ReddRadar
Agent skill
imrad-reviewer
Use when reviewing an IMRaD draft for structural integrity, evidentiary support, and section-boundary correctness.
Install this agent skill to your Project
npx add-skill https://github.com/narumiruna/agent-skills/tree/main/skills/imrad-reviewer
SKILL.md
IMRaD Reviewer
Purpose
Review an existing IMRaD draft for structural, logical, and evidentiary quality.
When to use
Use this skill when the user asks to:
- Audit IMRaD structure quality
- Find section-boundary violations
- Identify unsupported or over-interpreted claims
- Decide whether a draft is structurally publishable
When NOT to use
Do NOT use this skill when:
- The user asks for first-pass drafting from raw notes
- The user asks for full document rewrite by default
- The input is not an IMRaD draft and no review target exists
Review Criteria
- Introduction defines a concrete question/problem
- Methods are sufficient for the document scope
- Results are objective and non-interpretive
- Discussion interprets only what Results support
- Linkage is intact: question -> method -> result -> interpretation
- Limitations and assumptions are present where needed
Review Workflow
- Validate section presence and order.
- Check section-boundary purity.
- Trace major claims to Results evidence or explicit assumptions.
- Flag unsupported claims and over-interpretation.
- Produce actionable fixes with severity.
Output Requirements
The output MUST include:
- Overall assessment
- Strengths
- Issues list, where each issue includes:
- severity: high, medium, or low
- section
- problem
- why it matters
- suggested fix
- Optional final verdict:
- structurally sound
- needs revision
- unsuitable as IMRaD
Severity Model
- High: structural breakage, fabricated or unsupported core claims, major section mixing
- Medium: weak linkage, under-specified methods, incomplete limitations
- Low: clarity, concision, or minor organization issues
Truthfulness Constraints
- The reviewer MUST NOT invent missing evidence
- The reviewer MUST distinguish empirical vs non-empirical results
- Non-empirical results MUST be explicitly labeled as inferred, hypothetical, expected, or simulated
Failure Modes
- Rewriting the full draft instead of reviewing
- Mixing structural critique with factual speculation
- Missing contradictions between Results and Discussion
- Providing non-actionable feedback
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
narumiruna/agent-skills
slide-creator
Use when creating slide decks with Marp/Marpit Markdown (marp), including authoring slide content, designing slide color schemes, and building SVG diagrams or illustrations for the deck.
narumiruna/agent-skills
slide-color-design
Use when you only need slide color systems, palette selection, or palette generation workflows and want direct pointers to the color design references.
narumiruna/agent-skills
mermaid-creator
Use when creating or converting Mermaid diagrams (for example flowcharts, sequence diagrams, ER diagrams, and Gantt charts), including exporting to SVG for docs or slides.
narumiruna/agent-skills
test-driven-development
Use when implementing non-trivial code changes that should follow TDD (write a failing test first, make the smallest passing change, then refactor safely).
narumiruna/agent-skills
svg-illustration
Use when you need SVG diagram rules, layout patterns, or embedding guidance for slide decks and want the minimal SVG-focused reading path.
narumiruna/agent-skills
python-cli-typer
Use when building or structuring Python CLI commands with Typer, including commands, options, and multi-command apps.
Didn't find tool you were looking for?