hydromind-research-paper-writing — for Claude Code hydromind-research-paper-writing, HydroMind, community, for Claude Code, ide skills, hydromind-research-write, outline, paper_plan.json, paper_plan_sha256, opening

v4.0

关于此技能

适用场景: Ideal for AI agents that need treat read paths, write paths, forbidden paths, completion checks, and pre call prompts[] as. 本地化技能摘要: Internal doctrine for writer, reviewer, and reviser subagents under hydromind-research-write. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

功能特性

Treat read paths, write paths, forbidden paths, completion checks, and pre call prompts[] as
Draft paper/opening/opening.md from the approved outline and paper contract.
Preserve user citation markers instead of inventing citations.
Produce figure/table manifest, captions, and assets that trace to paper-plan figure/table IDs and
Keep diagnostic-only evidence out of main-text support unless the paper plan marks it as diagnostic.

# 核心主题

CMajorChords CMajorChords
[8]
[0]
更新于: 4/27/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 8/11

This page remains useful for teams, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Original recommendation layer Concrete use-case guidance Explicit limitations and caution
Review Score
8/11
Quality Score
44
Canonical Locale
en
Detected Body Locale
en

适用场景: Ideal for AI agents that need treat read paths, write paths, forbidden paths, completion checks, and pre call prompts[] as. 本地化技能摘要: Internal doctrine for writer, reviewer, and reviser subagents under hydromind-research-write. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

核心价值

推荐说明: hydromind-research-paper-writing helps agents treat read paths, write paths, forbidden paths, completion checks, and pre call prompts[] as. Internal doctrine for writer, reviewer, and reviser subagents under

适用 Agent 类型

适用场景: Ideal for AI agents that need treat read paths, write paths, forbidden paths, completion checks, and pre call prompts[] as.

赋予的主要能力 · hydromind-research-paper-writing

适用任务: Applying Treat read paths, write paths, forbidden paths, completion checks, and pre call prompts[] as
适用任务: Applying Draft paper/opening/opening.md from the approved outline and paper contract
适用任务: Applying Preserve user citation markers instead of inventing citations

! 使用限制与门槛

  • 限制说明: Keep diagnostic-only evidence out of main-text support unless the paper plan marks it as diagnostic.
  • 限制说明: Do not add unregistered empirical claims, use diagnostic-only evidence as main-text support, or describe a protocol diff
  • 限制说明: Read only paths authorized by the oracle

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.
  • - The underlying skill quality score is below the review floor.

Source Boundary

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

评审后的下一步

先决定动作,再继续看上游仓库材料

Killer-Skills 的主价值不应该停在“帮你打开仓库说明”,而是先帮你判断这项技能是否值得安装、是否应该回到可信集合复核,以及是否已经进入工作流落地阶段。

实验室 Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

常见问题与安装步骤

以下问题与步骤与页面结构化数据保持一致,便于搜索引擎理解页面内容。

? FAQ

hydromind-research-paper-writing 是什么?

适用场景: Ideal for AI agents that need treat read paths, write paths, forbidden paths, completion checks, and pre call prompts[] as. 本地化技能摘要: Internal doctrine for writer, reviewer, and reviser subagents under hydromind-research-write. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

如何安装 hydromind-research-paper-writing?

运行命令:npx killer-skills add CMajorChords/HydroMind。支持 Cursor、Windsurf、VS Code、Claude Code 等 19+ IDE/Agent。

hydromind-research-paper-writing 适用于哪些场景?

典型场景包括:适用任务: Applying Treat read paths, write paths, forbidden paths, completion checks, and pre call prompts[] as、适用任务: Applying Draft paper/opening/opening.md from the approved outline and paper contract、适用任务: Applying Preserve user citation markers instead of inventing citations。

hydromind-research-paper-writing 支持哪些 IDE 或 Agent?

该技能兼容 Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer。可使用 Killer-Skills CLI 一条命令通用安装。

hydromind-research-paper-writing 有哪些限制?

