Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Wiki Query

ASecurity

Answer questions from the active project wiki by reading the index and relevant wiki pages.

2 stars
0 votes
0 copies
0 views
Added 9/23/2026
ai-agentsgo

Security Analysis

A100/100

Scanned 9/23/2026

Install to Claude Code

$npx -y skills add juanitourquiza/shipframe --skill wiki-query --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Wiki Query?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Wiki Query
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/juanitourquiza-wiki-query/badge)](https://www.skillsdirectory.com/skills/juanitourquiza-wiki-query)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: wiki-query
description: Answer questions from the active project wiki by reading the index and relevant wiki pages.
allowed-tools: Read Glob
effort: low
---

# wiki-query

Smart search in any LLM wiki vault.

Implements the QUERY flow of the LLM Wiki pattern: find information
in the wiki quickly and precisely, without unnecessary traversal.

Works with any vault that follows the standard LLM wiki structure,
regardless of the topic (a course, a project, personal notes, etc.).

---

## Step 0 — Discover the wiki

Before searching, locate the wiki in the current directory.
Look for a `wiki/` folder containing an `index.md` file. This file
is the master catalog and the mandatory entry point.

If `wiki/index.md` is not found, check if there is a `CLAUDE.md` at the
root — it may indicate where the wiki is or what the main folder is called.

If there is no wiki, tell the user: "I can't find a wiki in this folder.
Would you like me to create one?" (and if so, use the wiki-forge skill).

---

## Step 1 — Scan the index

Read `wiki/index.md`. This file lists all wiki pages with a one-line
summary each, organized by category (the wiki subdirectories).

From the index, identify the 1-3 pages most relevant to the user's question.
The key: the index already tells you what each page contains.
You don't need to open all of them — only the ones that fit.

---

## Step 2 — Read the relevant pages

Open only the pages identified in the previous step. Each page has:

- **YAML frontmatter**: tags, type, sources, dates — useful for filtering
- **Content**: the text with the information
- **Wikilinks** `[[page-name]]`: links to related pages

If a page references another via wikilink and that reference seems important
to complete the answer, open it too. But don't chain long read sequences —
2-3 pages are usually enough.

---

## Step 3 — Synthesize and answer

Answer the user's question citing the wiki pages consulted.
Natural and direct format. At the end, include the sources as references:

> Sources: [[page-name-1]], [[page-name-2]]

---

## When to go to the original sources

Many wikis have a `raw/` folder with raw materials
(transcripts, articles, original documents). These are immutable.

Only go to `raw/` if:

- The user asks for an exact verbatim quote
- The wiki doesn't have enough detail to answer
- You need to verify something specific

Pages in the `sources/` subfolder of the wiki are summaries of each
original source — they work as a bridge between the processed wiki and
the raw material. Check them first before going directly to `raw/`.

---

## What NOT to do

- **Do not grep or launch agents**. The index exists precisely
  to avoid brute-force searches. Use it.
- **Do not read all pages "just in case"**. Read the index, identify
  the relevant ones, and go directly.
- **Do not answer without consulting the wiki**. The purpose of this skill
  is that the answer comes from the pages, not from general knowledge.
- **Do not invent information**. If it's not in the wiki, say so clearly.
  You can suggest the user ingest new information with wiki-forge.

Attribution

juanitourquizajuanitourquiza
View sourceMore from juanitourquiza →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →