CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

73

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

80%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-structured orchestrator: concise, with clean progressive disclosure to four real reference files and concrete safety rules. Its main gap is workflow clarity — a database/import skill should embed explicit validation checkpoints (e.g., verify snapshot integrity, confirm DB unlocks) as workflow steps rather than only stating precautions in a separate Safety Rules section.

Suggestions

Add explicit validation checkpoints to the Workflow (e.g., after copying agent.db, verify the copy opens read-only before proceeding; confirm the password unlocks the DB before reading schema), turning Safety Rules into embedded validate-then-proceed steps.

Include one small inline executable snippet (e.g., the SQLCipher open command or a parameterized key API call) in the body or import-recipes reference so the most common access path is copy-paste ready.

Add a brief feedback-loop note for schema drift (e.g., 'If sqlite_master differs from schema-reference.md, re-read schema_versions and update mappings before importing').

DimensionReasoningScore

Conciseness

Lean body with no padding about what SQLite or DeepChat is; every section (Overview, Workflow, Safety Rules, Source Files) earns its tokens and assumes Claude's competence, matching the lean-and-efficient anchor.

5 / 5

Actionability

Concrete navigation — each workflow step names the exact reference file to read, and Safety Rules cite specific files (agent.db, agent.db-wal, agent.db-shm) — but no copy-paste code lives in the body itself (executable recipes are delegated to import-recipes.md), so it is mostly rather than fully executable.

4 / 5

Workflow Clarity

The 5-step sequence is clear but the workflow involves database operations with no explicit validation checkpoints or feedback loops in the sequence itself; safety guidance exists in a separate section rather than as embedded validate-then-proceed steps, so the destructive/batch cap of 3 applies.

3 / 5

Progressive Disclosure

Clear overview pointing to four well-signaled one-level-deep references (data-locations, sqlite-access, schema-reference, import-recipes), all of which are real files, with content appropriately split and easy to navigate.

5 / 5

Total

17

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is exemplary: it names concrete actions, provides comprehensive trigger terms including file names and platform variants, explicitly covers both what and when, and occupies a distinct niche with minimal conflict risk. Third-person voice is maintained throughout.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'import, inspect, migrate, or analyze DeepChat data' — matching the comprehensive-coverage anchor; not below 5 because four distinct verbs are named rather than 1-2.

5 / 5

Completeness

Explicitly answers 'what' ('build third-party tools that import, inspect, migrate, or analyze') and 'when' ('Use when Codex needs to work with...') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage including file names ('agent.db', 'chat.db'), formats (SQLCipher, SQLite), and platform variants (macOS/Windows/Linux), matching the synonyms-and-extensions anchor.

5 / 5

Distinctiveness Conflict Risk

Clear DeepChat-specific niche with distinct triggers (agent.db, chat.db, Electron safeStorage, Tauri) giving minimal conflict risk; not below 5 because the triggers are uniquely scoped to this product.

5 / 5

Total

20

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
ThinkInAIXYZ/deepchat
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.