nihaisha

From the files and frontmatter at commit 3dc81ef. This is how much a skill can do, not whether it is risky.

• Touches credentials

  It reads, asks for or contains keys, tokens, passwords or similar secrets.

  .env.example:2 (opens in a new tab) · .gitignore:232 (opens in a new tab)

• 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.

  Outside links we did not follow

• Bundles scripts

  The folder holds code files the agent may run.

  evals/scripts/aggregate_v1.py (opens in a new tab) · evals/scripts/expand_multidimensional_v1.py (opens in a new tab) · evals/scripts/merge_incremental_v1.py (opens in a new tab) and 21 more

Pattern check: 14 items to review · commit 3dc81ef · 3 Nov 2026

• R21 · HighPadding, or a file too large to read

  evals/answer_eval_judgments_v1.jsonl (opens in a new tab)

  evals/answer_eval_judgments_v1.jsonl is too large to read in full

• R21 · HighPadding, or a file too large to read

  references/pdf-evidence/evidence-cards.jsonl (opens in a new tab)

  references/pdf-evidence/evidence-cards.jsonl is too large to read in full

• R21 · HighPadding, or a file too large to read

  references/pdf-evidence/modules/acupuncture.md (opens in a new tab)

  references/pdf-evidence/modules/acupuncture.md is too large to read in full

• R21 · HighPadding, or a file too large to read

  references/pdf-evidence/modules/bencao.md (opens in a new tab)

  references/pdf-evidence/modules/bencao.md is too large to read in full

• R21 · HighPadding, or a file too large to read

  references/pdf-evidence/modules/classics.md (opens in a new tab)

  references/pdf-evidence/modules/classics.md is too large to read in full

• R21 · HighPadding, or a file too large to read

  references/pdf-evidence/modules/huangdi.md (opens in a new tab)

  references/pdf-evidence/modules/huangdi.md is too large to read in full

• R21 · HighPadding, or a file too large to read

  references/pdf-evidence/modules/jingui.md (opens in a new tab)

  references/pdf-evidence/modules/jingui.md is too large to read in full

• R21 · HighPadding, or a file too large to read

  references/pdf-evidence/modules/shanghan.md (opens in a new tab)

  references/pdf-evidence/modules/shanghan.md is too large to read in full

• R21 · HighPadding, or a file too large to read

  references/pdf-evidence/term-index/acupuncture.json (opens in a new tab)

  references/pdf-evidence/term-index/acupuncture.json is too large to read in full

• R21 · HighPadding, or a file too large to read

  references/pdf-evidence/term-index/bencao.json (opens in a new tab)

  references/pdf-evidence/term-index/bencao.json is too large to read in full

We checked every text file in this skill, at commit 3dc81ef 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 specPasses

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

  • Note

    Anthropic's packaging script leaves these out: evals/. F8

    Fix: Delete them, or list them in .gitignore.

  • Note

    The first sentence of the description is 619 characters. Agents shorten long descriptions, so lead with the main job. D8

    Fix: Start with one short sentence that names the job.

  • 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: docs/BUILD_AND_UPDATE.md, docs/USE_AND_RISK_NOTICE.md (linked only from docs/RAG_GRAPH_MODE.md), evals/answer_eval_rubric_v1.md, references/notes-acupuncture-dacheng-scan-essence.md, references/notes-bencao-scan-essence.md and 6 more. 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: docs/RAG_GRAPH_MODE.md (101 lines), docs/USE_AND_RISK_NOTICE.md (126 lines), evals/answer_eval_rubric_v1.md (142 lines), references/acupuncture-screenshot-evidence.md (1143 lines), references/acupuncture.md (643 lines) and 28 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

    Anthropic's packaging script leaves these out: evals/. F8

    Fix: Delete them, or list them in .gitignore.

  • Note

    The first sentence of the description is 619 characters. Agents shorten long descriptions, so lead with the main job. D8

    Fix: Start with one short sentence that names the job.

  • Note

    Reference files that SKILL.md doesn't link: docs/BUILD_AND_UPDATE.md, docs/USE_AND_RISK_NOTICE.md (linked only from docs/RAG_GRAPH_MODE.md), evals/answer_eval_rubric_v1.md, references/notes-acupuncture-dacheng-scan-essence.md, references/notes-bencao-scan-essence.md and 6 more. 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: docs/RAG_GRAPH_MODE.md (101 lines), docs/USE_AND_RISK_NOTICE.md (126 lines), evals/answer_eval_rubric_v1.md (142 lines), references/acupuncture-screenshot-evidence.md (1143 lines), references/acupuncture.md (643 lines) and 28 more. 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

    The skill is 145.6 MB uncompressed; the Claude API accepts at most 30 MB. F6

    Fix: Move large files out of the skill or link to them.

  • Note

    Anthropic's packaging script leaves these out: evals/. F8

    Fix: Delete them, or list them in .gitignore.

  • Note

    The description is 792 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: docs/BUILD_AND_UPDATE.md, docs/USE_AND_RISK_NOTICE.md (linked only from docs/RAG_GRAPH_MODE.md), evals/answer_eval_rubric_v1.md, references/notes-acupuncture-dacheng-scan-essence.md, references/notes-bencao-scan-essence.md and 6 more. 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: docs/RAG_GRAPH_MODE.md (101 lines), docs/USE_AND_RISK_NOTICE.md (126 lines), evals/answer_eval_rubric_v1.md (142 lines), references/acupuncture-screenshot-evidence.md (1143 lines), references/acupuncture.md (643 lines) and 28 more. B5

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

• OpenAI (Codex & API)Fails

  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.

  • Error

    The skill has 3107 files; OpenAI's Skills API accepts at most 500 per version. F7

    Fix: Remove files the skill does not need.

  • Error

    Over OpenAI's 25 MB limit per file: references/pdf-evidence/evidence-cards.jsonl (28.9 MB). F7

    Fix: Shrink or remove those files.

  • Warning

    The skill is 145.6 MB uncompressed, so its zip may exceed OpenAI's 50 MB limit unless it compresses well. F7

    Fix: Remove large files the skill does not need.

  • Note

    Anthropic's packaging script leaves these out: evals/. F8

    Fix: Delete them, or list them in .gitignore.

  • Note

    The first sentence of the description is 619 characters. Agents shorten long descriptions, so lead with the main job. D8

    Fix: Start with one short sentence that names the job.

• 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

    Anthropic's packaging script leaves these out: evals/. F8

    Fix: Delete them, or list them in .gitignore.

500 files