web_search

web_search is a skill in axoviq-ai/synthadoc, last changed 16 Sept 2026. It can run shell commands, reach the network, name web addresses and bundle scripts — read the findings before installing. Our pattern check flagged nothing at commit be1d2ee on 27 Oct 2026.

Pattern check: nothing flagged · commit be1d2ee · 27 Oct 2026

Install
From the author
Search the web and ingest results as wiki pages
Licence
AGPL 3.0 or later
Repo stars
1.6k
Publisher
axoviq-ai
Files
6 files
Checked
be1d2ee (opens in a new tab) · 27 Oct 2026

Install

Each tab says whether it installs commit be1d2ee, the one we checked, or the latest version.

No tab for your agent? Use Any agent for OpenCode, Goose, Windsurf (Devin Desktop), Zed, Roo Code, Factory Droid, Junie, Amp and Antigravity, and Claude Code for Cline. Kiro needs the folder copied by hand.

Pinned to commit be1d2ee, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/axoviq-ai/synthadoc.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin be1d2eeedc88e6adb16d23ec22c07eb37119faba &&
  git -C "$tmp" sparse-checkout set -- synthadoc/skills/web_search &&
  git -C "$tmp" checkout -q be1d2eeedc88e6adb16d23ec22c07eb37119faba &&
  mkdir -p .claude/skills &&
  mkdir .claude/skills/web_search &&
  cp -R "$tmp"/synthadoc/skills/web_search/. .claude/skills/web_search/ &&
  rm -rf "$tmp"

If Claude Code was already running and this created the skills folder, run /reload-skills.

Claude Code docs (opens in a new tab)

What it can touch

From the files and frontmatter at commit be1d2ee. This is how much a skill can do, not whether it is risky.

What it can touch: Shell, network or credentials

  • Runs shell commands

    Its instructions or files give the agent commands to run on your computer.

  • Reaches the network

    It sends or fetches data over the internet, for example with curl, an HTTP library or a package install.

  • Names web addresses

    It mentions outside web addresses the agent may visit. We list them but don't follow them.

  • Bundles scripts

    The folder holds code files the agent may run.

    scripts/__init__.py

Pattern check

Pattern check: nothing flagged · commit be1d2ee · 27 Oct 2026

We checked every text file in this skill, at commit be1d2ee on 27 Oct 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.

How the check worksReport an incorrect finding

Outside links we did not follow

  • https://tavily.com

Format check

Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.

  • Agent Skills specFails

    The open format from agentskills.io, held to what the strictest agents enforce, so one folder loads everywhere.

    • Error

      The name "web_search" has underscores. Names may use only a–z, 0–9 and single hyphens. N3

      Fix: Use name: web-search and rename the folder to match.

    • Warning

      The frontmatter uses [ ] or { } values. Most agents accept them, but the spec's validator (skills-ref) rejects the file. F4

      Fix: Write lists as "- item" lines and maps as indented key: value lines, without anchors or tags.

    • Warning

      Fields outside the spec: version, entry, triggers, requires and author. Uploads to the Claude apps and API, and the spec's validator, reject the file; most agents ignore these fields. O1

      Fix: Delete them for a portable skill, or keep them if you only target the agents that read them.

    • Note

      The description doesn't say when to use the skill. D6

      Fix: Add a sentence such as "Use when …" naming the requests or files that should trigger it.

  • Claude CodePasses

    Claude Code reads its own extra fields, ignores unknown ones, and still loads a skill whose frontmatter is broken, without its fields.

    • Note

      Claude Code ignores fields it doesn't know: version, entry, triggers, requires and author. O1

      Fix: Check the spelling against Claude Code's field list, or delete them.

  • Claude apps & API uploadFails

    Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.

    • Error

      The name "web_search" has underscores. Anthropic's validator allows only lowercase letters, digits and hyphens. N3

      Fix: Use name: web-search and rename the folder to match.

    • Error

      Upload and packaging fail on fields outside the spec: version, entry, triggers, requires and author. O1

      Fix: Delete them, and keep your own data under metadata as text values.

  • OpenAI (Codex & API)Fails

    Codex finds SKILL.md by its exact name and needs a description; OpenAI's Skills API checks the frontmatter against the spec and caps uploads.

    • Error

      The name "web_search" has underscores. OpenAI's upload follows the spec, which allows only a–z, 0–9 and hyphens. N3

      Fix: Use name: web-search and rename the folder to match.

    • Warning

      Fields outside the spec: version, entry, triggers, requires and author. Codex ignores them; OpenAI doesn't say whether its upload accepts them. O1

      Fix: Delete them, or move your own data under metadata as text values.

  • VS Code & CopilotPasses with warnings

    VS Code reads skills one folder below .github/skills, .claude/skills or .agents/skills and falls back to the folder name when the name is missing or differs; GitHub's Copilot docs require the exact name SKILL.md.

    • Warning

      The name "web_search" has underscores. VS Code uses the folder name whenever the name differs from it. N3

      Fix: Use name: web-search and rename the folder to match.

    • Note

      VS Code ignores fields it doesn't support: version, entry, triggers, requires and author. O1

      Fix: Delete them unless another agent you target reads them.

SKILL.md

We only show SKILL.md text here when its licence clearly allows it.

Read SKILL.md on GitHub (opens in a new tab)

Files

More from axoviq-ai/synthadoc

  • docx

    axoviq-ai/synthadoc

    Extract text from Microsoft Word documents

    • Runs shell commands
    • Reaches the network
    • +1 more
    Pattern check: Nothing flagged

    AGPL 3.0 or later · 1.6k repo stars · Updated 26 Jun 2026

  • image

    axoviq-ai/synthadoc

    Extract text from images using a vision LLM

    • Bundles scripts
    Pattern check: Nothing flagged

    AGPL 3.0 or later · 1.6k repo stars · Updated 26 Jun 2026

  • markdown

    axoviq-ai/synthadoc

    Ingest Markdown and plain text files

    • Bundles scripts
    Pattern check: Nothing flagged

    AGPL 3.0 or later · 1.6k repo stars · Updated 26 Jun 2026

  • pdf

    axoviq-ai/synthadoc

    Extract text from PDF documents

    • Runs shell commands
    • Reaches the network
    • +1 more
    Pattern check: Nothing flagged

    AGPL 3.0 or later · 1.6k repo stars · Updated 6 Jul 2026

  • pptx

    axoviq-ai/synthadoc

    Extract text from Microsoft PowerPoint presentations

    • Runs shell commands
    • Reaches the network
    • +1 more
    Pattern check: Nothing flagged

    AGPL 3.0 or later · 1.6k repo stars · Updated 26 Jun 2026

  • session

    axoviq-ai/synthadoc

    Extract conversation turns from AI session history files (.jsonl)

    • Bundles scripts
    Pattern check: Nothing flagged

    AGPL 3.0 or later · 1.6k repo stars · Updated 29 Jul 2026

All skills in axoviq-ai/synthadoc