Automated summary
This skill detects the state of an interrupted webnovel writing task and offers safe recovery options (discard the partial work or roll back via Git) after loading its recovery protocol and data-flow references.
Strengths
- Explicitly detects the interruption point with workflow_manager.py detect rather than guessing how far the work got
- Requires user confirmation before any recovery and presents risk-ranked options (delete and restart vs Git rollback)
- Tailors the strategy to the difficulty of the interrupted step, including the costly (~$0.15) Step 6 dual-chapter review
- Flags long interruptions (>1 hour) as high context-loss risk and advises against resuming in place
Limitations
- Tightly coupled to the webnovel plugin: relies on CLAUDE_PLUGIN_ROOT, workflow_manager.py and the workflow-resume.md and system-data-flow.md references
- Assumes a Git history with per-chapter tags (ch0001, etc.) for the rollback option
- Written entirely in Chinese and scoped to a webnovel pipeline, which limits reuse outside that context
Use it when a /webnovel-write command or another webnovel task was interrupted and you want to resume cleanly without overwriting partial work.
Do not use it to resume a task outside the webnovel pipeline, or if you want an unfinished chapter generation to continue automatically.
Security analysis
CautionThe skill performs legitimate recovery tasks using Bash, git, and Python scripts. It includes potentially destructive operations (git reset --hard, cleanup) but only after explicit user selection via AskUserQuestion, and there is no network access or data exfiltration. Risk is moderate, not malicious.
- •Uses `git reset --hard` which can discard uncommitted changes and is irreversible.
- •Runs Python `workflow_manager.py cleanup/clear` scripts that may delete files or state; exact behavior depends on external scripts.
- •Executes commands in Bash with broad permissions, though recovery requires user confirmation via AskUserQuestion.
Examples
My /webnovel-write 7 run got cut off earlier. Run /webnovel-resume, show me where it stopped and what options I have.Before I start anything new, use /webnovel-resume to check whether any webnovel task is still in an interrupted state.I left a webnovel task unfinished overnight — please run /webnovel-resume and tell me whether resuming is still safe or if I should start over.name: webnovel-resume description: Recovers interrupted webnovel tasks with precise workflow state tracking. Detects interruption point and provides safe recovery options. Activates when user wants to resume or /webnovel-resume. allowed-tools: Read Bash AskUserQuestion
Task Resume Skill
Workflow Checklist
Copy and track progress:
任务恢复进度:
- [ ] Step 1: 加载恢复协议 (cat "${CLAUDE_PLUGIN_ROOT}/skills/webnovel-resume/references/workflow-resume.md")
- [ ] Step 2: 加载数据规范 (cat "${CLAUDE_PLUGIN_ROOT}/skills/webnovel-resume/references/system-data-flow.md")
- [ ] Step 3: 确认上下文充足
- [ ] Step 4: 检测中断状态
- [ ] Step 5: 展示恢复选项 (AskUserQuestion)
- [ ] Step 6: 执行恢复
- [ ] Step 7: 继续任务 (可选)
Step 1: 加载恢复协议(必须执行)
cat "${CLAUDE_PLUGIN_ROOT}/skills/webnovel-resume/references/workflow-resume.md"
核心原则(读取后应用):
- 禁止智能续写: 上下文丢失风险高
- 必须检测后恢复: 不猜测中断点
