Doc-First
v1.1.0Automatically consult official documentation first to accurately resolve configuration, usage, permission, or error issues with tools and APIs.
⭐ 0· 57·0 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
The name/description (consult official docs first) matches the SKILL.md instructions. The skill requests no binaries, env vars, or installs and only instructs the agent to fetch official documentation (via the web_fetch tool) and validate configs, which is expected for its stated purpose.
Instruction Scope
The instructions direct the agent to use web_fetch to retrieve official docs and to prefer Chinese-language official docs when available. It triggers when working on configs, CLI args, permissions, errors, or openclaw.json/environment-variable changes. The guidance does not explicitly instruct reading arbitrary local files or exporting secrets, but because it triggers around env var and config tasks the agent may request or handle sensitive values when helping the user — that behavior is plausible for the skill but not explicitly declared.
Install Mechanism
No install spec and no code files — instruction-only. This minimizes on-disk persistence and third-party install risk.
Credentials
The skill declares no required environment variables or credentials, which is proportionate. However the SKILL.md explicitly mentions handling environment variables and openclaw.json during troubleshooting; that means the agent may ask for or read configuration values while executing the skill. Users should be aware the skill may interact with sensitive configuration if prompted, even though none are declared.
Persistence & Privilege
always is false and autonomous invocation is allowed (platform default). The skill does not request permanent presence, nor does it include installation steps that modify other skills or system settings.
Assessment
This skill is coherent and low-risk because it only contains instructions to consult official documentation and has no installs or required credentials. However: (1) it relies on the agent's ability to fetch web pages (network access), so verify the agent's web_fetch tool and network policies before enabling; (2) the skill may prompt for or handle configuration values, including sensitive environment variables or openclaw.json contents — avoid pasting secrets into chat unless you trust the agent and session; (3) check that fetched links are official domains listed in the SKILL.md and be cautious if the agent suggests resources from unknown or personal servers; (4) note the preference for Chinese-language docs which can affect results. If you want to be extra cautious, disable autonomous invocation for this skill or limit the agent's web access until you confirm behavior.Like a lobster shell, security has layers — review code before you run it.
developer-toolsvk97a20p2rtt6xy08kgn09cbk8n84p0rnlatestvk979pmeknb5hktc2d51jaj96mh84p7xqopenclawvk97a20p2rtt6xy08kgn09cbk8n84p0rnproductivityvk97a20p2rtt6xy08kgn09cbk8n84p0rn
License
MIT-0
Free to use, modify, and redistribute. No attribution required.