求是skill
v1.0.0求是 OpenClaw Skills 是基于毛泽东思想方法论的 AI Agent 技能集合，按照 OpenClaw 技能格式进行改造，旨在为 AI 提供系统化的思考和行动框架。
⭐ 3· 409·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (methodology toolkit) match the contents: the package is a set of SKILL.md/README templates implementing analytical workflows. There are no unexpected required binaries, env vars, or config paths.
Instruction Scope
SKILL.md files give stepwise procedures and mapping between skills; they instruct the agent to call other internal skills where appropriate. They do not reference external endpoints, secrets, or unrelated system files. Note: the 'arming-thought' skill's description says it is invoked 'on each new top-level dialogue' — that is a behavioral intent expressed in docs (not an enforced install-time privilege) and relies on the host platform's trigger logic.
Install Mechanism
Instruction-only skill set with no install spec or bundled code to execute; low install risk. README mentions 'clawhub install' purely as user-facing documentation; no network downloads or extract steps are present in the package.
Credentials
No environment variables, credentials, or config paths are required in any clawhub.json or SKILL.md files. The skill does not ask for secrets or unrelated service access.
Persistence & Privilege
Package flags are default (always: false, agent invocation allowed). The only potential concern is behavioral: 'arming-thought' states it should run at the start of top-level dialogues — that describes an intended automatic trigger but does not itself grant system-level persistence. If you do not want a methodology skill to run automatically, verify how your host decides auto-triggering and/or disable autonomous invocation in the platform.
Assessment
This package is internally consistent and low-risk: it is a set of textual skill templates that request no credentials or external installs. Before installing, verify the source (repository/owner) because the top-level source is marked unknown; decide whether you are comfortable with a methodology/ideology influencing agent behavior; check your OpenClaw host's auto-triggering rules (the 'arming-thought' skill documents an automatic invocation intent) and, if undesired, disable autonomous invocation or adjust triggers. If you need stronger assurance, ask the author for a canonical repository URL or review the author’s public repo mentioned in per-skill metadata.Like a lobster shell, security has layers — review code before you run it.
latestvk973cqs41qge6w1cnh2f7xpt5184ezt4
License
MIT-0
Free to use, modify, and redistribute. No attribution required.