القائمة
Use when assessing innovation level of a research contribution — invoked after literature review (Phase 1) and after method design (Phase 3) to verify that novelty matches the target venue tier
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
| name | novelty-classifier |
| description | Use when assessing innovation level of a research contribution — invoked after literature review (Phase 1) and after method design (Phase 3) to verify that novelty matches the target venue tier |
Overstating novelty wastes months of work on a paper that will be rejected. This skill forces honest classification of the contribution type and innovation degree, then checks alignment with the target venue.
Core principle: Classify honestly, match realistically.
Violating the letter of this rule is violating the spirit of this rule.
CLASSIFY NOVELTY HONESTLY. DO NOT OVERSTATE. VENUE MISMATCH IS CAUGHT HERE, NOT AT REVIEW TIME.
If classification downgrades between Phase 1 and Phase 3, WARN the user immediately.
digraph novelty_classifier {
rankdir=TB;
start [label="Contribution\ndefined" shape=doublecircle];
type [label="Classify\ncontribution type" shape=box];
degree [label="Assess\ninnovation degree" shape=box];
check [label="Venue tier\nalignment?" shape=diamond];
pass [label="Aligned\nProceed" shape=box style=filled fillcolor="#d4edda"];
warn [label="Mismatch\nWARN user" shape=box style=filled fillcolor="#f8d7da"];
decide [label="User decides:\nadd depth / retarget / proceed" shape=diamond];
start -> type;
type -> degree;
degree -> check;
check -> pass [label="matches"];
check -> warn [label="insufficient"];
warn -> decide;
}
| Type | Description | Example |
|---|---|---|
| New Problem | First to formulate this problem | Defining few-shot learning |
| New Method | Novel algorithm or architecture | Transformer architecture |
| New Theory | Theoretical advance | PAC learning bounds |
| New Data/Benchmark | New dataset or evaluation standard | ImageNet |
| Engineering Integration | Combining existing techniques | Adding attention to existing model |
Classify the contribution into exactly one primary type. If it spans two, pick the stronger one and note the secondary.
| Degree | Definition |
|---|---|
| Foundational | Opens a new research direction |
| Significant improvement | Clear advance over SOTA with novel insight |
| Incremental improvement | Modest advance, refines existing approach |
| Combination/Engineering | Assembles known parts in new configuration |
Be precise. "Significant" requires a novel insight, not just better numbers.
| Venue Tier | Minimum Innovation |
|---|---|
| A (NeurIPS/ICML/Nature) | New method with significant insight, or foundational |
| B (AAAI/IJCAI/domain top) | Significant improvement or meaningful combination with strong experiments |
| C (workshops/lower journals) | Incremental improvement with solid experiments |
Warnings are presented to the user. The agent does not suppress them.
| Excuse | Reality |
|---|---|
| "Our combination is novel" | Is the insight novel, or just the combination? Reviewers will ask. |
| "No one has done exactly this" | Exact novelty ≠ meaningful novelty. What new insight does it provide? |
| "The experiments will show it's better" | Better results from engineering ≠ scientific contribution. |
| "We can frame it as novel" | Framing doesn't survive peer review. Real novelty does. |
Honest classification now → correct venue targeting → accepted paper
Inflated classification now → months of work → desk rejection
Classify honestly. Match realistically. Correct course early.
Use when designing the evaluation protocol for a method development project — locks primary metrics, datasets, seeds, statistical tests, and baseline list into an immutable contract
Use when G2 (plan freeze) and G3 (execution readiness) gates have passed — handles all implementation, baseline reproduction, experimentation, and iteration for both Type M and Type D projects; this is Phase 4
Use when research direction is validated (G1 passed) and the project needs method design, analysis framework, evaluation protocol, or story line — this is Phase 3 and must complete before any code or experiments
Reusable protocol for multi-agent discussions that iterate until convergence. Used by results-integration (Phase 5) and paper-writing (Phase 6) to ensure discussions actually resolve issues rather than just noting them.
Use when and ONLY when the user explicitly requests paper writing and G4 (write-ready) gate has passed — handles LaTeX structure, senior-level writing, reference verification, and iterative refinement
Use when Phase 1 (research-direction-exploration) is complete and G1 gate has passed — subjects the research problem to adversarial defense-style questioning, classifies project intent, re-evaluates venue target, and produces a final feasibility ruling before any method design begins