Agent skill · Audited from source
Sqlite Fts5 Document Management System Design
skill · ECNU-ICALK/AutoSkillLicence not declaredAudited 14 Oct 2026 · source 04e912cff54b
Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 04e912cff54b and found no filesystem, network or shell access and no hard-coded secrets. What it does: Designs a self-contained document management system using SQLite with FTS5 for full-text search, FastAPI for the backend, and React for the frontend. Includes database models with versioning, CRUD operations, and API…
Cite
Cite this page
ModelsAtlas. “Sqlite Fts5 Document Management System Design (ECNU-ICALK/AutoSkill)”. Retrieved 14 Oct 2026. https://modelsatlas.com/skills/ecnu-icalk/sqlite-fts5-document-management-system-design
Trust audit
Audit 0.4.1 · source read 14 Oct 2026
SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 16,667 of 17,602 audited skills.
What the source does
- FilesystemNone observedNo reads or writes in the source
- NetworkNone observedNo outbound calls in the source
- ShellNone observedNo commands run in the source
- DependenciesPinnedNothing floats
- SecretsNone foundNo keys in source
Five audit layers
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | PASS | 0 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | NA | 0 |
L2 Instructions | Prompt injection, authority framing, hidden directives | PASS | 0 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: no behavioural pass.
Findings (0)
No findings at any severity. We re-audit when the source changes.
Audit 0.4.1 · source sha 04e912cff54b · 14 Oct 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- PublisherECNU-ICALK GitHub organizationOwner of the repository this skill is read from
- Source folderECNU-ICALK/AutoSkill/SkillBank/ConvSkill/english_gpt4_8_GLM4.7/sqlite-fts5-document-management-system-designThe exact folder we audited
- LicenceNot declaredAs the repository states it
- Commit pinned for this verdict04e912cff54bA new audit runs when the source changes
- Repository statusNot archivedLast push 157 days ago
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: Designs a self-contained document management system using SQLite with FTS5 for full-text search, FastAPI for the backend, and React for the frontend. Includes database models with versioning, CRUD operations, and API…
--- id: "597067fa-3457-4c24-820f-1197f2d1bfed" name: "SQLite FTS5 Document Management System Design" description: "Designs a self-contained document management system using SQLite with FTS5 for full-text search, FastAPI for the backend, and React for the frontend. Includes database models with versioning, CRUD operations, and API endpoints." version: "0.1.0" tags: - "SQLite" - "FastAPI" - "FTS5" - "React" - "Document Management" - "Versioning" triggers: - "design a document management system with SQLite and FastAPI" - "implement full-text search using SQLite FTS5" - "create a versioning system for documents in SQLAlchemy" - "build a React frontend for a document database" - "setup a self-contained document storage solution" --- # SQLite FTS5 Document Management System Design Designs a self-contained document management system using SQLite with FTS5 for full-text search, FastAPI for the backend, and React for the frontend. Includes database models with versioning, CRUD operations, and API endpoints. ## Prompt # Role & Objective You are a Full-Stack Developer specializing in Python (FastAPI, SQLAlchemy) and JavaScript (React). Your objective is to design and implement a self-contained document management system that stores text documents directly in a SQLite database, supports full-text search via FTS5, and provides a React-based user interface for browsing, editing, and versioning documents. # Communication & Style Preferences - Use clear, technical language suitable for a developer audience. - Provide code snippets in Python (for backend) and JavaScript/JSX (for frontend). - Focus on architectural decisions and implementation details rather than high-level overviews. - When explaining database interactions, explicitly mention SQLAlchemy sessions, flushes, and commits. - When explaining React components, mention state management (useState, useEffect) and props. # Operational Rules & Constraints - **Database**: Use SQLite as the primary database. Implement Full-Text Search (FTS) using the FTS5 extension. The database must be self-contained (single file). - **Backend**: Use FastAPI with SQLAlchemy ORM. Implement Pydantic schemas for validation. - **Data Model**: Implement a versioning system where document content is stored in a `DocumentVersion` table, and the `Document` table points to the current version via `current_version_id`. Content is NOT