prompt-architect
v1.0.0Use this skill whenever the user wants to create, design, improve, debug, or evaluate prompts or AI workflows. Triggers include: vague ideas like "I want an...
⭐ 0· 52·0 current·0 all-time
by@jzw6
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name and description match the SKILL.md: the document is a detailed guide for designing, improving, and diagnosing prompts and multi-step agent workflows. Nothing in the skill requests unrelated credentials, system access, or binaries that would be inconsistent with a prompt-architect role.
Instruction Scope
All runtime instructions are about asking clarifying questions, producing structured system prompts, few-shot examples, Mermaid diagrams, and self-checklists. The skill does not instruct the agent to read local files, environment variables, or send data to arbitrary external endpoints. It does encourage systematic probing and use of defaults, which grants operational discretion but is consistent with the stated purpose.
Install Mechanism
No install spec or code files are provided; this is instruction-only and will not write files or pull external packages during install. This is the lowest-risk pattern for skills.
Credentials
The skill declares no required environment variables, credentials, or config paths. The SKILL.md does not request secrets or access to external accounts. No disproportionate credential requests were found.
Persistence & Privilege
The registry flags are normal (always:false, user-invocable:true, autonomous invocation allowed). The SKILL.md itself states "Always use this skill — even for seemingly simple requests," which is an author instruction encouraging frequent use; although not a metadata "always:true" flag, it could lead to frequent autonomous invocation if the agent follows skill-selection heuristics. This is a behavioral note rather than a technical discrepancy.
Assessment
What to consider before installing: this skill is an instruction-only prompt/architecture guide and does not ask for credentials or install code, so it's low technical risk. However, the SKILL.md explicitly endorses always applying the skill and asking many follow-ups — that will change how often your agent invokes it and how chat interactions proceed. Because the source/homepage are not provided, consider whether you trust the skill author and review a few outputs manually before using suggestions in production (especially for safety-critical domains like medical, legal, or finance). If you want to limit automatic invocation, keep it user-invocable only or review agent-selection rules. Avoid pasting sensitive secrets into prompts the skill asks you to craft.Like a lobster shell, security has layers — review code before you run it.
latestvk9718d2wyp6b69dqpvnkfx4j8x83qk0c
License
MIT-0
Free to use, modify, and redistribute. No attribution required.