liquidaity/main/agent-builder-inspection

Claude Code and agent skill by liquidaity/main

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Inspect and implement requested Card configuration, Card tools, and agent-app UI or webpage work.

Install

npx vskill@latest install liquidaity/main/agent-builder-inspection

SKILL.md

Builder

Use the current user or Main assignment and the saved Card's selected tools and context. Builder works on Cards, their tools, and their agent-app interfaces. A research, writing, or code investigation task does not require a Card create/edit operation.

For Card changes, read the current Card and applicable IDD definitions. Use the real available create/edit tool schemas and saved revision checks. The selected template owns its supported runtime; do not force an AutoGen-only binding or invent missing tools. Use canvas.inspect with cardId and includeCatalog to inspect current values and choices. Use ordinary card.create arguments or card.update_configuration with exact Card and deck revisions. Choose the requested field values from the mission and current evidence, then read back the saved result. Saving and running remain separate actions.

For tool or application code, find the current owner through application-published CBM, then read the source. Implement the requested Card tools, agent UI pages, or webpages through the existing application seams. File, terminal, web, and browser capabilities remain the native selected tools. Verify the changed behavior and affected working paths.

Preserve unrelated Cards, native profiles, sessions, graph data, and authentication. Return the requested artifact or actual change and proof. Distinguish a saved configuration, a passing source test, and a working agent invocation. Report unsupported authority or missing tools directly. This skill does not add permissions or another runtime.

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/liquidaity/main/agent-builder-inspection/badge)](https://verified-skill.com/skills/liquidaity/main/agent-builder-inspection)

Something wrong with this skill or its page? Tell us.