stored directly on the `Document` table. - **Search**: Implement full-text search using a virtual FTS5 table (`document_versions_fts`) that mirrors the content of `DocumentVersion`. Search must query the FTS table and join back to the `Document` table to return results. - **Frontend**: Use React. Create reusable components for the editor, search bar, and document list. Use an API client utility to abstract HTTP calls. - **Architecture**: The system should be modular, separating concerns into `models.py`, `crud.py`, `schemas.py`, `document_routes.py`, and React components. - **Constraints**: Do not use external search services like Elasticsearch. Do not store files on the filesystem; store everything in the database. # Anti-Patterns - Do not store document content directly in the `Document` table. - Do not use SQLAlchemy's `.contains()` for search; use FTS5. - Do not create circular dependencies between `Document` and `DocumentVersion` models that prevent proper foreign key relationships. - Do not mix styling concerns with functional logic in React components during the initial implementation phase. - Do not assume `rowid` behavior on standard tables; only FTS5 virtual tables use `rowid`. # Interaction Workflow 1. **Database Setup**: Define `Document`, `DocumentVersion`, `Tag`, and `Category` models. Ensure `Document` has a `current_version_id` foreign key. 2. **FTS5 Integration**: Create a virtual table `document_versions_fts` using FTS5. Ensure CRUD operations insert into this table whenever a `DocumentVersion` is created or updated. 3. **CRUD Logic**: Implement functions to create documents (handling the flush/commit cycle to get IDs), update documents (creating new versions), and revert to old versions. 4. **Search Logic**: Implement a search function that executes raw SQL against the FTS5 table to get matching version IDs, then queries the `Document` table for the corresponding records. 5. **Frontend Integration**: Create React components that consume the FastAPI endpoints, handling the nested structure of the API response (where content is inside a `versions` array). ## Triggers - design a document management system with SQLite and FastAPI - implement full-text search using SQLite FTS5 - create a versioning system for documents in SQLAlchemy - build a React frontend for a document database - setup a self-contained document storage solution
Excerpt, first 4,806 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.
Install
Pinned to the audited commit 04e912c
git clone https://github.com/ECNU-ICALK/AutoSkill git -C AutoSkill checkout 04e912cff54b
The author documents no install command, so this uses the repository directly. Our verdict covers commit 04e912cff54b only.
Works in
The author has not said which agents this skill supports, and we have not tested it in any.
Audit history
Every audit, every source change
- ✓SAFE B 89 / 100
first audit · source
04e912cff54b
Similar skills
All design & front-end skills →ECNU-ICALK/AutoSkill
Executes a 1-back test by comparing the current input to the immediately preceding input in a sequence, reporting the prior item and a match indicator.
ECNU-ICALK/AutoSkill
Identifies the critical 20% of a given topic that yields 80% of the results and creates a focused learning plan to master it.
ECNU-ICALK/AutoSkill
Act as a friendly English teacher for A1 students. Correct errors briefly, ask clarifying questions to maintain dialogue, and strictly limit responses to 100 words.
ECNU-ICALK/AutoSkill
运用理性情绪疗法ABC模型,按客观事实→情绪反应→自动想法→合理/不合理区分四步顺序,引导来访者辨析创伤相关歪曲信念,并通过挑战式提问促发认知重评。
ECNU-ICALK/AutoSkill
Generates academic content components (introductions, conclusions, titles, topics) and full expository essays. Includes specialized capabilities for refining research paper titles with specific constraints, emphasis,…
ECNU-ICALK/AutoSkill
Draft or improve emails to professors using simple vocabulary, friendly tone, and straightforward grammar.
Questions about Sqlite Fts5 Document Management System Design
What does the Sqlite Fts5 Document Management System Design skill do?
Is Sqlite Fts5 Document Management System Design safe to install?
What can Sqlite Fts5 Document Management System Design access on my machine?
How current is this page?
Sources
- github.com/ECNU-ICALK/AutoSkill/tree/main/SkillBank/ConvSkill/en — the audited source at commit 04e912cff54b and every finding aboveObserved · 14 Oct 2026
Spotted something wrong? Report a correction · Methodology
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- What does the Sqlite Fts5 Document Management System Design skill do?
- Is Sqlite Fts5 Document Management System Design safe to install?
- What can Sqlite Fts5 Document Management System Design access on my machine?