菜单
Common mistake — stating specific facts (API endpoints, library versions, config options, function signatures) with false confidence when uncertain. Always flag uncertainty rather than guessing specifics.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | avoid-hallucinating-specifics |
| description | Common mistake — stating specific facts (API endpoints, library versions, config options, function signatures) with false confidence when uncertain. Always flag uncertainty rather than guessing specifics. |
| category | common_mistakes |
High-risk categories for hallucination:
Prevention:
<version> or <your-endpoint> as placeholders rather than guessing.Anti-pattern: Confidently stating a URL or function signature that sounds right but does not exist.
Use this skill when delegating a subtask to a sub-agent, spawning a parallel worker, or handing off work across sessions. Write a self-contained task description so the receiving agent needs no prior context.
Use this skill when writing messages in async channels (Slack, GitHub issues, email threads) where the reader may not have context and cannot ask follow-up questions immediately.
Use this skill when writing any explanation, documentation, or response that will be read by someone else. Match vocabulary, depth, and format to the audience's expertise level before writing.
Use this skill when implementing authentication (login, token issuance) or authorization (access control, permissions). Apply whenever the task involves login flows, JWT, OAuth2, session management, or RBAC.
Common mistake — proceeding with assumptions about ambiguous requirements instead of asking a clarifying question first. This skill reminds you to stop and ask before acting on uncertain interpretations.
Common mistake — doing unrequested work (refactoring, adding extra features, cleaning up style) when the user asked for a specific, targeted change. Only change what was explicitly asked.