This consolidates multiple diagnostic snapshots from dbs-save into a single markdown report you can send to stakeholders. It reads timestamped files from ~/.dbs/sessions/, merges conclusions, tracks how the core question evolved, and lists rejected directions so you don't retread old ground. The output is deliberately archival: no AI summarization, just structured extraction from saved snapshots with timestamps and source attribution. Useful when you've run several diagnostic sessions over weeks and need something you can email to a cofounder or review three months later. The report never overwrites previous versions, so you get a history of how your understanding changed. Triggers with /dbs-report or just ask it to package things up.

skills.sh installs
26.7K
GitHub stars
11.4K
last updated
Aug 21, 2026

Install

$ npx -y skills add dontbesilent2025/dbskill --skill dbs-report --agent claude-code

Installs into .claude/skills of the current project.

Files

dbs-report:诊断报告

你是 dbskill 的报告产物工具。你的工作是:把 dbs-save 留下的多份存档文件合并成一份可读、可分享、可归档的诊断报告。

报告内容必须来自 {存档根目录}/sessions/{项目名}/ 下的存档文件。按时间顺序合并、去重、分类,保证每条内容都能追溯到用户已经确认过的状态。


为什么需要报告

诊断结论现在漂在聊天里。客户想发给合伙人、想三周后回顾、想跟外部顾问对账,都得自己截图复制。

报告把累积的存档固化成一份带日期、带版本、带索引的 markdown 文档。这是 dbskill 从「单次工具」升级到「可交付咨询」的产物。


触发方式

命令行为
/dbs-report把当前项目下所有存档合并成报告
/dbs-report --since YYYY-MM-DD只合并某日期之后的存档
/dbs-report --slug <项目名>指定项目
/dbs-report --slug <项目名> --since YYYY-MM-DD同时指定
「出报告」「打包」「整理一份」「给合伙人看的」等价于 /dbs-report

存档契约

措辞、项目名、存档根目录、文件名和存档格式统一按 references/archive-contract.md 执行。这份存档契约与保存、恢复、报告三个存档能力共用,内容一致。

本 Skill 只读取配置,不修改配置。配置有问题时停止生成报告并说明原因;用户要查看或调整位置时,引导使用 /dbs-save location。

后文中的 {存档根目录} 都指按契约第 3 节解析出的绝对路径。


工作流程

Step 1:确认有数据可合并

按项目找 {存档根目录}/sessions/{项目名}/*.md。

  • 0 个文件 → 「{项目名} 下还没有可汇总的存档。输入 /dbs 开始处理真实任务;形成结论并明确保存后,再回来生成报告。」
  • 1 个文件 → 提示:「{项目名} 下只有 1 份存档,单份不需要合并报告。直接看 {存档根目录}/sessions/{项目名}/{文件名} 就行。」并询问「还是要强制出报告吗?」如果用户说要,继续。
  • ≥2 个文件 → 直接进入合并

如果带了 --since,先按日期过滤。过滤后剩下的文件如果不到 2 份,按上面同样处理。

Step 2:读取并解析所有存档

按文件名 YYYYMMDD-HHMMSS 排序(早 → 晚)。

Sponsors

Details

Repository
github.com/dontbesilent2025/dbskill
First seen
May 16, 2026

More from dontbesilent2025/dbskill

All 30

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs