github.com/HHS/OPRE-OPS
| Skill | Added | Review |
|---|---|---|
backend-tests .claude/skills/backend-tests/SKILL.md Run backend tests and code quality checks for OPRE OPS. Covers ops_api pytest, data_tools pytest, and nox linting/formatting sessions. Use this skill when the user wants to run backend tests, check code quality, lint Python code, run pytest, or verify their backend changes pass CI checks — even if they just say "run the tests" or "does this pass". | 72 72 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 4ff5a51 | |
create-pr .claude/skills/create-pr/SKILL.md Create a GitHub pull request with the project's PR template fully populated. Analyzes the branch diff, fills in "What changed", "Issue", "How to test", "A11y impact", "Definition of Done", and other sections. Use this skill whenever the user wants to create a PR, open a pull request, submit their branch for review, or says things like "make a PR", "open a PR", "submit this for review", or "I'm ready to create a pull request" — even if they don't use the exact phrase "pull request". | 87 87 1.35x Agent success vs baseline Impact 84% 1.35xAverage score across 3 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: 4ff5a51 | |
db-migrations .claude/skills/db-migrations/SKILL.md Create, review, test, and rollback Alembic database migrations for OPRE OPS. Use this skill whenever the user mentions database migrations, alembic, schema changes, adding/modifying columns or tables, model changes that need migration, or "migrate the database". Also use when a model change has been made and the user needs to generate the corresponding migration. | 75 75 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 4ff5a51 | |
dead-code-after-removal-sweep .claude/skills/dead-code-after-removal-sweep/SKILL.md Use after deleting a feature, function, component, validation rule, config flag, enum value, or any symbol — to find the downstream artifacts the deletion orphaned. Covers orphaned string keys in object/label/i18n maps, dead branches, now-unused imports/props, stale comments, and test fixtures that ESLint and code review miss. Trigger when you removed code and want a clean, zero-dead-code diff. | 69 69 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 4ff5a51 | |
e2e-tests .claude/skills/e2e-tests/SKILL.md Run, monitor, and fix frontend Cypress E2E tests. Handles local execution, CI monitoring, failure diagnosis, flaky test detection, and accessibility regression checks. Use this skill whenever the user mentions Cypress, E2E tests, end-to-end tests, test failures, CI failures, "CI is red", flaky tests, accessibility testing, or wants to run/debug/fix any frontend integration test — even if they don't say "e2e" explicitly. | 69 69 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 4ff5a51 | |
init-story .claude/skills/init-story/SKILL.md Collect context from the developer and create a story markdown file in .claude/stories/ for the current branch. Use when the user says "init story", "create story", "start story", or "new story". | 69 69 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 4ff5a51 | |
sync-openapi .claude/skills/sync-openapi/SKILL.md Sync, update, and validate the OpenAPI specification (backend/openapi.yml) against the Flask API routes. Use whenever endpoints have been added, changed, or removed, or when the user mentions API docs, swagger, OpenAPI, endpoint documentation, "update the spec", or has just added/modified a route or resource class. Also use when checking for drift between the code and the spec. | 71 71 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 4ff5a51 | |
update-story .claude/skills/update-story/SKILL.md Update the current story's acceptance criteria checkboxes based on recent git history, then sync the updated body back to the linked GitHub issue. Use when the user says "update story", "mark AC done", "sync story", or "update the issue". | 76 76 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 4ff5a51 | |
useblocker-bypass-regression-test .claude/skills/useblocker-bypass-regression-test/SKILL.md Use when writing a Vitest test for a react-router useBlocker unsaved-changes guard in this repo — specifically an intentional-navigation handler (Edit / Submit / Cancel) that uses flushSync(() => setIsNavigating(true)) before navigate() to bypass the blocker. A test that reads the blocker predicate after act() passes even when flushSync is removed, so it does not guard the fix. Trigger on any test touching isNavigating, useBlocker, flushSync, or a *.hooks.js navigation-blocker handler. | 75 75 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 4ff5a51 |