Scenario First Thinking
v2.0.0场景路由 + 8工具直接执行。将 TaskType → 场景 → 工具序列的映射固化到 SKILL.md 内部，无需外链文件即可执行。HEARTBEAT.md 中的路由规则已迁移至此，统一作为技能触发入口。
⭐ 0· 120·2 current·2 all-time
byWH laowu@wukaifeng704-cell
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 (scenario routing + 8 thinking tools) matches the SKILL.md content. There are no unrelated env vars, binaries, or install steps requested that would be disproportionate to a decision-routing/thinking skill.
Instruction Scope
SKILL.md contains only guidance for classifying tasks into six scenarios and running the embedded 8-step tools; it explicitly claims to be self-contained and does not instruct reading files, credentials, or sending data to external endpoints. It does reference integration targets conceptually (e.g., Memory_Bus, Layout_Editor, render flow), which is expected for a routing/pipework skill but does not itself contain instructions to access secrets or external URLs.
Install Mechanism
No install spec and no code files to execute — instruction-only. This is lowest-risk from an install perspective.
Credentials
The skill requests no environment variables, credentials, or config paths. All required inputs are task text and internal decision logic, so requested privileges are proportionate.
Persistence & Privilege
Defaults are used (always:false, agent invocation allowed). The skill does not request permanent presence or modifications to other skills' configs. Autonomous invocation is enabled (platform default) but not combined with other red flags.
Assessment
This skill appears coherent and low-risk: it is an instruction-only, self-contained decision-routing framework and does not ask for secrets or to install code. Before installing, consider: (1) test it with non-sensitive sample tasks to confirm its routing behavior; (2) review how your agent/framework implements Memory_Bus / Layout_Editor / render flows (the SKILL.md expects outputs to be handed to those components), since those integration points could affect where data goes; (3) if you want to restrict autonomous invocation, disable model invocation or control when the skill is allowed to run. If you need higher assurance, inspect runtime logs to confirm the skill never calls external endpoints or reads files in your environment.Like a lobster shell, security has layers — review code before you run it.
latestvk971he9d7ga3k2ha7zz1kshbj983xajt
License
MIT-0
Free to use, modify, and redistribute. No attribution required.