菜单
Use this skill when you need deep verification of slide-5 interaction claims, continuous ArXiv/GitHub research on real-time social avatars, and self-evolving architecture guidance across MetaHuman, video generation, and Gaussian splatting.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | full-modality-social-evolver |
| description | Use this skill when you need deep verification of slide-5 interaction claims, continuous ArXiv/GitHub research on real-time social avatars, and self-evolving architecture guidance across MetaHuman, video generation, and Gaussian splatting. |
This skill runs repeatable research cycles to keep a full-modality social avatar stack current:
https://www.realtime-avatars.com/slides/5 against local source.Use this skill when the user asks for:
python .claude/skills/full-modality-social-evolver/scripts/evolve_social_modality_research.py--slide-url <url>--slide-source <path-relative-to-repo-root>--max-arxiv-per-query <n>--max-github-per-query <n>--no-publish to keep outputs local.GITHUB_TOKEN or GH_TOKEN.gh CLI is logged in, the runner auto-uses gh auth token for GitHub API calls.Local skill outputs:
.claude/skills/full-modality-social-evolver/references/latest-research.json.claude/skills/full-modality-social-evolver/references/latest-report.md.claude/skills/full-modality-social-evolver/references/latest-claim-check.json.claude/skills/full-modality-social-evolver/references/latest-architecture.json.claude/skills/full-modality-social-evolver/references/latest-dependency-graph.json.claude/skills/full-modality-social-evolver/references/latest-dependency-graph.mmd.claude/skills/full-modality-social-evolver/references/progress.md.claude/skills/full-modality-social-evolver/references/history/*.claude/skills/full-modality-social-evolver/state.json.claude/skills/full-modality-social-evolver/events.jsonlPublished mirrors (unless --no-publish):
web/public/docs/full-modality-research-latest.mdweb/public/docs/full-modality-research-latest.jsonweb/public/docs/full-modality-claim-check-latest.jsonweb/public/docs/full-modality-architecture-latest.jsonweb/public/docs/full-modality-dependency-graph-latest.jsonweb/public/docs/full-modality-dependency-graph-latest.mmdweb/public/docs/full-modality-research-progress.mdEach cycle must:
state.json and prior latest-research.json.state.json for next cycle query expansion.events.jsonl and append a narrative summary to progress.md.Do not delete history/events unless explicitly asked.
Use this skill when you need deep, repeatable multimodal inputs/outputs research across MetaHuman, video generation, and Gaussian splatting, with auto-updated conclusions in deep-research-multimodal_inputs_outputs.md.
Use this skill when you need to proofread research-focused slides, validate claims against primary-source links, avoid hallucinated metrics, and persist repeatable evidence-check history for future cycles.
Use this skill when a task asks for deeper MetaHuman understanding from Unreal source, architecture/module/function extraction, continuous MetaHuman documentation refreshes, or cumulative memory across repeated analysis cycles.
Use this skill when you need deep, repeatable research on realtime Gaussian avatars, continuous ArXiv/GitHub tracking, and auto-updated conclusions in deep-research-Realtime-Gaussian Avatars.md.
Use this skill when you need to continuously collect the latest YouTube research/demo videos for realtime Gaussian avatar systems, publish a curated video-wall dataset, and keep a self-evolving memory of queries/channels over repeated cycles.