技能 写作

文档 社区
解读按原文结构重写,命令、链接、术语均保留;右侧可核对作者原始 SKILL.md

方法与流程

  • Core Workflow References:Open when you need to... · Read choose the minimum workflow path for create, update, iterate, or research-first work · references/mode-selection.md choose the simplest adequate execution shape before deciding files · references/execution-shapes.md
  • Workflow Mechanic References:Open when you need to... · Read break a task into fixed ordered steps · references/workflow-prompt-chaining.md classify requests and route them to different downstream paths · references/workflow-routing.md
  • Step 1: Resolve target, path, and shape:Resolve the intended operation (create, update, synthesize, iterate) and inspect workspace prior art before choosing where files belong. Choose the target skill root from observed conventions. If the canonical location is still unclear after inspection, ask…

适用与边界

  • 当前原文没有单列适用场景。
  • Step 5: Optimize description quality:Read references/description-optimization.md. Validate should-trigger and should-not-trigger query sets. Reduce false positives and false negatives with targeted description edits.

原文中的明确线索

  • 要点:「Use this as the single canonical workflow for skill creation and improvement.」、「Follow the workflow steps in order.」、「| Open when you need to...」、「1. Resolve the intended operation (create, update, synthesize, iterate) and inspect workspace prior art before choosing where files belong.」、「Read references/synthesis-path.md.」、「1. Use this path for new skills, material changes, and research-first planning.」、「Read references/iteration-path.md first when selected path includes iteration (for example operation iterate).」、「1. Capture and anonymize examples with provenance.」
  • 文件与命令references/references/mode-selection.mdreferences/execution-shapes.mdreferences/design-principles.mdSPEC.mdreferences/reference-architecture.mdreferences/spec-template.mdreferences/source-discovery.md

流狐整理:以上内容来自当前 SKILL.md 的章节与原词;未补写作者没有声明的工具、兼容性或能力。

流狐档案 作者与许可取自来源;运行、权限和网络为流狐检测或估算
流狐分类
文档
作者声明 Agent
未找到明确声明;不据此推断已兼容或已测试
静态检查
88 / 100 · 启发式扫描,不代表运行安全
作者 / 版本 / 许可
@getsentry · 未声明 license
流狐 Token 估算
中等消耗
流狐接入估算
需简单配置
是否需要外部 API Key
未发现要求
检测到的系统要求
未声明
底层运行要求
未声明
检测到的文件与系统行为
  • 只读
  • 允许写入 / 修改
  • Shell 执行
检测到的网络行为
仅限本地
安装命令数
无(仅作为资料)

档案由构建时根据 SKILL.md 与安装命令自动衍生,可能与作者实际意图存在差异。

需要注意: 未限定 allowed-tools,默认拥有全部工具权限。

输出预览 skill-writer-getsentry.preview
# Step 3: Run iteration first when improving from outcomes/examples

1. Capture and anonymize examples with provenance.
2. Read `references/iteration-evidence.md` when examples should persist beyond the current turn.
3. Review skill behavior against working and holdout slices.
4. Propose improvements from positive/negative/fix evidence.
5. Carry concrete behavior deltas into authoring.

讨论

基于 GitHub Discussions。登录 GitHub 即可参与讨论、点赞、订阅更新。