Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By kkunkunya
Experiment planning toolkit for P4 academic research: turn claims into evidence chains, baseline/ablation plans, figure/table specs, feasibility salvage paths, and req-suite handoff tasks.
npx claudepluginhub kkunkunya/experiment-planning-suite --plugin experiment-planning-suite用于 P4 设计最低可交付 baseline、投稿级强 baseline、消融实验、指标阈值和 stop condition。不用于真正运行实验。
用于把论文贡献主张映射成实验矩阵、指标、成功判定、失败动作和机器 verifier 契约。不用于 baseline 细化或图表设计。
用于 P4 判断实验计划可实施性、预计论文级别、low-confidence 风险、失败后贡献重定位和最低补救方案。不用于拒稿信预演。
用于 P4 设计论文图、表、截图/系统演示证据,绑定 claim、章节位置、caption 和数据字段 schema。不用于实际画图。
Experiment-planning-suite 主入口。用于 P4 实验规划、实验矩阵、图表证据链、做一半能不能发、怎么交给 req 拆实验任务时路由。不用于真正跑实验(交给 req-suite 执行)。
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Frontend design skill for UI/UX implementation
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Memory compression system for Claude Code - persist context across sessions
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.
Marketing skills for AI agents — conversion optimization, copywriting, SEO, paid ads, ad creative, and growth
AI-first frontend design toolkit for Claude Code and Codex: 7-stage flow (requirement -> six-dimension research -> dualround interview -> visual anchors -> asset gen -> code impl -> design review) + scenario C increment router + ten-line anti-slop gate + kun 15-segment DESIGN.md writer + i18n essentials. Each skill ships with packaged cognitive knowledge snapshots, no external vault dependency.
PPT production toolkit: route presentation requests across HTML showcase, image assets, editable PPTX, fixed-template fill, and verification.
Experiment Planning Suite is an agent plugin for turning early academic ideas, partial evidence, benchmark notes, and resource constraints into a concrete experiment plan.
It is not an experiment runner. It helps an agent write a verifiable planning surface under knowledge/experiment-plan/, then hands execution planning to a task-ledger workflow such as req-suite.
Author: Kunkun
plugins/experiment-planning-suite/
├── .claude-plugin/plugin.json
├── .codex-plugin/plugin.json
├── README.md
├── references/workflow-profile.md
└── skills/
├── orchestrator/
├── research-claim-snapshot/
├── evidence-chain-planner/
├── baseline-ablation-designer/
├── figure-table-planner/
├── feasibility-salvage-gate/
└── req-experiment-handoff/
experiment-planning-suite.experiment-planning-suite:orchestrator on a project folder that contains research notes, benchmark notes, drafts, or early requirements.Example request:
Use experiment-planning-suite:orchestrator to read this project and write a paper-level experiment plan under knowledge/experiment-plan/.
knowledge/experiment-plan/
├── research-claim-snapshot.md
├── paper-level-assessment.md
├── claim-evidence-map.md
├── experiment-matrix.md
├── baseline-ablation-plan.md
├── figure-table-plan.md
├── feasibility-salvage-plan.md
├── req-handoff.md
├── machine/
│ ├── verifier-contracts.yaml
│ ├── experiment-artifacts.schema.json
│ └── stop-conditions.yaml
└── data-schema/
├── metrics-table.schema.md
├── figure-data-fields.md
└── screenshot-evidence-schema.md
This repository does not include maintainer-owned API keys, private project files, customer materials, or generated experiment logs. Users should configure any required tools locally.
See:
MIT