Self-Governor
v1.0.0LLM 通用内部自裁决技能。在关键节点判断"当前这一层最优的下一步动作是什么"，再让主链继续执行。触发条件：(1) 路径分叉时——多个可行方案且无明显优先级；(2) 高代价动作前——搜索/生成/发布等消耗军费或不可逆操作；(3) 连续两步无明显增益时——进展停滞、输出质量未提升。禁止：改写主任务、输出并列动作、长...
⭐ 0· 94·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
Name and description describe an internal decision layer; the SKILL.md, action set, triggers, and I/O all implement exactly that behavior. There are no unrelated env vars, binaries, or config paths requested — the requested capabilities align with the stated purpose.
Instruction Scope
Runtime instructions only describe receiving a small structured input, returning a single action+reason, and expecting the host (main chain) to perform an Update. The skill does not instruct reading arbitrary files, accessing environment variables, or sending data to external endpoints. It does require the main chain to supply Update callbacks to prevent loop-triggering, which is a legitimate integration requirement.
Install Mechanism
This is instruction-only with no install spec and no code files executed at runtime. That is the lowest-risk install profile and matches the declared metadata.
Credentials
No environment variables, credentials, or config paths are required. The skill does not request any secrets or broad access, and the declared inputs are limited and appropriate for the decision role.
Persistence & Privilege
always is false and the skill is user-invocable (normal). Autonomous invocation (disable-model-invocation=false) is the platform default; by itself this is not a problem given the skill's narrow scope. There is no request to modify other skills or system-wide settings.
Assessment
This skill appears coherent and low-risk: it only implements a small decision filter and asks nothing extra. Before installing, verify provenance (no homepage or identifiable author), test it in a safe/staging agent to ensure the host correctly enforces the required Update callback (to avoid loop triggers), and confirm you trust the agent's orchestration logic to enforce the skill's 'must not' rules. If you allow autonomous invocation, monitor logs initially to ensure the skill doesn't get inserted in inappropriate places. If provenance or publisher identity matters to you, ask the publisher for more info or prefer a skill with an auditable source.Like a lobster shell, security has layers — review code before you run it.
latestvk973cj05889hvf1qx3yveac6w183k13q
License
MIT-0
Free to use, modify, and redistribute. No attribution required.