CtrlK
BlogDocsLog inGet started
Tessl Logo

assistant-rocky-lti-assist

Coding assistant for the Rocky-LTI project — a Canvas LTI 1.3 integration with an AI-powered educational agent. Use when working on FastAPI endpoints, MCP server components, SQLAlchemy models, Alembic migrations, Azure Functions workers, React/TypeScript frontend, or LTI/OAuth authentication flows in this codebase.

82

1.51x
Quality

75%

Does it follow best practices?

Impact

91%

1.51x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/assistant-rocky-lti-assist/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

92%

27%

Submission History Endpoint

New FastAPI endpoint with correct domain structure

Criteria
Without context
With context

router.py file

62%

100%

models.py file

100%

100%

service.py file

100%

100%

db.py file

100%

100%

Thin router

100%

100%

Depends injection

0%

0%

Async endpoint

100%

100%

Pydantic v2 model_config

100%

100%

Pydantic v2 model_dump

100%

100%

Type annotations

100%

100%

uv for linting

0%

100%

uv for tests

0%

100%

No pip usage

0%

100%

91%

48%

Student Engagement Tracking

Database model with correct location and async patterns

Criteria
Without context
With context

Correct model location

0%

100%

Async SQLAlchemy base

75%

83%

uv run alembic revision

0%

100%

uv run alembic upgrade

0%

100%

No pip usage

100%

100%

Correct alembic directory

0%

100%

Type annotations

40%

30%

Async patterns in any queries

100%

100%

No class Config

100%

100%

90%

16%

Canvas Announcements MCP Tool

MCP tool with FastMCP and correct component structure

Criteria
Without context
With context

Service in canvas_mcp/services/

30%

100%

Registration in canvas_mcp/servers/

30%

100%

Models in canvas_mcp/models/

70%

100%

FastMCP used

100%

100%

Async service function

100%

100%

Async tool handler

100%

100%

Pydantic v2 field_validator or model_validator

100%

87%

No .dict() usage

100%

100%

Type annotations

100%

100%

uv add for dependencies

0%

0%

Repository
ucdavis/ai-skills-registry
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

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.