Problem Mapper
v2.0.0［何时使用］当用户需要系统化定义问题、设定成功标准、识别风险时；当用户说"帮我分析这个问题"时；当面临重大决策/战略模糊/复杂情境时；当需要将模糊问题转化为清晰行动时；支持两种模式（多轮对话/问题瀑布）
⭐ 0· 95·1 current·1 all-time
by@lj22503
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Benign
high confidencePurpose & Capability
Name, description, examples and templates all describe structured problem diagnosis and decision framing; the skill requires no binaries, credentials or config paths—nothing requested is disproportionate to the stated purpose.
Instruction Scope
SKILL.md is a comprehensive set of templates and prompts guiding either a one-shot 'waterfall' report or multi-turn guided dialogue. The instructions do not ask the agent to read or exfiltrate unrelated system files or environment variables. It includes features to 'export Markdown' and references Read/Write/Bash allowed-tools (for saving/exporting reports); consider that Bash access could be used to run shell commands if the agent is granted that tool at runtime, though the skill's texts themselves do not require arbitrary shell access.
Install Mechanism
No install spec and no code files — instruction-only — so nothing is downloaded or written by an installer.
Credentials
The skill requests no environment variables, no credentials, and no config path access. All templates and references are local to the skill bundle and consistent with its function.
Persistence & Privilege
Registry flags are default (always:false, agent invocation allowed). SKILL.md contains a 'self_improvement: true' metadata field which is ambiguous in practice for an instruction-only skill; there is no install-time behavior that persists or escalates privileges. If the platform allows autonomous tool use, combined with allowed-tools (Bash/Read/Write), that grants the agent ability to write/export files — expected for exporting reports but worth reviewing in your agent's runtime policy.
Assessment
This skill appears coherent and self-contained: it only provides templates and prompt instructions for structured problem analysis and requests no secrets or installs. Before enabling it, consider two practical precautions: (1) confirm whether your agent runtime will grant it Bash/Write permissions — if you don't need file export, disallow Bash/Write to reduce risk; (2) avoid entering highly sensitive personal or corporate secrets into the interactive sessions (career offers, financial account details, proprietary IP), since the skill will produce and may write reports. The ambiguous 'self_improvement: true' flag in the SKILL.md is likely informational; if you need higher assurance, ask the publisher how that flag is used or run the skill in a restricted environment first.Like a lobster shell, security has layers — review code before you run it.
analysisvk9791agqt0gg5n660qdx38h4q984z5mcdecisionvk9791agqt0gg5n660qdx38h4q984z5mcframeworkvk9791agqt0gg5n660qdx38h4q984z5mclatestvk9791agqt0gg5n660qdx38h4q984z5mcproblemvk9791agqt0gg5n660qdx38h4q984z5mc
License
MIT-0
Free to use, modify, and redistribute. No attribution required.