Menu
Use when scope expansion is detected at any phase — enforces focus by quantifying risk and requiring explicit user approval before scope changes
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
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
Basé sur la classification professionnelle SOC
| name | scope-control |
| description | Use when scope expansion is detected at any phase — enforces focus by quantifying risk and requiring explicit user approval before scope changes |
A focused paper with 1–2 strong contributions beats a scattered paper with 5 weak ones. This skill can trigger at ANY phase when scope expansion is detected.
Core principle: Focus is a feature. Scope creep is a bug.
Violating the letter of this rule is violating the spirit of this rule.
Any ONE of these activates this skill:
When triggered, the agent MUST execute all four steps in order:
1. WARN: "Current scope may be too large for [target venue] as a single paper."
2. QUANTIFY: "Current experiment plan requires ~X GPU-hours. Budget is Y. Excess: Z%."
or "There are N contribution points. A focused paper typically has 1-2."
3. PROPOSE: Reduction options, prioritized:
a) Core contribution to keep
b) Items to defer to future work
c) Items to cut entirely
4. PRESENT: User decides. Agent cannot decide scope reduction on its own.
Skip any step = scope creep enabled = paper quality at risk
| Excuse | Reality |
|---|---|
| "We can fit it all in" | Page limits exist. Reviewers penalize unfocused papers. |
| "Each piece is small" | Small pieces compound into confusion. |
| "We already did the work" | Sunk cost. Extra work that dilutes the paper hurts more than helps. |
| "The reviewer might ask for it" | Anticipate reviewers, but don't preemptively answer every possible question. |
More contributions ≠ better paper
Focused contribution + strong evidence = acceptance
Detect expansion. Quantify risk. Propose cuts. Let the user decide.