跳到正文
cccskills
免费在 GitHub 公开

deepchat-data-import

Help developers build third-party tools that import, inspect, migrate, or analyze DeepChat data. Use when Codex needs to work with DeepChat provider configuration, model configuration, MCP/app settings, sessions, messages, legacy chat data, `agent.db`, `chat.db`, SQLCipher encrypted SQLite, Electron safeStorage wrapped passwords, Tauri importers, or native macOS/Windows/Linux data access.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(6)

  • SKILL.md2.9 KB
  • agents/openai.yaml280 B
  • references/data-locations.md2.5 KB
  • references/import-recipes.md4.5 KB
  • references/schema-reference.md7.6 KB
  • references/sqlite-access.md4.8 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

DeepChat Data Import

Overview

Use this skill to design or implement importers for DeepChat local data. Treat DeepChat's SQLite schema as an internal but documentable contract: inspect the current schema when precision matters, prefer read-only snapshots, and avoid writing to a live profile.

Workflow

  1. Identify the source: live DeepChat profile, copied profile, sync backup, exported agent.db, or legacy chat.db.
  2. Read references/data-locations.md to locate agent.db, sidecar files, encryption metadata, and backup paths.
  3. Read references/sqlite-access.md before opening SQLite. Decide whether the database is unencrypted, can be unlocked through Electron safeStorage, or must ask the user for the SQLite password.
  4. Read references/schema-reference.md for provider config, settings, session, message, and legacy table relationships.
  5. Read references/import-recipes.md when writing extractor code, mapping DeepChat data to another app, or creating a compatibility import.

Safety Rules

  • Get explicit user consent before reading local DeepChat data. Provider keys, OAuth tokens, MCP env vars, prompt text, message traces, and chat content may be sensitive.
  • Never open the active agent.db read-write from a third-party tool. Copy agent.db, agent.db-wal, and agent.db-shm, or use SQLite backup APIs through DeepChat itself.
  • If DeepChat is running, either ask the user to quit it or make a WAL-aware snapshot before import.
  • Prefer parameterized key APIs for SQLCipher passwords. Do not interpolate passwords into SQL.
  • Redact secrets by default in logs, telemetry, previews, and generated sample output.
  • When the schema has changed, inspect schema_versions, sqlite_master, and the table classes under src/main/presenter/sqlitePresenter/tables/ before assuming column availability.

Source Files

Use these repository files as the current source of truth when updating the skill or answering version-sensitive questions:

  • src/main/presenter/sqlitePresenter/index.ts
  • src/main/presenter/sqlitePresenter/connectionConfig.ts
  • src/main/presenter/databaseSecurityPresenter/index.ts
  • src/main/presenter/sqlitePresenter/tables/*.ts
  • src/main/presenter/agentRuntimePresenter/messageStore.ts
  • src/main/presenter/agentRuntimePresenter/sessionStore.ts
  • src/main/presenter/configPresenter/**

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Add a DeepChat LLM provider through explicit reviewed source changes. Use when a developer asks Codex to add a provider, provider profile, upstream provider config, model catalog mapping, provider auth behavior, or a special provider adapter in this repository.

中文简介正在准备中。当前显示原文说明。

ThinkInAIXYZ/deepchat63702026年10月13日 更新

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

中文简介正在准备中。当前显示原文说明。

ThinkInAIXYZ/deepchat63702026年10月13日 更新

Comprehensive code review assistant that analyzes code quality, security, and best practices

中文简介正在准备中。当前显示原文说明。

ThinkInAIXYZ/deepchat63702026年10月13日 更新

Drive native desktop apps through DeepChat's built-in Computer Use tools. Use when the user asks to operate, inspect, automate, or perform a GUI task in a real desktop application.

中文简介正在准备中。当前显示原文说明。

ThinkInAIXYZ/deepchat63702026年10月13日 更新

Use DeepChat's bundled CLI control plane for model inference, image/video/speech generation, transcription, OCR, artifact inspection, public configuration, Skills, and MCP operations. Activate when a user asks to invoke DeepChat capabilities that are not already exposed as a more specific tool, compare models, run a benchmark, inspect DeepChat runtime state, or manage DeepChat through the CLI.

中文简介正在准备中。当前显示原文说明。

ThinkInAIXYZ/deepchat63702026年10月13日 更新

Prepare and publish DeepChat releases in this repository. Use when Codex needs to bump the app version, update CHANGELOG.md, keep release notes bilingual from v1.0.1 onward with English bullets first and Chinese bullets second, run release checks, create or update versioned release branches such as release/v1.0.1, continue a half-finished release, fast-forward main with the documented release flow, create or push version tags, or clean up release branches after publishing.

中文简介正在准备中。当前显示原文说明。

ThinkInAIXYZ/deepchat63702026年10月13日 更新

查看 ThinkInAIXYZ 的全部技能

报告此技能的问题