query — for Claude Code labwiki, community, for Claude Code, ide skills, Answer, following, question, ARGUMENTS, Follow, defined

v1.0.0

Sobre este Skill

Cenario recomendado: Ideal for AI agents that need answer the following question using the wiki: $arguments. Resumo localizado: A lightweight, LLM-maintained knowledge base for research. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

Recursos

Answer the following question using the wiki: $ARGUMENTS
Follow the Workflow: Query defined in CLAUDE.md. Use the tiered search strategy.
Tiered Search (stop as soon as you have enough)
Tier 1: Index scan (cheap)
Read wiki/index.md only. Check if the question can be answered from page titles and one-line

# Core Topics

tommy-fcy tommy-fcy
[0]
[0]
Updated: 4/8/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 8/11

This page remains useful for operators, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Original recommendation layer Concrete use-case guidance Explicit limitations and caution
Review Score
8/11
Quality Score
30
Canonical Locale
en
Detected Body Locale
en

Cenario recomendado: Ideal for AI agents that need answer the following question using the wiki: $arguments. Resumo localizado: A lightweight, LLM-maintained knowledge base for research. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

Por que usar essa habilidade

Recomendacao: query helps agents answer the following question using the wiki: $arguments. A lightweight, LLM-maintained knowledge base for research. This AI agent skill supports Claude Code, Cursor, and Windsurf

Melhor para

Cenario recomendado: Ideal for AI agents that need answer the following question using the wiki: $arguments.

Casos de Uso Práticos for query

Caso de uso: Applying Answer the following question using the wiki: $ARGUMENTS
Caso de uso: Applying Follow the Workflow: Query defined in CLAUDE.md. Use the tiered search strategy
Caso de uso: Applying Tiered Search (stop as soon as you have enough)

! Segurança e Limitações

  • Limitacao: Read wiki/index.md only. Check if the question can be answered from page titles and one-line descriptions alone.
  • Limitacao: If sufficient, answer immediately and stop. Do not read any other pages.
  • Limitacao: Only if Tier 2 is insufficient:

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.
  • - The underlying skill quality score is below the review floor.

Source Boundary

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

After The Review

Decide The Next Action Before You Keep Reading Repository Material

Killer-Skills should not stop at opening repository instructions. It should help you decide whether to install this skill, when to cross-check against trusted collections, and when to move into workflow rollout.

Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is query?

Cenario recomendado: Ideal for AI agents that need answer the following question using the wiki: $arguments. Resumo localizado: A lightweight, LLM-maintained knowledge base for research. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

How do I install query?

Run the command: npx killer-skills add tommy-fcy/labwiki/query. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for query?

Key use cases include: Caso de uso: Applying Answer the following question using the wiki: $ARGUMENTS, Caso de uso: Applying Follow the Workflow: Query defined in CLAUDE.md. Use the tiered search strategy, Caso de uso: Applying Tiered Search (stop as soon as you have enough).

Which IDEs are compatible with query?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for query?

Limitacao: Read wiki/index.md only. Check if the question can be answered from page titles and one-line descriptions alone.. Limitacao: If sufficient, answer immediately and stop. Do not read any other pages.. Limitacao: Only if Tier 2 is insufficient:.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add tommy-fcy/labwiki/query. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use query immediately in the current project.

! Reference-Only Mode

This page remains useful for installation and reference, but Killer-Skills no longer treats it as a primary indexable landing page. Read the review above before relying on the upstream repository instructions.

Upstream Repository Material

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Upstream Source

query

A lightweight, LLM-maintained knowledge base for research. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows. Answer the following

SKILL.md
Readonly
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
Supporting Evidence

Query Wiki

Answer the following question using the wiki: $ARGUMENTS

Follow the Workflow: Query defined in CLAUDE.md. Use the tiered search strategy.

Tiered Search (stop as soon as you have enough)

Tier 1: Index scan (cheap)

Read wiki/index.md only. Check if the question can be answered from page titles and one-line descriptions alone.

Examples that Tier 1 can handle:

  • "Do we have a page on X?" → check index
  • "How many papers have we ingested?" → count entries
  • "List all methods" → read Methods section

If sufficient, answer immediately and stop. Do not read any other pages.

Tier 2: Targeted read (moderate)

If Tier 1 is insufficient, identify the 3-5 most relevant pages from the index. Read only those pages. This handles most queries:

  • "What does paper X say about Y?"
  • "Explain concept Z"
  • "What method did experiment W use?"

If sufficient, answer and stop.

Tier 3: Broad search (expensive)

Only if Tier 2 is insufficient:

  • Use Grep across wiki/ for query terms to find additional pages
  • Read wiki/synthesis.md for cross-cutting themes
  • Read up to 10-15 pages total (hard cap)

This is for complex synthesis questions:

  • "Compare all methods for X"
  • "What contradictions exist in the literature?"
  • "Summarize everything we know about Y"

Synthesize

Compose an answer based on wiki content:

  • Cite sources with wikilinks: [[src-slug|Author et al. (Year)]]
  • Reference concept/method pages: [[slug]]
  • If wiki content is insufficient, explicitly state what's missing

Optionally File

If the answer is a significant synthesis or comparison worth preserving, ask:

"This analysis seems worth filing as a thread. Shall I create a thread page?"

If yes: create wiki/threads/{slug}.md, update index and log.

Habilidades Relacionadas

Looking for an alternative to query or another community skill for your workflow? Explore these related open-source skills.

Ver tudo

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

widget-generator

Logo of f
f

Gerar plugins de widgets personalizáveis para o sistema de feed do prompts.chat

flags

Logo of vercel
vercel

O Framework React

138.4k
0
Navegador

pr-review

Logo of pytorch
pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

98.6k
0
Desenvolvedor