Success Plan Generator
v1.0.0为 B2B 客户生成成功计划，绑定里程碑、可验证结果与复盘节奏。；use for success-plan, customer-success, b2b workflows；do not use for 承诺合同外服务, 替代正式项目计划.
⭐ 0· 91·0 current·0 all-time
byvx：17605205782@52yuanchangxing
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (success plan generator) match the included resources: templates, spec.json, examples, and a local Python script that produces structured Markdown reports. The only required binary is python3, which is reasonable for a Python script. There are no unrelated credentials, binaries, or install steps.
Instruction Scope
SKILL.md limits behavior to producing reviewable success-plan drafts and explicitly says not to perform external system changes. It offers an optional local execution step: python3 scripts/run.py --input <...>. The script will read files/directories provided as input and can also scan directories for file lists, headings, CSVs, and pattern matches. That behavior is coherent for auditing or assembling inputs, but it means if the agent (or user) runs the script against broad system paths (e.g., / or home), it will read many files. The skill does not request broad system credentials, but you should avoid pointing it at sensitive system directories or repositories you do not want inspected.
Install Mechanism
Instruction-only + bundled local Python script; no install spec and no external downloads. This is low-risk: nothing is fetched from the network, and the script uses only the standard library per README/SELF_CHECK.
Credentials
No environment variables, credentials, or external config paths are required. The script reads local files only; it does not embed any hardcoded tokens or remote endpoints. The regex-based pattern detector in the script searches for secret-like patterns but also tries to partially redact those matches.
Persistence & Privilege
Skill is user-invocable and not always-on. It does not attempt to modify other skills or global agent settings. The bundled script may write output files when given an --output path (normal behavior) but does not persist configuration or enable itself.
Assessment
This skill appears to do what it says: generate reviewable success-plan drafts from templates or input files. Safe practices before using it: (1) Prefer to run the script only on the specific input files/directories containing customer materials, not on root or system directories — the script will traverse and read many file types and could surface sensitive snippets. (2) Do not supply unredacted sensitive credentials or PII as input; the tool is designed for non-sensitive planning material. (3) If you cannot or do not want to execute the local script, you can still use the SKILL.md and resources/template.md to produce outputs manually. (4) Review any generated output before sharing with customers. If you want a stricter audit, provide the full run.py output or confirm whether you plan to run the script against arbitrary directories so I can assess potential data-exposure risk further.Like a lobster shell, security has layers — review code before you run it.
latestvk978mrqrnkfv7zm5jyx3btz7qh8389dh
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🎛️ Clawdis
OSmacOS · Linux · Windows
Binspython3