一键导入
agent-behavior
Use before non-trivial ARIA-NBV work to choose a lane, state assumptions, inspect owners, keep diffs traceable, and verify.
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 before non-trivial ARIA-NBV work to choose a lane, state assumptions, inspect owners, keep diffs traceable, and verify.
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 | agent-behavior |
| description | Use before non-trivial ARIA-NBV work to choose a lane, state assumptions, inspect owners, keep diffs traceable, and verify. |
| metadata | {"mode":"router","not_when":["obvious one-line answer or command output with no durable edit"],"handoff_to":["aria-nbv-context for unknown local ownership","aria-litkg-memory for KG-backed routing or claim checks","diagnose-aria for concrete failures","plan-grill for ambiguous high-impact decisions"],"evidence_required":["root or nearest AGENTS.md for touched surface","request-traceable edit scope","surface-specific verification or explicit blocker"],"applies_to":["**"],"triggers":["non-trivial work","scaffold cleanup","memory or guidance edit"],"must_read":["AGENTS.md"],"canonical_sources":["AGENTS.md",".agents/references/source_order.md#capture-rule",".agents/references/skill_style_guide.md#required-frontmatter"],"verification":["surface-specific checks from .agents/references/verification_matrix.md","make check-agent-memory when agent guidance or memory changes"]} |
Apply this skill before non-trivial ARIA-NBV work. Keep it lightweight for obvious one-line fixes.
AGENTS.md or the active skill metadata, state why
it owns the work, and name the handoff if evidence disproves that choice.AGENTS.md, the nearest nested guide, or
the relevant skill.AGENTS.md.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 to localize unknown ARIA-NBV files, symbols, docs, or source families through deterministic local discovery before handoff.
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.