Name: lanceDB-viewer
Author: wufeng1740

Imported from wufeng1740/lanceDB-viewer (AGENTS.md). Install upstream with npx skills add wufeng1740/lanceDB-viewer. Copyright stays with the author.

Project AI Agent Entry

This file defines project-level agent behavior for all assistants used in this repository, including Codex, Claude, Gemini, Copilot, and Cursor-based agents.

Required startup sequence

Read this file first.
Read project rules under /.agent/rules/.
Discover skills from /.agent/skills/ by loading each SKILL.md in direct subfolders when relevant.
Apply only the minimal set of relevant skills for the current request.

Skill loading policy

Treat /.agent/skills/ as the project-level skill registry.
Do not hardcode to a single skill path.
If multiple skills apply, follow all applicable skills in a conflict-free way.
If a skill conflicts with repository rules, use this priority:

User request
AGENTS.md
Files in /.agent/rules/
Individual /.agent/skills/*/SKILL.md

Shared workflow artifacts

Store process artifacts in workspace/:
workspace/plan.md
workspace/task.md
workspace/review.md
Archive completed artifacts in workspace/archive/ with normalized names.

Codex-specific note

Codex should treat this file as the primary project entrypoint and must load relevant skills from /.agent/skills/ instead of relying only on global/default skills.

Install lanceDB-viewer and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

{ "ocm": "1", "id": "wufeng1740-lancedb-viewer-lancedb-viewer", "kind": "skill", "name": "lanceDB-viewer", "description": "This file defines project-level agent behavior for all assistants used in this repository, including Codex, Claude, Gemini, Copilot, and Cursor-based agents.", "publisher": "wufeng1740", "version": "1.0.0", "capabilities": { "domains": [ "general" ], "tags": [ "skill-md", "github-agents" ], "languages": [ "en" ] }, "quality_prior": 0.6, "examples": [ "This file defines project-level agent behavior for all assistants used in this repository, including Codex, Claude, Gemini, Copilot, and Cursor-based agents." ], "primary": false, "metadata": { "source": { "provider": "github-agents", "repository": "https://github.com/wufeng1740/lanceDB-viewer", "path": "AGENTS.md", "ref": "345394eea727b01f8aa3f4a9082cc5836de4739c", "url": "https://github.com/wufeng1740/lanceDB-viewer/blob/345394eea727b01f8aa3f4a9082cc5836de4739c/AGENTS.md", "key": "wufeng1740/lanceDB-viewer/AGENTS.md" } }, "instructions": "# Project AI Agent Entry\n\nThis file defines project-level agent behavior for all assistants used in this repository, including Codex, Claude, Gemini, Copilot, and Cursor-based agents.\n\n## Required startup sequence\n\n1. Read this file first.\n2. Read project rules under `/.agent/rules/`.\n3. Discover skills from `/.agent/skills/` by loading each `SKILL.md` in direct subfolders when relevant.\n4. Apply only the minimal set of relevant skills for the current request.\n\n## Skill loading policy\n\n- Treat `/.agent/skills/` as the project-level skill registry.\n- Do not hardcode to a single skill path.\n- If", "cost": { "context_tokens": 313 } }

lanceDB-viewer

About

Project AI Agent Entry

Required startup sequence

Skill loading policy

Shared workflow artifacts

Codex-specific note

Use it

Install lanceDB-viewer and it becomes one more candidate the router can pick - when it fits.

Manifest

Reviews