限制说明: Keep diagnostic-only evidence out of main-text support unless the paper plan marks it as diagnostic.;限制说明: Do not add unregistered empirical claims, use diagnostic-only evidence as main-text support, or describe a protocol diff;限制说明: Read only paths authorized by the oracle。

安装步骤

  1. 1. 打开终端

    在你的项目目录中打开终端或命令行。

  2. 2. 执行安装命令

    运行:npx killer-skills add CMajorChords/HydroMind。CLI 会自动识别 IDE 或 AI Agent 并完成配置。

  3. 3. 开始使用技能

    hydromind-research-paper-writing 已启用,可立即在当前项目中调用。

! 参考页模式

此页面仍可作为安装与查阅参考,但 Killer-Skills 不再把它视为主要可索引落地页。请优先阅读上方评审结论,再决定是否继续查看上游仓库说明。

Upstream Repository Material

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Upstream Source

hydromind-research-paper-writing

Internal doctrine for writer, reviewer, and reviser subagents under hydromind-research-write. This AI agent skill supports Claude Code, Cursor, and Windsurf

SKILL.md
Readonly
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
Supporting Evidence

Internal doctrine for writer, reviewer, and reviser subagents under hydromind-research-write. The parent skill owns all phase advancement and promotion decisions; this skill governs how subagents write, review, and revise artifacts.

Shared Rules

  • Start by reading hydro research write status <research_id> --json and hydro research write instructions <research_id> --phase <phase> --json.
  • Treat read_paths, write_paths, forbidden_paths, completion_checks, and pre_call_prompts[] as authority.
  • Record every LLM call in paper/provenance.json.llm_calls[] with SHA-256 hashes of the prompts supplied by oracle instructions.
  • Read only paths authorized by the oracle. Typical sources include design/paper/paper_plan.json, the complete design/paper/*.md design group, execution/results.md, execution/evidence_review.json, and loop evidence.
  • Finish by running hydro research write validate <research_id> --phase <phase> --strict --json and return the JSON findings to the parent.

outline-planner

  • Phase: outline.
  • Read the current write status and hydro research write instructions <research_id> --phase outline --json before reading authorized source files.
  • Produce paper/outline.json from paper_plan.json; include paper_plan_sha256, sections, figures, tables, equations, and claims.
  • Finish by running hydro research write validate <research_id> --phase outline --strict --json and return the JSON findings to the parent.

opening-drafter

  • Phase: opening.
  • Read the current write status and hydro research write instructions <research_id> --phase opening --json before reading authorized source files.
  • Draft paper/opening/opening.md from the approved outline and paper contract.
  • Preserve user citation markers instead of inventing citations.
  • Finish by running hydro research write validate <research_id> --phase opening --strict --json and return the JSON findings to the parent.

figures-planner

  • Phase: figures.
  • Read the current write status and hydro research write instructions <research_id> --phase figures --json before reading authorized source files.
  • Produce figure/table manifest, captions, and assets that trace to paper-plan figure/table IDs and ready evidence.
  • Keep diagnostic-only evidence out of main-text support unless the paper plan marks it as diagnostic.
  • Finish by running hydro research write validate <research_id> --phase figures --strict --json and return the JSON findings to the parent.

draft-writer

  • Phase: draft.
  • Read the current write status and hydro research write instructions <research_id> --phase draft --json before reading authorized source files and applying any pre_call_prompts[].
  • Write a unified paper/drafts/paper.md; use [CLAIM:<claim_id>] and [EVIDENCE:<evidence_id>] markers where needed for validator traceability.
  • Do not add unregistered empirical claims, use diagnostic-only evidence as main-text support, or describe a protocol different from execution/evidence_review.json.
  • Finish by running hydro research write validate <research_id> --phase draft --strict --json and return the JSON findings to the parent.

refinement-reviewer

  • Phase: refinement.
  • Read the current write status and hydro research write instructions <research_id> --phase refinement --json before reviewing or revising, and apply any pre_call_prompts[].
  • Run the formal reviewer quorum, aggregate required revisions, revise only when evidence remains sufficient, and preserve the best accepted draft snapshot.
  • If evidence is insufficient, tell the parent to rollback to Execute or Propose instead of filling gaps with prose.
  • Finish by running hydro research write validate <research_id> --phase refinement --strict --json and return the JSON findings to the parent.

