complete and deduplicated. Use when you have a curated candidate list under `paperAnalysis/` and want all corresponding PDFs downloaded/checked before analysis or collection rebuild.

Queries the local `paperAnalysis/` notes for research. Finds papers by title, task path, technique tags, venue, or year; summarizes methods and evidence across papers; cites core_operator and primary_logic from analysis frontmatter. `paperCollection/` is optional and mainly serves statistics, Obsidian navigation, and backlink exploration.

Syncs papers from a Zotero library into RF's structured layout via pyzotero / Zotero API (primary) or flat PDF folder import (fallback). Copies PDFs into `paperPDFs/<Category>/<Venue_Year>/`, writes rich metadata to `paperAnalysis/processing/zotero/manifest.jsonl`, and appends lightweight rows to `analysis_log.csv`. Supports incremental sync. Use when the user wants to import papers from Zotero into the ResearchFlow pipeline.

Explores and structures research ideas into `paperIDEAs/` notes using the local paper knowledge base and frontier techniques. Use when the user provides research questions or ideas and wants decomposed candidate directions, related-work analysis based primarily on `paperAnalysis`, and cross-domain support from image/video generation, MLLM, Agent, or RL, automatically saved as dated idea notes under `paperIDEAs/`.

Runs a strict-but-fair ICLR/CVPR/SIGGRAPH reviewer challenge on idea, roadmap, or full paper, with major-risk diagnostics and actionable repair paths. Use when the user wants high-pressure review questioning instead of brainstorming.

Obsidian Flavored Markdown conventions for ResearchFlow. Use when generating or editing any .md file in the vault (analysis notes, collection indexes, idea notes, wiki pages). Ensures all output is Obsidian-native and renders correctly in reading view, graph view, and backlink panels. Adapted from kepano/obsidian-skills (MIT).

Detects post-invocation skill mismatch patterns, summarizes why they may recur, and asks whether to revise the skill now. Use when a called .claude skill output is clearly unfit for the user intent and similar mismatch is likely to happen again.