mine-writing-patterns
The mine-writing-patterns command extracts reusable writing conventions, structural patterns, and stylistic signals from academic papers and merges them into a persistent writing memory file. Use it to study how strong papers frame sections, construct arguments, handle rebuttals, and conform to venue expectations before drafting your own work or composing reviewer responses.
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/Galaxy-Dawn/claude-scholar/HEAD/commands/mine-writing-patterns.md -o ~/.claude/commands/mine-writing-patterns.mdmine-writing-patterns.md
# /mine-writing-patterns - Installed Writing Memory Mining Read the paper source "$source" and update the active installed **paper-miner writing memory**. ## Default target Always write mined knowledge into the active installed skill memory, not the repository checkout copy: ```text ~/.claude/skills/ml-paper-writing/references/knowledge/paper-miner-writing-memory.md ``` This command does **not** create project-specific writing memory unless the user explicitly asks for a project-local writing memory. ## When to use Use this command when you want to: - learn reusable writing patterns from a strong paper, - study how a venue frames introductions, methods, results, or rebuttals, - mine phrasing and structure signals before drafting, - enrich the writing memory that powers `ml-paper-writing` and `review-response`. ## Usage ### Basic usage ```bash /mine-writing-patterns path/to/paper.pdf ``` ### Mine from an arXiv paper ```bash /mine-writing-patterns https://arxiv.org/abs/2301.xxxxx ``` ### Focus on rebuttal or venue signals ```bash /mine-writing-patterns path/to/paper.pdf rebuttal /mine-writing-patterns path/to/paper.pdf venue ``` ## Workflow ### Step 1: Resolve the paper source Acceptable inputs: - local PDF - local DOCX - arXiv URL - readable web URL - short natural-language request that identifies the paper(s) If the source is ambiguous, narrow it before mining. ### Step 2: Invoke `paper-miner` Use the `paper-miner` agent to: - extract paper content, - identify reusable writing knowledge, - merge it into the active installed writing memory, - avoid duplicate entries, - preserve source attribution. ### Step 3: Respect the focus mode Interpret `$focus` as follows: | Focus | Priority | |------|----------| | `general` | Mine balanced signals across all major sections | | `introduction` | Emphasize framing, motivation, and contribution setup | | `method` | Emphasize exposition style, technical sequencing, and clarity | | `results` | Emphasize result narration, claim-evidence language, and interpretation | | `rebuttal` | Emphasize clarification phrases, response structure, and reviewer-facing tone | | `venue` | Emphasize venue-specific style and convention signals | ### Step 4: Update the canonical memory only The canonical write target is the active installed skill memory: ```text ~/.claude/skills/ml-paper-writing/references/knowledge/paper-miner-writing-memory.md ``` Update one or more of these sections: - `Writing patterns mined` - `Structure signals` - `Reusable phrasing` - `Venue-specific signals` - `How this helps our writing` - `Source index` If that file is unavailable in the current runtime, use the configured installed skill home for the active runtime and state the exact path in the final summary. Do not silently fall back to the repository checkout. Do not create project-local writing memory. Do not scatter the mined result across multiple maintained knowledge files. ### Step 5: Return a standardized mining summary The final response should follow the `paper-miner` standardized output format: - metadata - memory write summary - new reusable patterns - how we should reuse this - blockers or limits ## Related integrations - `ml-paper-writing` reads this active installed memory before drafting or revising sections. - `review-response` reads this active installed memory when tone, phrasing, and rebuttal structure matter. - `paper-miner` is the agent that performs the actual mining work. ## Success criteria - the target paper is read successfully, - reusable writing knowledge is merged into the canonical memory, - source attribution is preserved, - no project-specific writing memory is created, - the user receives a standardized mining summary.
Use when creating or configuring Claude Code agents and their frontmatter.
Run a blocker-first post-experiment workflow: validate evidence, produce strict statistical analysis when possible, and generate a decision-oriented results report only when the analysis bundle is sufficient. Uses results-analysis + results-report as a gated two-stage workflow.
Use only when creating new registrable ML components that require Factory or Registry patterns.
This skill should be used when the user asks to "debug this", "fix this error", "investigate this bug", "troubleshoot this issue", "find the problem", "something is broken", "this isn't working", "why is this failing", or reports errors/exceptions/bugs. Provides systematic debugging workflow and common error patterns.
This skill provides reference guidance for citation verification in academic writing. Use when the user asks about "citation verification best practices", "how to verify references", "preventing fake citations", or needs guidance on citation accuracy. This skill supports ml-paper-writing by providing detailed verification principles and common error patterns.
This skill should be used when the user asks to review a diff or pull request, write review comments, audit code quality, establish review standards, or improve how a team performs code review.
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.