Topic Planner Agent
v1.0.0选题策划智能体。当需要生成小说选题、评估市场机会、设计卖点钩子、制定创作约束时触发本技能。用于：(1) 基于市场洞察师的数据生成备选选题 (2) 对选题进行多维度评分和ROI估算 (3) 设计核心卖点、开篇钩子、节奏大纲 (4) 输出标准选题策划文档给小说创作师 (5) 竞品对标分析和差异化定位
⭐ 0· 66·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name/description (novel topic planning, scoring, sell-point design, multi-platform adaptation) matches the SKILL.md content: scoring model, templates, output format, workflow and constraints. No unrelated capabilities (cloud access, system administration, or unrelated APIs) are requested.
Instruction Scope
Runtime instructions are limited to generating topic ideas, scoring against listed dimensions, producing planning documents, and interacting with other agent roles (market-insights, creator, overseer). The skill does not instruct the agent to read local files, environment variables, or send data to external endpoints beyond normal message passing with other agents.
Install Mechanism
Instruction-only skill with no install spec, no code files, and no downloads — lowest-risk install posture. Regex scanner had nothing to analyze, which is expected for an instruction-only skill.
Credentials
Requires no environment variables, credentials, or config paths. The SKILL.md references consuming market-insights data (from another agent) — this is proportional to the described purpose and does not imply excess credential access.
Persistence & Privilege
Flags show always:false and default autonomous invocation allowed — appropriate for a user-invocable planning skill. The skill does not request persistent system-level presence or modification of other skills' configs.
Assessment
This skill appears coherent and safe in terms of requested access. Before installing, confirm the source/trustworthiness of the market-insights data the skill will consume (avoid supplying PII or sensitive commercial secrets), test the agent on non-sensitive example reports, and verify any outputs (ROI estimates, legal/content boundaries) with a human reviewer before acting on them. Also ensure the skill is not granted extra platform permissions or credentials later — the current package does not request any.Like a lobster shell, security has layers — review code before you run it.
latestvk97f2t43ys7hywm36a95j28b31843xrg
License
MIT-0
Free to use, modify, and redistribute. No attribution required.