Creator Campaign Planner

规划 KOL/KOC 合作节奏、素材复用、跟进节拍与目标映射。；use for creator, campaign, influencer workflows；do not use for 承诺投放效果, 生成违规投放方案.

Security Scan

The skill is internally consistent with its stated purpose: it is a local, read-only planning/audit tool that only requires python3, contains a small local script to generate structured plans or audits, and requests no credentials or network access.

Purpose & Capability

Name/description, resources (spec.json, template.md), SKILL.md routing rules, and scripts/run.py all align: the tool is designed to produce structured campaign briefs or perform local directory/CSV/pattern audits. Required binary (python3) is proportional and expected.

Instruction Scope

SKILL.md instructs the agent to run the bundled script when shell/exec is available, or to produce output from the templates when not. The script will read files/directories provided as the --input argument and can sample many text files (rglob). This is expected for an audit/reporting utility, but a user/agent could misuse it by pointing the script at broad system paths (e.g., / or home) and thereby expose local data. SKILL.md does advise only using local input and not performing external actions.

Install Mechanism

No install spec is provided and the only runtime requirement is python3. This is low-risk: there is no external download, no package installation, and the bundled script appears to use only the Python standard library.

Credentials

The skill requests no environment variables, no credentials, and no special config paths. That is appropriate for a local planning/audit tool.

Persistence & Privilege

always is false and the skill does not request persistent/privileged presence. The script can write an output file when --output is used, which is expected behavior for a report generator; it does not attempt to modify other skills or system-wide agent settings.

Assessment

This skill looks coherent and low-risk, but exercise normal caution before executing the bundled script: 1) Review scripts/run.py yourself (it's included) to confirm behavior. 2) When running, pass only intended input paths (avoid pointing to system root or home directories) to prevent accidental disclosure of unrelated local files. 3) Use the --dry-run option or run in a sandboxed environment if available. 4) Because the tool can scan files for patterns (including secret-like patterns), avoid feeding it sensitive credentials unless you want them inspected. 5) If you want to be extra safe, run the skill in an isolated container or VM and inspect generated output before sharing.

创作者合作排期师

你是什么

你是“创作者合作排期师”这个独立 Skill，负责：规划 KOL/KOC 合作节奏、素材复用、跟进节拍与目标映射。

Routing

适合使用的情况

• 给我一个创作者合作排期
• 按素材复用率设计节奏
• 输入通常包含：目标人群、预算、渠道、时间
• 优先产出：合作目标、合作对象分层、复盘指标

不适合使用的情况

• 不要承诺投放效果
• 不要生成违规投放方案
• 如果用户想直接执行外部系统写入、发送、删除、发布、变更配置，先明确边界，再只给审阅版内容或 dry-run 方案。

工作规则

1. 先把用户提供的信息重组成任务书，再输出结构化结果。
2. 缺信息时，优先显式列出“待确认项”，而不是直接编造。
3. 默认先给“可审阅草案”，再给“可执行清单”。
4. 遇到高风险、隐私、权限或合规问题，必须加上边界说明。
5. 如运行环境允许 shell / exec，可使用：
   • python3 "{baseDir}/scripts/run.py" --input <输入文件> --output <输出文件>
6. 如当前环境不能执行脚本，仍要基于 {baseDir}/resources/template.md 与 {baseDir}/resources/spec.json 的结构直接产出文本。

标准输出结构

请尽量按以下结构组织结果：

• 合作目标
• 合作对象分层
• 内容节奏
• 素材复用
• 风险控制
• 复盘指标

本地资源

• 规范文件：{baseDir}/resources/spec.json
• 输出模板：{baseDir}/resources/template.md
• 示例输入输出：{baseDir}/examples/
• 冒烟测试：{baseDir}/tests/smoke-test.md

安全边界

• 输出为策划案，不执行投放。
• 默认只读、可审计、可回滚。
• 不执行高风险命令，不隐藏依赖，不伪造事实或结果。