CoPaper-OpenCode

Detect when the user wants to start a new CoPaper paper project or initialize a workspace, run `copaper --root . init` when needed, then inspect the current workflow phase and immediately begin the appropriate next phase work.

Inspect the current CoPaper workflow phase, move forward, move backward, or jump to a named phase when the user asks to view, advance, return, roll back, or switch phases in OpenCode, then invoke the skill for the active phase. Uses `copaper status --json` and `copaper set-phase` instead of editing state files.

Convert `paper.md` into a final LaTeX paper project using a user-provided conference or journal template placed under `templates/latex/`. Use when the user asks to generate the final LaTeX paper from the CoPaper markdown draft with a local template.

Helps create placeholder data (tables, figures, metrics) for evaluation sections with clear warnings that all numbers must be replaced with real experimental results. Also generates descriptions explaining what the data shows and how it supports the paper's claims and insights.

Detects undefined terms, unclear descriptions, and clarity issues in academic paper drafts to improve readability and understanding.

Teaches agents how to manage a CoPaper project through the OpenCode plugin tools, including dashboard, initialization, artifact readiness, workflow status, event log inspection, and phase updates. Use this skill whenever the task is about workflow/state management rather than direct paper writing.

Checks for bogus/placeholder data in evaluation sections and verifies that each table and figure has a linked reproduction script that generates matching results.

Evaluates whether the evaluation protocol has comprehensive research questions that support the main insight and design decisions, and ensures proper handling of threats to validity.

Helps users understand experiment code, analyze results, and review experimental protocols. Use this skill when the user wants to analyze experiments, understand code, or review experimental design.

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Detects and fixes patterns including inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, passive voice, negative parallelisms, and filler phrases. Triggers on "humanize this", "make this sound more human", "remove AI traces".

Guides the post-paper.md LaTeX final-draft workflow. Use when the user has a completed paper.md and wants to write the final LaTeX paper from a downloaded conference template, create writing_plan.md, initialize tex/ structure, draft sections, or revise the LaTeX final draft.

Extracts content from LaTeX files to fill in paper.md. Use this skill when the user wants to import content from existing LaTeX papers into the CoPaper structure.

Detects logical discrepancies and inconsistencies in academic paper drafts, including claim-evidence mismatches, contradictions, and argumentation flaws.

Automatically writes and improves paper.md content by running a write-check-fix loop. Can use relatedwork-finder to download papers and bogus-data-helper to generate placeholder data. Runs all checkers to iteratively improve the paper until no issues remain or user input is needed.

Helps users write and improve markdown academic paper content following CoPaper GUI structure. Use this skill when the user wants to write or improve paper.md content for academic quality.

Reviews and improves markdown academic paper content following CoPaper GUI structure. Use this skill when the user wants to review or improve paper.md content for academic quality.

Converts markdown academic paper content to high-quality LaTeX format suitable for top-tier conferences and journals. Supports user-provided conference templates for format adaptation. Use this skill when the user wants to generate LaTeX from paper.md.

Evaluates whether the paper's key insight is sufficiently novel by comparing with existing literature and analyzing novelty claims and differentiation from prior work.

Converts an existing PDF draft into paper.md section by section by extracting text, mapping claims into the existing paper framework, and polishing wording without inventing new content.

Converts a research PPT/PPTX deck into storyline.md by extracting slide text, mapping it to existing storyline sections, and polishing wording without inventing new claims.

Evaluates whether the problem is clearly defined, and whether its importance and practicalness are thoroughly supported with evidence.

Find the related work papers in the relatedwork folder based on storyline.md or paper.md content.

Drive the relatedwork summarization CLI, build the literature cross-index, and produce a coverage report.

Conducts multi-round Review-Revise cycles based on 7-checker output to systematically improve paper quality. Each issue requires user confirmation before modification. Use this skill when the user wants to review and revise their paper.

Conducts Socratic research discussions to help users critically examine their insights, methods, and claims. Integrates with 7 checker dimensions for targeted questioning. Use this skill when the user wants to discuss or analyze their research.

Helps users write and improve markdown academic paper content using a strict state-machine workflow with context isolation to prevent hallucinations. Use this skill when the user explicitly requests strict state-machine writing or high-fidelity paragraph-by-paragraph writing with RAG.

Guides users through constructing and refining their research storyline in storyline.md. It can also reverse-extract storyline structure from an existing paper.md. Interactive, section-by-section workflow that polishes user input without inventing content. Triggers on "help me write storyline", "帮我写 storyline", "构建研究主线".

Performs comprehensive pre-submission checks on paper.md covering format, citations, figures, word count, completeness, data authenticity, and overall quality. Generates a structured precheck report. Use this skill when the user wants to verify their paper is ready for submission.

Evaluates whether the design section contains sufficient technical depth, including significant new designs, non-trivial challenges, and solutions that cannot be achieved with simple approaches.

Orchestrates structured paper framework writing by scanning paper.md completion status, recommending writing order, and offering fine mode (markdown-helper), strict mode (state-machine-markdown-helper), or fast mode (mad-writer). Auto-triggers 7-checker review after each section. Use this skill when the user wants to write or start writing their paper systematically.

Helps teachers add structured human comments to academic paper drafts, distinguishing between real reviewer feedback and AI-generated guidance/examples.