- 必须用户确认: 不自动恢复
Step 2: 加载数据规范
cat "${CLAUDE_PLUGIN_ROOT}/skills/webnovel-resume/references/system-data-flow.md"
Step 3: 确认上下文充足
检查清单:
- [ ] 恢复协议已理解
- [ ] Step 难度分级已知
- [ ] 状态结构已理解
- [ ] "删除重来" vs "智能续写" 原则已明确
如有缺失 → 返回对应 Step
Step 难度分级(来自 workflow-resume.md)
| Step | 难度 | 恢复策略 | |------|------|---------| | Step 1 | ⭐ | 直接重新执行 | | Step 2 | ⭐⭐ | 删除半成品,重新开始 | | Step 3 | ⭐⭐ | 重新运行提取 | | Step 4 | ⭐⭐⭐ | 验证 state.json 一致性 | | Step 5 | ⭐⭐ | 重新运行 strand 更新 | | Step 6 | ⭐⭐⭐⭐⭐ | 成本高 - 5个检查员 ~$0.15 | | Step 7 | ⭐ | 重新运行 git 备份 |
Step 4: 检测中断状态
python "${CLAUDE_PLUGIN_ROOT}/scripts/workflow_manager.py" detect
输出情况:
- 无中断 → 结束流程,通知用户
- 检测到中断 → 继续 Step 5
Step 5: 展示恢复选项(必须执行)
展示给用户:
- 任务命令和参数
- 中断时间和已过时长
- 已完成步骤
- 当前(中断)步骤
- 剩余步骤
- 恢复选项及风险等级
示例输出:
🔴 检测到中断任务:
任务:/webnovel-write 7
中断位置:Step 2 - 章节内容生成中
已完成:
✅ Step 1: 上下文加载
未完成:
⏸️ Step 2: 章节内容(已写1500字)
⏹️ Step 3-7: 未开始
恢复选项:
A) 删除半成品,从Step 1重新开始(推荐)
B) 回滚到Ch6,放弃Ch7所有进度
请选择(A/B):
Step 6: 执行恢复
选项 A - 删除重来(推荐):
python "${CLAUDE_PLUGIN_ROOT}/scripts/workflow_manager.py" cleanup --chapter {N}
python "${CLAUDE_PLUGIN_ROOT}/scripts/workflow_manager.py" clear
选项 B - Git 回滚:
git reset --hard ch{N-1:04d}
python "${CLAUDE_PLUGIN_ROOT}/scripts/workflow_manager.py" clear
Step 7: 继续任务(可选)
如用户选择立即继续:
/{original_command} {original_args}
特殊场景
Step 6 中断(成本高)
恢复选项:
A) 重新执行双章审查(成本:~$0.15)⚠️
B) 跳过审查,继续下一章(可后续补审)
Step 4 中断(部分状态)
⚠️ state.json 可能部分更新
A) 检查并修复 state.json
B) 回滚到上一章(安全)
长时间中断(>1小时)
⚠️ 中断已超过1小时
上下文丢失风险高
建议重新开始而非续写
禁止事项
- ❌ 智能续写半成品内容
- ❌ 自动选择恢复策略
- ❌ 跳过中断检测
- ❌ 不验证就修复 state.json
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/webnovel-task-resume-mmh8qr0z/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/webnovel-task-resume-mmh8qr0z' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/webnovel-task-resume-mmh8qr0z/download' --output '.skill-downloads/webnovel-task-resume-mmh8qr0z/SKILL.md.part' && mv '.skill-downloads/webnovel-task-resume-mmh8qr0z/SKILL.md.part' '.skill-downloads/webnovel-task-resume-mmh8qr0z/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
Tools declared by the author (check availability in your agent): Read Bash AskUserQuestion
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/webnovel-task-resume-mmh8qr0z/SKILL.md' && test -s '.skill-downloads/webnovel-task-resume-mmh8qr0z/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/webnovel-resume' && cp -R '.skill-downloads/webnovel-task-resume-mmh8qr0z' '.claude/skills/webnovel-resume'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/webnovel-task-resume-mmh8qr0z'openskills read 'webnovel-task-resume-mmh8qr0z'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/webnovel-task-resume-mmh8qr0z/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Writing Fragments
Content
Mine raw writing fragments through a relentless interview, without imposing structure. Capture ideas, quotes, and leading words for later use.
UI Copywriting & Auditing
Content
Write or audit user-facing UI copy including buttons, errors, empty states, and tooltips across the monorepo, following the design system source of truth.
Music MIDI Extraction
Content
Extracts the MIDI or score from an existing music production via the CogMusic MCP tool and confirms availability.