Skip to content

nexu-io/open-design / plugins/_official/examples/hps-academic-paper

hps-academic-paper

Verified

A review deck on compositional generalization in large language models — the field map, the gap, the evidence, and open questions. Built as a decision-grade academic research deck for PI, lab group, reviewers.

FileKindSize
LICENSEother1.1 KB
SKILL.mdskill md9.9 KB
example.htmlother28.9 KB
open-design.jsonconfig5.5 KB

open-design.json

View on GitHub
{
  "$schema": "https://open-design.ai/schemas/plugin.v1.json",
  "specVersion": "1.0.0",
  "name": "example-hps-academic-paper",
  "title": "Write an Academic Review Deck like a Top-Journal Survey Author",
  "title_i18n": {
    "en": "Write an Academic Review Deck like a Top-Journal Survey Author",
    "zh-CN": "像顶刊综述作者一样写学术报告",
    "zh-TW": "像顶刊综述作者一样写学术报告"
  },
  "version": "1.0.0",
  "publishedAt": "2026-06-16T09:32:15Z",
  "description": "A review deck on compositional generalization in large language models — the field map, the gap, the evidence, and open questions. Built as a decision-grade academic research deck for PI, lab group, reviewers.",
  "description_i18n": {
    "en": "A review deck on compositional generalization in large language models — the field map, the gap, the evidence, and open questions. Built as a decision-grade academic research deck for PI, lab group, reviewers.",
    "zh-CN": "像顶刊综述作者一样写学术报告——一份可商业交付的学术研究 Deck,围绕真实主题、证据链与决策目标组织。",
    "zh-TW": "像顶刊综述作者一样写学术报告——一份可商业交付的学术研究 Deck,围绕真实主题、证据链与决策目标组织。"
  },
  "license": "MIT",
  "author": {
    "name": "lewislulu",
    "url": "https://github.com/lewislulu"
  },
  "homepage": "https://github.com/lewislulu/html-ppt-skill",
  "plugin": {
    "repo": "https://github.com/lewislulu/html-ppt-skill"
  },
  "tags": [
    "community",
    "deck",
    "slides",
    "presentation",
    "academic",
    "paper",
    "serif",
    "latex",
    "light",
    "ai",
    "copilot",
    "workflow",
    "hps-academic-paper",
    "enterprise-ai-literacy",
    "research",
    "grant",
    "review",
    "academic-research",
    "academic-review-deck",
    "decision-deck",
    "commercial-slide-agent"
  ],
  "compat": {
    "agentSkills": [
      {
        "path": "./SKILL.md"
      }
    ]
  },
  "od": {
    "kind": "scenario",
    "taskKind": "new-generation",
    "mode": "deck",
    "scenario": "research",
    "surface": "web",
    "preview": {
      "type": "html",
      "entry": "./example.html",
      "motion": "deck"
    },
    "useCase": {
      "query": {
        "en": "Create \"Write an Academic Review Deck like a Top-Journal Survey Author\" as a decision-grade Academic research deck in this template's own visual system. Subject: A review deck on compositional generalization in large language models — the field map, the gap, the evidence, and open questions. Audience: PI, lab group, reviewers. First ask only for missing essentials: audience, decision target, source-of-truth materials, deadline, and must-keep numbers. Then produce the slide plan, written slides, visual direction, speaker-ready structure, and a critic pass against this rubric: does the deck prove novelty without overclaiming.",
        "zh-CN": "像顶刊综述作者一样写学术报告。像顶刊综述作者一样写学术报告——一份可商业交付的学术研究 Deck,围绕真实主题、证据链与决策目标组织。 主题:A review deck on compositional generalization in large language models — the field map, the gap, the evidence, and open questions. 先确认受众、决策目标、素材来源、截止时间和必须保留的数据,再输出叙事主线、页面规划、逐页文案、视觉方向和按评审标准自检的版本。"
      },
      "exampleOutputs": [
        {
          "path": "./example.html",
          "title": "Write an Academic Review Deck like a Top-Journal Survey Author",
          "title_i18n": {
            "en": "Write an Academic Review Deck like a Top-Journal Survey Author",
            "zh-CN": "像顶刊综述作者一样写学术报告",
            "zh-TW": "像顶刊综述作者一样写学术报告"
          }
        }
      ]
    },
    "inputs": [
      {
        "name": "topic",
        "label": "Topic",
        "type": "string",
        "required": true,
        "placeholder": "A paper, a thesis chapter, a research review, a journal-club pick…",
        "default": "the user's brief"
      },
      {
        "name": "audience",
        "label": "Audience",
        "type": "string",
        "required": true,
        "placeholder": "Conference session, thesis committee, lab group, students…",
        "default": "an academic audience"
      },
      {
        "name": "slideCount",
        "label": "Length",
        "type": "select",
        "required": true,
        "options": [
          "short 8-11 slides",
          "medium 12-18 slides",
          "long 18+ slides"
        ],
        "default": "short 8-11 slides"
      },
      {
        "name": "density",
        "label": "Density",
        "type": "select",
        "required": true,
        "options": [
          "low density / talk-led",
          "high density / reading-first"
        ],
        "default": "low density / talk-led"
      }
    ],
    "context": {
      "skills": [
        {
          "path": "./SKILL.md"
        }
      ],
      "assets": [
        "./example.html"
      ]
    },
    "pipeline": {
      "stages": [
        {
          "id": "discovery",
          "atoms": [
            "discovery-question-form"
          ]
        },
        {
          "id": "generate",
          "atoms": [
            "file-write",
            "live-artifact"
          ]
        }
      ]
    },
    "capabilities": [
      "prompt:inject",
      "fs:write"
    ],
    "category": "academic-research"
  }
}
add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks.Stars: 115kUpdated Claude CodeCodexVerifiedInstall