office-hours

Each tab says whether it installs commit a50cf58, the one we checked, or the latest version.

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/garrytan/gstack.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin a50cf589656c0dc3f785af9b7c483861b13c8288 &&
  git -C "$tmp" sparse-checkout set -- office-hours &&
  git -C "$tmp" checkout -q a50cf589656c0dc3f785af9b7c483861b13c8288 &&
  mkdir -p .claude/skills &&
  mkdir .claude/skills/office-hours &&
  cp -R "$tmp"/office-hours/. .claude/skills/office-hours/ &&
  rm -rf "$tmp"

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/garrytan/gstack.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin a50cf589656c0dc3f785af9b7c483861b13c8288 &&
  git -C "$tmp" sparse-checkout set -- office-hours &&
  git -C "$tmp" checkout -q a50cf589656c0dc3f785af9b7c483861b13c8288 &&
  out="$(mktemp -d)" &&
  cp -R "$tmp"/office-hours "$out"/office-hours &&
  (cd "$out" && zip -qr - office-hours) > office-hours.zip &&
  rm -rf "$tmp" "$out"

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/garrytan/gstack.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin a50cf589656c0dc3f785af9b7c483861b13c8288 &&
  git -C "$tmp" sparse-checkout set -- office-hours &&
  git -C "$tmp" checkout -q a50cf589656c0dc3f785af9b7c483861b13c8288 &&
  mkdir -p .agents/skills &&
  mkdir .agents/skills/office-hours &&
  cp -R "$tmp"/office-hours/. .agents/skills/office-hours/ &&
  rm -rf "$tmp"

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/garrytan/gstack.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin a50cf589656c0dc3f785af9b7c483861b13c8288 &&
  git -C "$tmp" sparse-checkout set -- office-hours &&
  git -C "$tmp" checkout -q a50cf589656c0dc3f785af9b7c483861b13c8288 &&
  mkdir -p .cursor/skills &&
  mkdir .cursor/skills/office-hours &&
  cp -R "$tmp"/office-hours/. .cursor/skills/office-hours/ &&
  rm -rf "$tmp"

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/garrytan/gstack.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin a50cf589656c0dc3f785af9b7c483861b13c8288 &&
  git -C "$tmp" sparse-checkout set -- office-hours &&
  git -C "$tmp" checkout -q a50cf589656c0dc3f785af9b7c483861b13c8288 &&
  mkdir -p .github/skills &&
  mkdir .github/skills/office-hours &&
  cp -R "$tmp"/office-hours/. .github/skills/office-hours/ &&
  rm -rf "$tmp"

gh skill install garrytan/gstack office-hours/SKILL.md@a50cf589656c0dc3f785af9b7c483861b13c8288 --agent github-copilot --scope project

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/garrytan/gstack.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin a50cf589656c0dc3f785af9b7c483861b13c8288 &&
  git -C "$tmp" sparse-checkout set -- office-hours &&
  git -C "$tmp" checkout -q a50cf589656c0dc3f785af9b7c483861b13c8288 &&
  mkdir -p .gemini/skills &&
  mkdir .gemini/skills/office-hours &&
  cp -R "$tmp"/office-hours/. .gemini/skills/office-hours/ &&
  rm -rf "$tmp"

gemini skills install https://github.com/garrytan/gstack.git --path office-hours --scope workspace

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/garrytan/gstack.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin a50cf589656c0dc3f785af9b7c483861b13c8288 &&
  git -C "$tmp" sparse-checkout set -- office-hours &&
  git -C "$tmp" checkout -q a50cf589656c0dc3f785af9b7c483861b13c8288 &&
  mkdir -p .agents/skills &&
  mkdir .agents/skills/office-hours &&
  cp -R "$tmp"/office-hours/. .agents/skills/office-hours/ &&
  rm -rf "$tmp"

npx skills@1.7.4 add garrytan/gstack --skill office-hours

From the files and frontmatter at commit a50cf58. 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.

• Pre-approves tools

  Its allowed-tools field lists tools the agent may use without asking you first, in agents that honour it.

  SKILL.md:7

Pattern check: 1 item to review · commit a50cf58 · 26 Oct 2026

• R34 · HighBroad tools pre-approved in allowed-tools

  SKILL.md:7 (opens in a new tab)

  - Bash

We checked every text file in this skill, at commit a50cf58 on 26 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: preamble-tier, version, triggers and gbrain. 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

    allowed-tools is a list; the spec defines a space-separated string. gh skill publish rejects a list, though Claude Code accepts one. O5

    Fix: Write it on one line: allowed-tools: Bash Read Grep Glob Write Edit AskUserQuestion WebSearch

  • Warning

    The body is 1300 lines; the spec suggests under 500. B1

    Fix: Move detailed sections into reference files and link to them from SKILL.md.

  • Warning

    The body is about 23,232 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.

  • 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 over 100 lines with no table of contents at the top: sections/design-and-handoff.md (707 lines) and sections/phase-2a-startup-diagnostic.md (164 lines). 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

    Claude Code ignores fields it doesn't know: preamble-tier, version, triggers and gbrain. O1

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

  • Note

    The body is 1300 lines; the spec suggests under 500. Claude Code's docs say the same. B1

    Fix: Move detailed sections into reference files and link to them from SKILL.md.

  • Note

    The body is about 23,232 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.

  • Note

    Reference files over 100 lines with no table of contents at the top: sections/design-and-handoff.md (707 lines) and sections/phase-2a-startup-diagnostic.md (164 lines). B5

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

• 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: preamble-tier, version, triggers and gbrain. O1

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

  • Note

    allowed-tools is a list; the spec defines a space-separated string. O5

    Fix: Write it on one line: allowed-tools: Bash Read Grep Glob Write Edit AskUserQuestion WebSearch

  • Note

    The body is 1300 lines; the spec suggests under 500. Anthropic's guidance says the same. B1

    Fix: Move detailed sections into reference files and link to them from SKILL.md.

  • Note

    The body is about 23,232 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.

  • Note

    Reference files over 100 lines with no table of contents at the top: sections/design-and-handoff.md (707 lines) and sections/phase-2a-startup-diagnostic.md (164 lines). B5

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

• 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: preamble-tier, version, triggers and gbrain. 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.

  • Note

    allowed-tools is a list; the spec defines a space-separated string. O5

    Fix: Write it on one line: allowed-tools: Bash Read Grep Glob Write Edit AskUserQuestion WebSearch

• 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: preamble-tier, version, triggers and gbrain. O1

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

  • Note

    allowed-tools is a list; the spec defines a space-separated string. O5

    Fix: Write it on one line: allowed-tools: Bash Read Grep Glob Write Edit AskUserQuestion WebSearch

9 files