Best use case
quality-assess is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
It is a strong fit for teams already working in Codex.
Perform GRADE quality assessment on a research source
Teams using quality-assess should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/quality-assess/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How quality-assess Compares
| Feature / Agent | quality-assess | Standard Approach |
|---|---|---|
| Platform Support | Codex | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Perform GRADE quality assessment on a research source
Which AI agents support this skill?
This skill is designed for Codex.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
SKILL.md Source
# Quality Assess Command
Perform a GRADE evidence quality assessment on a research source or finding.
## Instructions
When invoked, perform systematic GRADE assessment:
1. **Load Source**
- Accept REF-XXX identifier or file path
- Load frontmatter metadata
- Determine source type and baseline quality
2. **Apply GRADE Framework**
- Evaluate 5 downgrade factors (bias, inconsistency, indirectness, imprecision, publication bias)
- Evaluate 3 upgrade factors (large effect, dose-response, confounding)
- Calculate final GRADE level
3. **Generate Assessment**
- Fill assessment template per @.aiwg/research/docs/grade-assessment-guide.md
- Include hedging language recommendations
- Include applicability notes for AIWG context
4. **Save Assessment**
- Save to `.aiwg/research/quality-assessments/{ref-id}-assessment.yaml`
- Update frontmatter in source document if --update-frontmatter
5. **Report**
- Display GRADE level with confidence statement
- Show allowed vs forbidden hedging language
- Flag any existing citations that violate the assessed quality level
## Arguments
- `[ref-id or file-path]` - Source to assess (required)
- `--output [yaml|markdown]` - Output format (default: yaml)
- `--update-frontmatter` - Update source document frontmatter with assessment
- `--check-citations` - Also check existing citations of this source for GRADE compliance
## References
- @.aiwg/research/docs/grade-assessment-guide.md - GRADE methodology
- @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/agents/quality-assessor.md - Quality Assessor agent
- @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/schemas/research/quality-dimensions.yaml - Quality schema
- @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/rules/citation-policy.md - Hedging language rulesRelated Skills
Quality Filtering
Accept/reject logic and quality scoring heuristics for media content
security-assessment
Execute STRIDE threat modeling, vulnerability scanning, and security control validation with risk scoring
research-quality
Assess source quality using GRADE methodology
research-quality-audit
Audit research corpus for shallow stubs, incomplete sections, missing source files, and doc depth issues. Detects docs written from abstracts rather than full papers and optionally auto-dispatches expansion agents.
quality-checker
Validate skill quality, completeness, and adherence to standards. Use before packaging to ensure skill meets quality requirements.
aiwg-orchestrate
Route structured artifact work to AIWG workflows via MCP with zero parent context cost
venv-manager
Create, manage, and validate Python virtual environments. Use for project isolation and dependency management.
pytest-runner
Execute Python tests with pytest, supporting fixtures, markers, coverage, and parallel execution. Use for Python test automation.
vitest-runner
Execute JavaScript/TypeScript tests with Vitest, supporting coverage, watch mode, and parallel execution. Use for JS/TS test automation.
eslint-checker
Run ESLint for JavaScript/TypeScript code quality and style enforcement. Use for static analysis and auto-fixing.
repo-analyzer
Analyze GitHub repositories for structure, documentation, dependencies, and contribution patterns. Use for codebase understanding and health assessment.
pr-reviewer
Review GitHub pull requests for code quality, security, and best practices. Use for automated PR feedback and approval workflows.