chore: Extract prompts from python to text files for shared infra#10
Merged
adnanrhussain merged 2 commits intoahussain/sdk_typescriptfrom Mar 2, 2026
Merged
Conversation
adnanrhussain
changed the base branch from
ahussain/vocab_all_grades
to
ahussain/sdk_typescript
This was referenced Feb 6, 2026
Merged
There was a problem hiding this comment.
Pull request overview
This PR extracts prompts from Python files (/evals/prompts/*.py) to text files organized in eval-specific folders as part of building shared infrastructure for prompt management. The extracted prompts will be used by components being built in downstream PRs, including a TypeScript SDK. This is the first PR in a series of 5 PRs (#10-#14) implementing SDK features.
Changes:
- Extracted vocabulary evaluation prompts to text files in
evals/prompts/vocabulary/ - Extracted sentence structure evaluation prompts to text files in
evals/prompts/sentence-structure/ - Extracted grade-level appropriateness prompts to text files in
evals/prompts/grade-level-appropriateness/
Reviewed changes
Copilot reviewed 14 out of 14 changed files in this pull request and generated 7 comments.
Show a summary per file
| File | Description |
|---|---|
| evals/prompts/vocabulary/other-grades-user.txt | User prompt for vocabulary complexity evaluation (grades 5-12) with rubric, examples, and annotation guide |
| evals/prompts/vocabulary/other-grades-system.txt | System prompt defining the role for vocabulary complexity evaluation |
| evals/prompts/vocabulary/grades-3-4-user.txt | User prompt for vocabulary complexity evaluation specifically for grades 3-4 |
| evals/prompts/vocabulary/grades-3-4-system.txt | System prompt with rubric for grades 3-4 vocabulary evaluation |
| evals/prompts/vocabulary/background-knowledge.txt | Prompt for generating background knowledge assumptions based on grade level |
| evals/prompts/sentence-structure/rubric-grades-5-12.txt | Rubric for sentence structure complexity evaluation (grades 5-12) |
| evals/prompts/sentence-structure/rubric-grade-4.txt | Rubric for sentence structure complexity evaluation (grade 4) |
| evals/prompts/sentence-structure/rubric-grade-3.txt | Rubric for sentence structure complexity evaluation (grade 3) |
| evals/prompts/sentence-structure/complexity-user.txt | User prompt for sentence structure complexity analysis |
| evals/prompts/sentence-structure/complexity-system.txt | System prompt for sentence structure complexity analysis |
| evals/prompts/sentence-structure/analysis-user.txt | User prompt for detailed grammatical sentence analysis |
| evals/prompts/sentence-structure/analysis-system.txt | System prompt for grammatical analysis |
| evals/prompts/grade-level-appropriateness/user.txt | User prompt for determining grade-level appropriateness of text |
| evals/prompts/grade-level-appropriateness/system.txt | System prompt for grade-level appropriateness evaluation |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
czi-fsisenda
approved these changes
Feb 19, 2026
czi-fsisenda
left a comment
czi-fsisenda
left a comment
There was a problem hiding this comment.
Looks good! Just moving existing prompts as-is.
I think it's a great idea to separate these out this way.
|
Keeping typos since that is the version of the prompts that have been benchmarked. |
adnanrhussain
force-pushed
the
ahussain/sdk_typescript
branch
from
75f0e45 to
8988061
Compare
adnanrhussain
force-pushed
the
ahussain/sdk_1_prompts
branch
from
ad3614d to
2b4ef17
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
In preparation of building components that rely on this shared infra (prompts), this PR copies the prompts from the corresponding python files (
/evals/prompts/*.py) to text-files in eval-specific folders.In a downstream PR, once these changes are validated, to remove the duplicity, the python files will import the prompts from these text files
Documentation
N/A
Testing
N/A
SDK Feature PR Index
Note:: All approved stacked PRs will be linearly merged into
[ahussain/sdk_typescript](https://github.com/learning-commons-org/evaluators/tree/ahussain/sdk_typescript)feature branch (PR Pending) for a final check, before being merged to main.