construct

From the files and frontmatter at commit b19db04. This is how much a skill can do, not whether it is risky.

• Runs shell commands

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

• Names web addresses

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

  Outside links we did not follow

• Bundles scripts

  The folder holds code files the agent may run.

  test_construct_skill.py (opens in a new tab)

Pattern check: 1 item to review · commit b19db04 · 3 Nov 2026

• R38 · HighName copied from another skill

  SKILL.md:2 (opens in a new tab)

  name: construct

We checked every text file in this skill, at commit b19db04 on 3 Nov 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 specFails

  The open format from agentskills.io, held to the strictest version of each rule among the agents we check.

  • Error

    The name "construct" doesn't match its folder "hermes_submission". The spec requires them to match. N4

    Fix: Set name: hermes-submission, or rename the folder to construct.

  • 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, author, platforms and prerequisites. 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

    metadata values should be text; hermes (a map) is not. The spec's validator turns them into text; other readers may not. O4

    Fix: Quote each value, for example version: "1.0".

  • Warning

    The body is about 5,150 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

    Reference files that SKILL.md doesn't link: PR.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.

• 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

    The name "construct" doesn't match its folder "hermes_submission". Claude Code shows the skill as /construct, and the folder name also invokes it. N4

    Fix: Set name: hermes-submission, or rename the folder to construct.

  • Note

    Claude Code ignores fields it doesn't know: version, author, platforms and prerequisites. O1

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

  • Note

    The body is about 5,150 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 that SKILL.md doesn't link: PR.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.

• 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 "construct" doesn't match its folder "hermes_submission". claude.ai refuses an upload whose folder name doesn't match the skill name. N4

    Fix: Set name: hermes-submission, or rename the folder to construct.

  • Error

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

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

  • Note

    metadata values should be text; hermes (a map) is not. The spec defines metadata as text to text. O4

    Fix: Quote each value, for example version: "1.0".

  • Note

    The body is about 5,150 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 that SKILL.md doesn't link: PR.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.

• 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

    The name "construct" doesn't match its folder "hermes_submission". OpenAI's own upload example uses a differently named folder, but the spec it follows says they must match. N4

    Fix: Set name: hermes-submission, or rename the folder to construct.

  • Warning

    Fields outside the spec: version, author, platforms and prerequisites. 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.

  • Warning

    metadata values should be text; hermes (a map) is not. OpenAI's upload follows the spec's text-to-text rule. O4

    Fix: Quote each value, for example version: "1.0".

• 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 "construct" doesn't match its folder "hermes_submission". VS Code uses the folder name, hermes_submission, instead. N4

    Fix: Set name: hermes-submission, or rename the folder to construct.

  • Note

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

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

3 files