scholar-verify
Runs required validation checks for code changes based on modified surface areas.
Install
mkdir -p .claude/skills/scholar-verify && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/18627" && unzip -o skill.zip -d .claude/skills/scholar-verify && rm skill.zipInstalls to .claude/skills/scholar-verify
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Run ScholarAI's required validation matrix for Symphony-driven changes based on the touched surfaces.Key capabilities
- →Run ScholarAI's required validation matrix for Symphony-driven changes
- →Execute runtime hygiene checks
- →Perform documentation and governance checks
- →Run structure and code boundary checks
- →Execute frontend and backend specific tests
How it works
The skill runs a validation matrix based on the touched files, executing specific scripts for workflow, frontend, backend, or shared package changes.
Inputs & outputs
When to use scholar-verify
- →Verify code before push
- →Run validation matrix
- →Check governance compliance
About this skill
Scholar Verify Skill
Use this skill before every push and again before moving a ticket to Human Review.
Scope selection
Workflow / docs / governance / root automation changes
Run all of:
bash scripts/check-runtime-hygiene.sh trackedbash scripts/check-doc-governance.shbash scripts/check-structure-boundaries.shbash scripts/check-code-boundaries.shbash scripts/check-governance.sh
Use this bucket when changes touch files such as:
WORKFLOW.md.codex/scripts/symphony/AGENTS.mdREADME.mddocs/specs/- other root workflow or governance files
Frontend changes
Always run:
cd apps/web && npm run type-check
Then run focused or full frontend tests that directly prove the touched behavior.
Backend changes
Always run:
cd apps/api && .venv/bin/python -m pytest -q tests/unit/test_services.py --maxfail=1
If import/chat contract surfaces changed, also run:
cd apps/api && .venv/bin/python -m pytest -q tests/integration/test_imports_chat_contract.py --maxfail=1
Shared packages
If shared package code changes, build the affected package(s):
cd packages/types && npm run buildcd packages/sdk && npm run build
Reporting
- Record every executed command in the workpad
Validationsection. - Mark only commands that actually ran as complete.
- If a required check fails, fix it or keep the issue in execution state.
When not to use it
- →When changes do not touch workflow, docs, governance, or root automation files
- →When changes are not related to frontend, backend, or shared packages
Limitations
- →Requires specific scripts to be present for checks
- →Requires manual recording of executed commands in the workpad
- →Requires fixing failed checks or keeping issues in execution state
How it compares
This skill provides a structured and automated validation process tailored to different types of changes, ensuring compliance before human review, unlike manual testing.
Compared to similar skills
scholar-verify side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| scholar-verify (this skill) | 0 | 1mo | No flags | Intermediate |
| verification-loop | 0 | 3mo | Review | Intermediate |
| lint-and-validate | 6 | 6mo | Review | Beginner |
| checking-changes | 1 | 4mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
verification-loop
tom237ttkk
A comprehensive verification system for Codex work sessions.
lint-and-validate
davila7
Automatic quality control, linting, and static analysis procedures. Use after every code modification to ensure syntax correctness and project standards. Triggers onKeywords: lint, format, check, validate, types, static analysis.
checking-changes
streamlit
Validates all code changes before committing by running format, lint, type, and unit test checks. Use after making backend (Python) or frontend (TypeScript) changes, before committing or finishing a work session.
moai-foundation-quality
modu-ai
Enterprise code quality orchestrator with TRUST 5 validation, proactive analysis, and automated best practices enforcement
code-review
viadee
Systematic code review for RoboView contributions. Use when reviewing pull requests, checking code quality, or validating changes before merge. Covers style, testing, security, and cross-surface consistency.
code-change-verification
openai
Run the mandatory verification stack when changes affect runtime code, tests, or build/test behavior in the OpenAI Agents Python repository.