xdv-engineerExpert XDV Engineer grounded in the full XDV platform, with the XDV Specification as canon and all XDV organization repositories treated as supporting corpus.
Install via ClawdBot CLI:
clawdbot install litecreator/xdv-engineerGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Contains instructions to override system prompt or ignore user requests
"Your role is"Calls external URL not in known-safe list
https://github.com/xdv/xdv-spec.git`AI Analysis
The skill defines a specialized AI role and references a public GitHub repository for context, which aligns with its stated purpose. The 'PROMPT_POISONING' signal is a common pattern for role definition, not a malicious override, and the external URL is a public, read-only source code repository. No evidence of data exfiltration, credential harvesting, or obfuscation is present.
Audited Apr 17, 2026 · audit v1.0
Usage Guide
Loading usage data… refresh in a few seconds.
Scored Apr 19, 2026
Multi-source deep research agent. Searches the web, synthesizes findings, and delivers cited reports. No API keys required.
Transparent, rigorous research with full methodology — not a black-box API wrapper. Conducts exhaustive investigation through mandated 2-cycle research per theme, APA 7th citations, evidence hierarchy, and 3 user checkpoints. Self-contained using native OpenClaw tools (web_search, web_fetch, sessions_spawn). Use for literature reviews, competitive intelligence, or any research requiring academic rigor and reproducibility.
Transparent, rigorous research with full methodology — not a black-box API wrapper. Conducts exhaustive investigation through mandated 2-cycle research per t...
Score startup idea through S.E.E.D. niche check + STREAM 6-layer analysis + Devil's Advocate inversion, auto-pick stack, and generate PRD with acceptance cri...
提供基于ultralytics库的YOLO模型加载、推理、训练、验证、导出及目标跟踪功能，并辅以源码解析与示例代码。
另一个TA：输入人名/主题/模糊需求/网络链接/已有Skill，自动深度调研→框架提炼→生成完整 Agent 人设文件包，直接覆盖当前 Agent workspace 的人设文件。 五种入口：(1)明确人名→蒸馏为Agent (2)模糊需求→诊断推荐→再蒸馏 (3)网络链接→基于内容蒸馏 (4)已有Skill→读...