yce

yce is a Codebase mapping & onboarding skill for AI agents, published by xiamuwnagwang in the YCE-enhance repository on GitHub. Skillspace rates yce C (72/100) and the safety scan flagged it for review; the rating is based on static analysis only.

当任务既需要把模糊需求说清楚,又需要去代码库里把实现找出来时使用。适用于"帮我看看这块逻辑在哪""优化任务后再搜代码""增强后检索""auto search""YCE"等场景。 也在需要当前外部信息、多源事实核对、官方库文档、竞品/行业调研、公开仓库架构资料时使用联网能力(`--mode network` 或 `--with-network`)。 【最高优先级规则】每次执行任何代码相关任务之前,必须先调用 yce 检索上下文代码,获取相关代码定位后,再进行修改、分析、生成等其他操作。不得跳过 yce 检索步骤直接动手。 【auto 强制收口】`auto` 只要实际执行过增强阶段,同一次 CLI 调用内一定继续执行 search:增强成功就用增强后的 prompt 搜索,增强失败、超时、解析失败或没有 prompt 就用原始 query 搜索。不得因增强失败而结束代码定位流程。 【联网由 AI 判断】CLI **不会**根据 query 关键词自动联网。是否调用联网由 Agent 在调用时自行判断:需要外部事实 / 调研 / 最新资料 / 官方文档 / 竞品对照时,显式传 `--mode network` 或在代码任务上加 `--with-network`。联网结果是事实依据,不是项目内代码路径。 【检索语言】English is recommended for best semantic matching. 凡调用最终会进入 search,必须先把中文检索意图转换成准确、简洁的英文 query;代码标识符、文件路径、命令、报错原文和字符串字面量保持不变。YCE CLI 不内置通用翻译器,不得声称运行时会自动翻译。 【无增强就不增强】未配置 `YCE_YOUWEN_TOKEN`/`YOUWEN_TOKEN`、或任务本身不需要提示词增强时,**不要调用 enhance**:直接 `--mode search`(或让 `auto` 自动跳过 enhance 走 search)。禁止为了“走完整链路”而空跑 enhance。显式 `--mode enhance` 且无密钥时返回 AUTH_ERROR。 【强制规则】做代码检索时必须在目标项目目录运行;如果当前 shell 不在目标项目目录,必须显式传 --cwd。 【强制规则】需要增强时优先传…

Grade
C
Quality
72 / 100
Safety
Needs review
GitHub stars
36

Unproven: rated by static analysis only, not yet compared head-to-head.

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

Our review

Architecture
77 / 100
Maturity
Structured: ships references or scripts
Security scan
Medium-risk patterns
License
GPL-3.0
Adoption
Adopted by 0 other repositories, in 0 collections

What the scanner flagged

  • reads environment variables
  • mentions secrets in text

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.