بنقرة واحدة
research-f-iteration
ResearchPilot Research Assistant [Phase F]: Code iteration
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
القائمة
ResearchPilot Research Assistant [Phase F]: Code iteration
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 | research[F]-iteration |
| description | ResearchPilot Research Assistant [Phase F]: Code iteration |
| version | 2.0.0 |
| license | LICENSE |
user_requirements.md priority: All user constraints in
docs/user_requirements.mdtake precedence over any default instruction in this skill. Always read that file before generating any output.
ResearchPilot-Skills splits a complete academic research project into seven independent stage skills. The current skill is one link in that chain.
| Skill | Phase | Main Output |
|---|---|---|
/research[A]-exploration | Direction Exploration | docs/idea_report.md Part 1 |
/research[B]-idea | Idea Deepening | docs/idea_report.md Part 2 |
/research[C]-experiment | Experiment Design | docs/idea_report.md Part 3 |
/research[D]-implementation | Implementation Design | docs/implementation.md |
/research[E]-coding | Coding | code/ + docs/dev_log.md |
/research[F]-iteration | Code Iteration | dev_log.md iteration records |
/research[G.0]-plan | Paper Planning | manuscript architecture + notebooks/figures.ipynb |
/research[G.1]-method | Method | manuscript Method section |
/research[G.2]-experiments | Experiments | manuscript Experiments section |
/research[G.3]-abstract | Abstract | manuscript Abstract |
/research[G.4]-introduction | Introduction | manuscript Introduction |
/research[G.5]-related | Related Works | manuscript Related Works |
/research[G.6]-conclusion | Conclusion + References | manuscript Conclusion |
/research[G.7]-review | Full-paper Review | review report |
docs/
idea_report.md # Part 1 (Phase A) / Part 2 (Phase B) / Part 3 (Phase C)
implementation.md # Coding guide (Phase D)
dev_log.md # Dev log (append-only, never delete)
user_requirements.md # User constraints, collected by Claude
papers/ # Downloaded PDFs or abstract TXTs
manuscripts/ # Phase G paper drafts
code/
src/models/{model}.py / baseline/
src/data/ / src/train.py / src/evaluate.py / src/utils/
scripts/ # nohup shell scripts
configs/
data/ / results/ / logs/
README.md / requirements.txt
/research[F]-iteration
An optional natural-language instruction may follow the command. The AI will treat it as an additional constraint or supplement for this invocation.
F-1 Diagnostic analysis (read dev_log.md + results/ + idea_report.md, produce report)
F-2 Confirm backtrack scope (hyperparams only / model architecture / experiment design)
F-3 Update design documents (documents first, then code — never skip)
F-4 Code changes (append iteration log entry after every file change)
F-5 Validation (run experiments, append results to dev_log)
F-6 Decide whether to continue (loop F-1, or proceed to next phase)
Full step-by-step instructions: references/phase-F.md.
dev_log.md, results/ data, and idea_report.md before diagnosing — no guessing.references/template-flexibility.md take precedence over any specific template instruction.When results are satisfactory:
Phase F complete. {N} iteration rounds completed. Final results recorded in dev_log.md.
→ Use `/research[G]-paper` to enter the Paper Writing phase.
references/phase-F.mdreferences/template-flexibility.mdResearchPilot Research Assistant [Phase G.0]: Paper planning
ResearchPilot 科研助手[阶段 G.0]:论文规划
Global-installable, project-level academic rebuttal strategy skill for AI/ML/CV/NLP/Robotics papers. Use when authors need a workspace-local .awesome-rebuttal state folder, paper/code/review/venue-rule intake, JSON memory, snapshots, LaTeX/template handling for one-page rebuttals, reviewer stance analysis, strategy planning, experiment triage, safe author response drafting, or AC summaries under confirmed venue rules.
Use when the user has a research question and needs a complete experiment package — design document, runnable code, results (measured or simulated with honest provenance), publication-grade figures, structured report. Single-stage, no Python runtime.
Use when the user wants a paper audited for integrity issues — image misuse, numerical anomalies, logical gaps — and needs a reviewable evidence report. Works on external papers (PDF / DOI / arXiv) and on outputs from a local paper-writer run. Single-stage skill.
Use when the user wants a comprehensive literature survey on a specific research topic. Outputs a complete PDF survey (6–20 pages, 60+ real citations, 100+ recommended) with LaTeX source, taxonomy figures, and a classified literature table. Single-stage, no Python runtime.