feat(skills): gloss each mode word in the slash picker description

.agents/skills/euthyna-en/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: euthyna-en
-description: 'The adjudication discipline and delivery gate for code security audits. Use when the user asks to audit the security of a piece of code, a pull request, a change, or to verify an existing vulnerability claim. It does three things: supply the deterministic facts a model cannot compute (callers, test coverage, git history origins), judge every claim against six gates, and downgrade any claim that cannot produce evidence to "observation" rather than a finding. The slash command may carry a mode word — pr / graph / repo / claim / gate / help — to narrow the run to a single entry (the mapping lives in the mode table in the body); with no mode word the full audit runs. Not for: asking about the details of a single CVE, running an existing scanner once, pure documentation or formatting changes, or when the user explicitly wants a quick summary and accepts the risk.'
+description: 'The adjudication discipline and delivery gate for code security audits. Use when the user asks to audit the security of a piece of code, a pull request, a change, or to verify an existing vulnerability claim. It does three things: supply the deterministic facts a model cannot compute (callers, test coverage, git history origins), judge every claim against six gates, and downgrade any claim that cannot produce evidence to "observation" rather than a finding. The slash command may carry a mode word: pr = audit a change; graph = draw the provenance lineage of deleted code; repo = dependency surface only; claim = verify an existing vulnerability conclusion; gate = check an already-written report; help = print this table. With no mode word the full audit runs (the mapping table lives in the body). Not for: asking about the details of a single CVE, running an existing scanner once, pure documentation or formatting changes, or when the user explicitly wants a quick summary and accepts the risk.'
 whenToUse: Use when the user asks to audit the security surface of code or a repository, verify whether a suspected vulnerability is real, decide whether a finding is exploitable, review whether a change introduces a security regression, or asks to "audit before delivery". For single-topic checks such as only searching for secrets or only checking dependency versions, use the dedicated specialist skill instead and do not trigger this one.
 disable-model-invocation: true
 user-invocable: true

.agents/skills/euthyna/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: euthyna
-description: 代码安全审计的判定纪律与交付门禁。当用户要求对一段代码、一个 PR、一次变更或一条已有的漏洞结论做安全审查与验证时使用。它做三件事：补上模型算不准的确定性事实（调用方、测试覆盖、git 历史来源），用 6 道门禁判定每条结论真假，拿不出证据的一律降级为「观察」而不是「发现」。斜杠命令可带模式词 pr / graph / repo / claim / gate / help，把本次运行收窄到单个入口（映射见正文「模式词」表）；不带模式词则走完整审计流程。不适用于：仅询问某个 CVE 的详情、仅要求跑一次现成扫描器、纯文档或格式化改动、以及用户只要一句快速摘要且明确接受风险时。
+description: 代码安全审计的判定纪律与交付门禁。当用户要求对一段代码、一个 PR、一次变更或一条已有的漏洞结论做安全审查与验证时使用。它做三件事：补上模型算不准的确定性事实（调用方、测试覆盖、git 历史来源），用 6 道门禁判定每条结论真假，拿不出证据的一律降级为「观察」而不是「发现」。斜杠命令可带模式词：pr=审计一次变更；graph=画出被删代码的来源谱系；repo=只查依赖面；claim=验证一条已有的漏洞结论；gate=校验一份审计报告；help=打印这张表。不带模式词则走完整审计流程（映射表见正文）。不适用于：仅询问某个 CVE 的详情、仅要求跑一次现成扫描器、纯文档或格式化改动、以及用户只要一句快速摘要且明确接受风险时。
 whenToUse: 用户要求审计代码或仓库的安全面、验证一条疑似漏洞结论真假、判定某个发现是否可利用、审查一次变更是否引入安全回归，或要求「审完再交付」时使用。只查密钥、只查依赖版本这类单一主题，直接用对应专项技能，不要触发本技能。
 disable-model-invocation: true
 user-invocable: true