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

86%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 model navigator skill: lean, safety-conscious, and cleanly structured around existing one-level-deep reference files. The workflow is well sequenced with pre-flight checks, though it lacks an explicit post-import verification loop, and the body delegates all executable detail to the references.

DimensionReasoningScore

Conciseness

The body is lean with zero concept explanations Claude already knows (no 'SQLite is a...' or library tutorials); every line is a workflow step, safety rule, or pointer to a reference file. Matches the 'every token earns its place' anchor; not the 4 anchor since there is no over-explanation to trim.

5 / 5

Actionability

Concrete, executable guidance for an instruction-only navigator skill: exact reference filenames with read-conditions, exact files to copy ("`agent.db`, `agent.db-wal`, and `agent.db-shm`"), and exact repository source paths. It stays below 5 because the body itself contains no sample SQL or commands a developer could copy-paste, leaving minor gaps; it is well above the pseudocode midpoint.

4 / 5

Workflow Clarity

A clear 5-step sequenced workflow with meaningful checkpoints (consent gate, WAL-aware snapshot decision, schema_versions/sqlite_master inspection before assuming columns). It misses 5 because there is no post-import validation/feedback loop verifying that extracted or migrated data is correct; the destructive-operation cap does not apply since the workflow is explicitly snapshot-first and read-only.

4 / 5

Progressive Disclosure

A concise overview with four well-signaled, one-level-deep references, each paired with a 'when to read' condition, and all four files exist in references/ with no further nesting (import-recipes.md points only to sibling sqlite-access.md). Matches the clear-overview anchor exactly.

5 / 5

Total

18

/

20

Passed

Description

95%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.

A strong description: concrete actions, an explicit 'Use when...' trigger clause, and exceptional keyword coverage including exact database filenames and encryption/technology terms. The only nit is that the trigger clause names 'Codex' as the agent, which is unusual for a Claude skill but does not degrade the description's own quality.

DimensionReasoningScore

Specificity

"import, inspect, migrate, or analyze DeepChat data" names the domain plus several distinct concrete actions. It falls short of the 5 anchor because the actions are generic verbs without per-operation specifics (e.g., no "decrypt safeStorage values" or "extract sessions"), but is well above the 1-2-action midpoint.

4 / 5

Completeness

Explicitly answers both: what ("build third-party tools that import, inspect, migrate, or analyze DeepChat data") and when ("Use when Codex needs to work with DeepChat provider configuration, model configuration, MCP/app settings, sessions, messages..."). Both what and when are concrete with explicit trigger phrases, matching the 5 anchor exactly; the 4 anchor requires a weaker 'when', which does not apply.

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage including exact file names (`agent.db`, `chat.db`), technologies (SQLCipher, Electron safeStorage, Tauri), data categories (sessions, messages, provider configuration), and platform variants (macOS/Windows/Linux). Matches the comprehensive-synonyms-plus-extensions anchor; not the 4 anchor because nothing obvious is missing.

5 / 5

Distinctiveness Conflict Risk

A clear niche (DeepChat local data access) with highly distinct triggers (`agent.db`, SQLCipher, Electron safeStorage, Tauri importers) that no other skill would claim; minimal conflict risk. It does not merely reduce overlap with closely related skills as the 4 anchor describes.

5 / 5

Total

19

/

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.

Validation — 16 / 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.