Writing Reboot Review
v0.1.0帮助用户做写作复盘、内容定位梳理和写作重启规划。通过结构化深度对话识别断更或写不下去的真实原因，澄清继续写作想获得的收益，提炼适合长期输出的独特价值，并产出明确的目标读者、内容方向和可执行的重启建议。Use when users ask for 写作复盘、写作定位、内容定位、写作方向梳理、深度写作对话，或提到断更...
⭐ 0· 181·0 current·0 all-time
byAllen Chen@cr330326
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name and description (writing reboot / content positioning) align with the SKILL.md: the file contains a step-by-step conversational workflow to identify causes of interruption, clarify goals, and produce concrete restart suggestions. No unrelated capabilities or resource requests are present.
Instruction Scope
Runtime instructions are limited to guided dialogue, clarifying questions, and producing a structured output. The workflow does not instruct the agent to read local files, environment variables, or send data to external endpoints, and it explicitly forbids fabricating user experiences.
Install Mechanism
No install spec and no code files — instruction-only skill. Nothing will be downloaded or written to disk as part of installing this skill.
Credentials
The skill declares no required environment variables, credentials, or config paths. Its needs are proportionate to a purely conversational assistance task.
Persistence & Privilege
always is false and the skill does not request elevated or persistent system presence. Autonomous invocation is enabled by default on the platform, which is expected and not by itself a concern here.
Assessment
This skill is internally consistent and appears safe to add: it only contains conversation instructions and asks no credentials or installs. Before using, remember it will prompt you for personal writing experiences and motivations — avoid sharing passwords, private documents, or other sensitive secrets in the chat. If you want the agent to reference files (drafts, analytics), prefer pasting only the necessary excerpts or use a separate, explicit integration that you trust. Finally, review any concrete advice the agent gives before acting on it (e.g., publication or monetization steps) — the skill structures the conversation but does not validate external outcomes.Like a lobster shell, security has layers — review code before you run it.
content positioningvk9785b5knkd8h3bpxbyq6sqn6n82tgczlatestvk9785b5knkd8h3bpxbyq6sqn6n82tgczwriting reviewvk9785b5knkd8h3bpxbyq6sqn6n82tgcz
License
MIT-0
Free to use, modify, and redistribute. No attribution required.