No-Reference Policy

HydroMind Research does not perform citation discovery, citation pool construction, BibTeX generation, reference formatting, or citation coverage verification. Do not invent citation keys.

If the paper needs a user-supplied reference, preserve a marker such as [USER_CITATION_NEEDED: reservoir forecasting baseline]. This marker may remain in the final manuscript for user post-processing.

Reviewer Personas

Formal-paper refinement uses at least six comprehensive reviewers per round:

  • narrative_quality_reviewer
  • hydrology_logic_reviewer
  • experimental_skeptic_reviewer
  • method_reporting_reviewer
  • figure_equation_reviewer
  • severe_generalist_reviewer

Each persona may emphasize a different concern, but every reviewer must cover the whole manuscript: sections, mandatory claims, main-text evidence, protocol transparency, writing quality, blocking issues, required revisions, and score justification.

paper-review-v1

Each reviewer writes one JSON review with:

  • schema_version: "paper-review-v1"
  • reviewer_id
  • round
  • axis_scores with numeric scores and concrete justifications
  • per_section_comments
  • claim_level_objections
  • evidence_checks
  • blocking_issues
  • required_revisions
  • decision
  • overall_score

Invalid reviews do not count toward review quorum. A review is invalid if it misses required sections, mandatory claims, main-text evidence, score justifications, traceable blocking issues, or actionable required revisions.

paper-refinement-v2

The reviser and parent workflow maintain paper/refinement/worklog.json with schema paper-refinement-v2:

  • rounds[]
  • per-round review_paths
  • valid_review_count and invalid_review_count
  • aggregate_path
  • reviser_response_path
  • decision
  • overall_score
  • blocking_issue_count
  • accepted_snapshot
  • top-level best_round, best_score, halted, and halt_reason

Acceptance rules are conservative: score drops, increased blocking issues, unsupported claims, stale paper-plan linkage, or protocol transparency regressions require revert. Halt requires minimum rounds, valid review quorum, zero blocking issues, and a best accepted draft snapshot.

Promote Boundary

Subagents do not write paper/final/paper.md. The parent calls hydro research write promote <research_id> --json, which copies the best accepted draft and records promotion provenance.

Do Not

  • Do not create references, BibTeX, or citation keys.
  • Do not merge reviewer and reviser roles into one transcript.
  • Do not omit prompt hashes from provenance.
  • Do not bypass oracle validation with manual structure checks.
  • Do not write outside the current phase's write_paths.

相关技能

寻找 hydromind-research-paper-writing 的替代方案 (Alternative) 或可搭配使用的同类 community Skill?探索以下相关开源技能。

查看全部

openclaw-release-maintainer

Logo of openclaw
openclaw

本地化技能摘要: 🦞 # OpenClaw Release Maintainer Use this skill for release and publish-time workflow. It covers ai, assistant, crustacean workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

333.8k
0
AI

widget-generator

Logo of f
f

本地化技能摘要: Generate customizable widget plugins for the prompts.chat feed system # Widget Generator Skill This skill guides creation of widget plugins for prompts.chat . It covers ai, artificial-intelligence, awesome-list workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf

149.6k
0
AI

flags

Logo of vercel
vercel

本地化技能摘要: The React Framework # Feature Flags Use this skill when adding or changing framework feature flags in Next.js internals. It covers blog, browser, compiler workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

138.4k
0
浏览器

pr-review

Logo of pytorch
pytorch

本地化技能摘要: Usage Modes No Argument If the user invokes /pr-review with no arguments, do not perform a review . It covers autograd, deep-learning, gpu workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

98.6k
0
开发者工具