kami

Each tab says whether it installs commit 210f3bc, the one we checked, or the latest version.

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/tw93/Kami.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin 210f3bcc9c1a86e2b21455cc62ba31c56233b966 &&
  git -C "$tmp" sparse-checkout set -- plugins/kami/skills/kami &&
  git -C "$tmp" checkout -q 210f3bcc9c1a86e2b21455cc62ba31c56233b966 &&
  mkdir -p .claude/skills &&
  mkdir .claude/skills/kami &&
  cp -R "$tmp"/plugins/kami/skills/kami/. .claude/skills/kami/ &&
  rm -rf "$tmp"

claude plugin marketplace add tw93/Kami --scope project &&
  claude plugin install kami@kami --scope project

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/tw93/Kami.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin 210f3bcc9c1a86e2b21455cc62ba31c56233b966 &&
  git -C "$tmp" sparse-checkout set -- plugins/kami/skills/kami &&
  git -C "$tmp" checkout -q 210f3bcc9c1a86e2b21455cc62ba31c56233b966 &&
  out="$(mktemp -d)" &&
  cp -R "$tmp"/plugins/kami/skills/kami "$out"/kami &&
  (cd "$out" && zip -qr - kami) > kami.zip &&
  rm -rf "$tmp" "$out"

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/tw93/Kami.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin 210f3bcc9c1a86e2b21455cc62ba31c56233b966 &&
  git -C "$tmp" sparse-checkout set -- plugins/kami/skills/kami &&
  git -C "$tmp" checkout -q 210f3bcc9c1a86e2b21455cc62ba31c56233b966 &&
  mkdir -p .agents/skills &&
  mkdir .agents/skills/kami &&
  cp -R "$tmp"/plugins/kami/skills/kami/. .agents/skills/kami/ &&
  rm -rf "$tmp"

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/tw93/Kami.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin 210f3bcc9c1a86e2b21455cc62ba31c56233b966 &&
  git -C "$tmp" sparse-checkout set -- plugins/kami/skills/kami &&
  git -C "$tmp" checkout -q 210f3bcc9c1a86e2b21455cc62ba31c56233b966 &&
  mkdir -p .cursor/skills &&
  mkdir .cursor/skills/kami &&
  cp -R "$tmp"/plugins/kami/skills/kami/. .cursor/skills/kami/ &&
  rm -rf "$tmp"

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/tw93/Kami.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin 210f3bcc9c1a86e2b21455cc62ba31c56233b966 &&
  git -C "$tmp" sparse-checkout set -- plugins/kami/skills/kami &&
  git -C "$tmp" checkout -q 210f3bcc9c1a86e2b21455cc62ba31c56233b966 &&
  mkdir -p .github/skills &&
  mkdir .github/skills/kami &&
  cp -R "$tmp"/plugins/kami/skills/kami/. .github/skills/kami/ &&
  rm -rf "$tmp"

gh skill install tw93/Kami plugins/kami/skills/kami/SKILL.md@210f3bcc9c1a86e2b21455cc62ba31c56233b966 --agent github-copilot --scope project

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/tw93/Kami.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin 210f3bcc9c1a86e2b21455cc62ba31c56233b966 &&
  git -C "$tmp" sparse-checkout set -- plugins/kami/skills/kami &&
  git -C "$tmp" checkout -q 210f3bcc9c1a86e2b21455cc62ba31c56233b966 &&
  mkdir -p .gemini/skills &&
  mkdir .gemini/skills/kami &&
  cp -R "$tmp"/plugins/kami/skills/kami/. .gemini/skills/kami/ &&
  rm -rf "$tmp"

gemini skills install https://github.com/tw93/Kami.git --path plugins/kami/skills/kami --scope workspace

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/tw93/Kami.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin 210f3bcc9c1a86e2b21455cc62ba31c56233b966 &&
  git -C "$tmp" sparse-checkout set -- plugins/kami/skills/kami &&
  git -C "$tmp" checkout -q 210f3bcc9c1a86e2b21455cc62ba31c56233b966 &&
  mkdir -p .agents/skills &&
  mkdir .agents/skills/kami &&
  cp -R "$tmp"/plugins/kami/skills/kami/. .agents/skills/kami/ &&
  rm -rf "$tmp"

npx skills@1.7.4 add tw93/Kami --skill kami

From the files and frontmatter at commit 210f3bc. 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/mcp_server.py

• Installs more skills

  It tells the agent to install other skills, plugins or tool servers.

  scripts/shared.py:48 · scripts/mcp_server.py:13

Pattern check: 1 item to review · commit 210f3bc · 27 Oct 2026

• R27 · HighInstalls more skills or tool servers without asking

  scripts/shared.py:48 (opens in a new tab)

  GENERIC_AGENT_INSTALL_COMMAND = f"npx skills add {PUBLIC_REPO} -a claude-code codex cursor -g -y"

We checked every text file in this skill, at commit 210f3bc 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

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

  • Note

    There is no license field, so readers can't tell whether they may reuse the skill. O2

    Fix: Add license: with an SPDX name such as MIT or Apache-2.0, or the name of a bundled licence file.

  • Note

    Reference files that SKILL.md doesn't link: references/brand.example.md. Anthropic suggests linking every reference file directly from SKILL.md. B4

    Fix: Link each one from SKILL.md and say when to read it.

  • Note

    Reference files over 100 lines with no table of contents at the top: CHEATSHEET.md (371 lines), references/anti-patterns.md (108 lines), references/design.md (1545 lines), references/diagrams.md (693 lines), references/production.md (1092 lines) and 2 more. B5

    Fix: Add a short list of the sections at the top of each.

• 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

    Reference files that SKILL.md doesn't link: references/brand.example.md. Anthropic suggests linking every reference file directly from SKILL.md. B4

    Fix: Link each one from SKILL.md and say when to read it.

  • Note

    Reference files over 100 lines with no table of contents at the top: CHEATSHEET.md (371 lines), references/anti-patterns.md (108 lines), references/design.md (1545 lines), references/diagrams.md (693 lines), references/production.md (1092 lines) and 2 more. B5

    Fix: Add a short list of the sections at the top of each.

• Claude apps & API uploadPasses

  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.

  • Note

    The description is 270 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

    Reference files that SKILL.md doesn't link: references/brand.example.md. Anthropic suggests linking every reference file directly from SKILL.md. B4

    Fix: Link each one from SKILL.md and say when to read it.

  • Note

    Reference files over 100 lines with no table of contents at the top: CHEATSHEET.md (371 lines), references/anti-patterns.md (108 lines), references/design.md (1545 lines), references/diagrams.md (693 lines), references/production.md (1092 lines) and 2 more. B5

    Fix: Add a short list of the sections at the top of each.

• OpenAI (Codex & API)Passes
• VS Code & CopilotPasses

118 files