proof-orchestrator

From the files and frontmatter at commit 8dd077b. 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

• Pre-approves tools

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

  SKILL.md:4 (opens in a new tab)

Pattern check: 1 item to review · commit 8dd077b · 31 Oct 2026

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

  SKILL.md:4 (opens in a new tab)

  allowed-tools: Read, Grep, Glob, Write, Edit, Skill(call-gpt-pro), mcp__llm_chat__chat, Skill(lean-formalize)

We checked every text file in this skill, at commit 8dd077b on 31 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

    Paths that may not work once the skill is installed: line 130: ../lean-formalize/SKILL.md (outside the skill folder). B6

    Fix: Use forward-slash paths relative to SKILL.md, and copy shared files into the skill.

  • 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: NOTICE.md, references/dispatch-prompts.md and references/stress-tests.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: references/audit-output-contract.md (127 lines), references/dispatch-prompts.md (228 lines) and references/notation-audit.md (136 lines). B5

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

• Claude CodePasses with warnings

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

  • Warning

    Paths that may not work once the skill is installed: line 130: ../lean-formalize/SKILL.md (outside the skill folder). B6

    Fix: Use forward-slash paths relative to SKILL.md, and copy shared files into the skill.

  • Note

    Reference files that SKILL.md doesn't link: NOTICE.md, references/dispatch-prompts.md and references/stress-tests.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: references/audit-output-contract.md (127 lines), references/dispatch-prompts.md (228 lines) and references/notation-audit.md (136 lines). B5

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

• Claude apps & API uploadPasses with warnings

  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.

  • Warning

    Paths that may not work once the skill is installed: line 130: ../lean-formalize/SKILL.md (outside the skill folder). B6

    Fix: Use forward-slash paths relative to SKILL.md, and copy shared files into the skill.

  • Note

    The description is 461 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: NOTICE.md, references/dispatch-prompts.md and references/stress-tests.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: references/audit-output-contract.md (127 lines), references/dispatch-prompts.md (228 lines) and references/notation-audit.md (136 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

    Paths that may not work once the skill is installed: line 130: ../lean-formalize/SKILL.md (outside the skill folder). B6

    Fix: Use forward-slash paths relative to SKILL.md, and copy shared files into the skill.

• 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

    Paths that may not work once the skill is installed: line 130: ../lean-formalize/SKILL.md (outside the skill folder). B6

    Fix: Use forward-slash paths relative to SKILL.md, and copy shared files into the skill.

8 files