一键导入
aria-nbv-context
Use to localize unknown ARIA-NBV files, symbols, docs, or source families through deterministic local discovery before handoff.
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。
菜单
Use to localize unknown ARIA-NBV files, symbols, docs, or source families through deterministic local discovery before handoff.
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
Use for ARIA-NBV Typst proposal/thesis authoring, shared notation, scientific prose, citations, scientific/geometric figures, tables, Mermaid inclusion, and compile/render QA.
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools.
Use when reviewing ARIA-NBV working-tree or PR diffs, following up external/model review findings, or supplying ARIA-NBV domain context to the oh-my-codex code-review harness with severity-ranked file and line findings.
Use to diagnose ARIA-NBV bugs, regressions, failing metrics, Streamlit issues, docs builds, KG failures, or suspicious outputs.
Use when ARIA-NBV work touches pose, camera, coordinate-frame, CW90, PyTorch3D projection, depth backprojection, candidate frusta, or geometry diagnostics contracts.
Stress-test vague, high-impact, research-facing, advisor-facing, or cross-surface ARIA-NBV decisions before implementation, including theory-rich or elaborate Plan Mode option analysis when requested.
| name | aria-nbv-context |
| description | Use to localize unknown ARIA-NBV files, symbols, docs, or source families through deterministic local discovery before handoff. |
| metadata | {"mode":"router","not_when":["exact file and owner are already known","KG-backed authority, freshness, or claim checking is required","a concrete failure command or traceback owns the task"],"handoff_to":["aria-litkg-memory for KG-backed retrieval, routing, or claim checks","diagnose-aria for concrete failures","nearest AGENTS.md or narrow skill after localization"],"evidence_required":["localized owning files or source family","nearest applicable AGENTS.md","targeted rg or generated context evidence"],"applies_to":["**"],"triggers":["locate files","cross-surface context","where is this implemented","source family"],"must_read":["AGENTS.md",".agents/references/source_order.md"],"canonical_sources":["AGENTS.md",".agents/references/source_order.md#role-split",".agents/skills/aria-nbv-context/references/context_map.md"],"literature_refs":["docs/contents/literature/index.qmd","docs/literature/sources.jsonl","quality-driven-rri","finite-candidate-rl"],"tool_refs":["mcp__code_index.search_code_advanced","mcp__code_index.get_symbol_body"],"verification":["make context when generated context is stale or missing"]} |
Use this skill as the local discovery layer. It should identify the smallest relevant set of files, then hand off to a narrower implementation, docs, KG, or diagnostic workflow.
AGENTS.md and .agents/references/source_order.md.docs/_generated/context/source_index.md only when it already exists or
source-family routing is unclear; refresh with make context only when
needed.scripts/nbv_qmd_outline.sh --compactscripts/nbv_typst_includes.py --paper --mode outlinescripts/nbv_literature_index.shscripts/nbv_get_context.sh modules|contracts|match <term>AGENTS.md once the surface is known.rg inside the narrowed file set.When asked to map a surface, return:
AGENTS.mdreferences/context_map.md for non-obvious concept-to-source routing.