nopua

Each tab says whether it installs commit 44010e0, the one we checked, or the latest version.

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/wuji-labs/nopua.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin 44010e045b7dd72b16d760ceefd7a8d408dabf37 &&
  git -C "$tmp" sparse-checkout set -- codex/nopua &&
  git -C "$tmp" checkout -q 44010e045b7dd72b16d760ceefd7a8d408dabf37 &&
  mkdir -p .claude/skills &&
  mkdir .claude/skills/nopua &&
  cp -R "$tmp"/codex/nopua/. .claude/skills/nopua/ &&
  rm -rf "$tmp"

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/wuji-labs/nopua.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin 44010e045b7dd72b16d760ceefd7a8d408dabf37 &&
  git -C "$tmp" sparse-checkout set -- codex/nopua &&
  git -C "$tmp" checkout -q 44010e045b7dd72b16d760ceefd7a8d408dabf37 &&
  out="$(mktemp -d)" &&
  cp -R "$tmp"/codex/nopua "$out"/nopua &&
  (cd "$out" && zip -qr - nopua) > nopua.zip &&
  rm -rf "$tmp" "$out"

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/wuji-labs/nopua.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin 44010e045b7dd72b16d760ceefd7a8d408dabf37 &&
  git -C "$tmp" sparse-checkout set -- codex/nopua &&
  git -C "$tmp" checkout -q 44010e045b7dd72b16d760ceefd7a8d408dabf37 &&
  mkdir -p .agents/skills &&
  mkdir .agents/skills/nopua &&
  cp -R "$tmp"/codex/nopua/. .agents/skills/nopua/ &&
  rm -rf "$tmp"

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/wuji-labs/nopua.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin 44010e045b7dd72b16d760ceefd7a8d408dabf37 &&
  git -C "$tmp" sparse-checkout set -- codex/nopua &&
  git -C "$tmp" checkout -q 44010e045b7dd72b16d760ceefd7a8d408dabf37 &&
  mkdir -p .cursor/skills &&
  mkdir .cursor/skills/nopua &&
  cp -R "$tmp"/codex/nopua/. .cursor/skills/nopua/ &&
  rm -rf "$tmp"

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/wuji-labs/nopua.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin 44010e045b7dd72b16d760ceefd7a8d408dabf37 &&
  git -C "$tmp" sparse-checkout set -- codex/nopua &&
  git -C "$tmp" checkout -q 44010e045b7dd72b16d760ceefd7a8d408dabf37 &&
  mkdir -p .github/skills &&
  mkdir .github/skills/nopua &&
  cp -R "$tmp"/codex/nopua/. .github/skills/nopua/ &&
  rm -rf "$tmp"

gh skill install wuji-labs/nopua codex/nopua/SKILL.md@44010e045b7dd72b16d760ceefd7a8d408dabf37 --agent github-copilot --scope project

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/wuji-labs/nopua.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin 44010e045b7dd72b16d760ceefd7a8d408dabf37 &&
  git -C "$tmp" sparse-checkout set -- codex/nopua &&
  git -C "$tmp" checkout -q 44010e045b7dd72b16d760ceefd7a8d408dabf37 &&
  mkdir -p .gemini/skills &&
  mkdir .gemini/skills/nopua &&
  cp -R "$tmp"/codex/nopua/. .gemini/skills/nopua/ &&
  rm -rf "$tmp"

gemini skills install https://github.com/wuji-labs/nopua.git --path codex/nopua --scope workspace

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/wuji-labs/nopua.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin 44010e045b7dd72b16d760ceefd7a8d408dabf37 &&
  git -C "$tmp" sparse-checkout set -- codex/nopua &&
  git -C "$tmp" checkout -q 44010e045b7dd72b16d760ceefd7a8d408dabf37 &&
  mkdir -p .agents/skills &&
  mkdir .agents/skills/nopua &&
  cp -R "$tmp"/codex/nopua/. .agents/skills/nopua/ &&
  rm -rf "$tmp"

npx skills@1.7.4 add wuji-labs/nopua --skill nopua

From the files and frontmatter at commit 44010e0. This is how much a skill can do, not whether it is risky.

What it can touch: Scripts or outside hosts

• Names web addresses

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

Pattern check: nothing flagged · commit 44010e0 · 27 Oct 2026

We checked every text file in this skill, at commit 44010e0 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

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 specPasses with warnings

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

  • Warning

    Fields outside the spec: version, author and homepage. 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.

  • Warning

    The body is about 7,047 tokens (approx.); the spec suggests under 5,000. B2

    Fix: Move detail into reference files that the agent reads only when needed.

  • 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, author and homepage. O1

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

  • Note

    The body is about 7,047 tokens (approx.); the spec suggests under 5,000. After compaction Claude Code keeps only the first 5,000 tokens of a skill. B2

    Fix: Move detail into reference files that the agent reads only when needed.

• 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

    Upload and packaging fail on fields outside the spec: version, author and homepage. O1

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

  • Note

    The description is 356 characters. The claude.ai Help Center says 200 at most, though Anthropic's API docs and validator allow 1,024. D4

    Fix: If the claude.ai upload refuses it, trim the description to 200 characters.

  • Note

    The body is about 7,047 tokens (approx.); the spec suggests under 5,000. Anthropic's guidance says the same. B2

    Fix: Move detail into reference files that the agent reads only when needed.

• OpenAI (Codex & API)Passes with warnings

  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.

  • Warning

    Fields outside the spec: version, author and homepage. 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

  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.

  • Note

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

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

1 file