2.4 KiB
2.4 KiB
name, description
| name | description |
|---|---|
| helia-dev | Aligns development tasks with Helia's thesis goals (Local vs Cloud) and enforces project standards (Ruff, Pyrefly). Use when working on the Helia codebase. |
<quick_start> Always invoke this skill when starting a new task in the Helia repository. It grounds the agent in the research context and enforces the "Quality Contract". </quick_start>
<context_alignment>
Research Context Awareness
Before performing any task, the agent MUST understand:
- Goal: We are benchmarking Local Quantized LLMs vs. Cloud LLMs for PHQ-8 assessment.
- Constraint 1 (Privacy): Data processing must support on-premise execution.
- Constraint 2 (Modularity): The system must allow easy swapping of Model Tiers (1-3).
- Constraint 3 (Persistence):
AssessmentResultis the source of truth for experiments.
Tooling Standards
All code changes must pass:
- Linting/Formatting:
uv run ruff check .anduv run ruff format . - Type Checking:
uv run ty check</context_alignment>
-
Execute Task:
- Perform the requested engineering task (Feature, Bugfix, Refactor).
- Critical: Ensure any architectural changes support the 3-Tier Model Strategy (Local, Self-Hosted, Cloud).
-
Enforce Quality:
- Run
uv run ruff format .to fix formatting. - Run
uv run ruff check . --fixto fix linting errors. - Run
uv run ty checkto ensure type safety. - Fix any errors found by these tools before declaring the task complete.
- Run
-
Verify Alignment:
- Check: Does the change break the "swappable model" architecture?
- Check: Does the change introduce any hard dependencies on cloud services (violating Privacy-First)?
<success_criteria>
- Task is completed.
- Code passes
ruff(lint/format). - Code passes
ty(types). - Architecture remains modular (supports Tiers 1-3).
CLAUDE.mdis updated if the task changed the architecture or standards. </success_criteria>