yzsp-studio/mediakit-shared-suite / verifier-hub
verifier-hub
VerifiedDeterministic artifact verifier CLI (file/xlsx/docx/pdf/pptx/text/archive/rubric) for pre-delivery artifact checks and agentic judges. 58 subcommands callable as `verifier {family} {subcmd} [args]`. Use before delivering or uploading a file, or whenever you need to check file format, sheet/section presence, cell values, formulas, keywords, character counts, page counts, placeholders, signatures or zip contents, instead of guessing from an LLM reading. Every call prints one JSON object with a quotable `evidence` field.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 3.9 KB |
| SKILL.md | skill md | 8.5 KB |
| bin/verifier | other | 8.2 KB |
| bin/verifier.cmd | script | 482 B |
| lib/__init__.py | script | 299 B |
| lib/_common.py | script | 14.3 KB |
| lib/_pdf_backend.py | script | 8.1 KB |
| lib/archive.py | script | 6.2 KB |
| lib/docx.py | script | 32.2 KB |
| lib/file_io.py | script | 10.3 KB |
| lib/pdf.py | script | 8.9 KB |
| lib/pptx.py | script | 11.1 KB |
| lib/rubric.py | script | 17.9 KB |
| lib/text.py | script | 21.9 KB |
| lib/xlsx.py | script | 25.7 KB |
| references/questionnaire.md | markdown | 4.1 KB |
| references/subcommands.md | markdown | 11.0 KB |
| requirements.txt | manifest | 2.3 KB |
README.md
View on GitHub# verifier-hub
Deterministic artifact verifier CLI. Used for pre-delivery self-checks by any
agent, and for evidence collection in questionnaire judging mode.
This hub is **read-only / inspection-only**. It never creates or modifies the
files it inspects. It opens xlsx / docx / pdf / pptx / text / zip files and
reports structural and content facts as JSON, so an agent can collect evidence
without parsing binary formats itself or guessing content from a flattened
text trajectory.
## Layout
```
verifier-hub/
├── SKILL.md # agent-facing entry point (kept short on purpose)
├── references/
│ ├── subcommands.md # all 58 subcommands, args + examples
│ └── questionnaire.md # judge-mode workflow (harness-provided scripts)
├── bin/verifier # single CLI dispatcher (argparse, 2-level subparsers)
├── lib/
│ ├── _common.py # JSON protocol, error codes, paths, file URIs,
│ │ # cross-platform binary lookup, install hints
│ ├── _pdf_backend.py # pymupdf / pdfplumber / pypdf behind one interface
│ ├── file_io.py # 4 cmds: artifact-list / validate / extract-text / count
│ ├── xlsx.py # 12 cmds: get-value / assert-value / eval-formula / ...
│ ├── docx.py # 12 cmds: outline / section-text / page-count / ...
│ ├── pdf.py # 4 cmds: pages / text-dump / cjk-check / count-images
│ ├── pptx.py # 4 cmds: list-slides / slide-text / find-slide / count-images
│ ├── text.py # 9 cmds: must-contain / count-matches / date-extract / ...
│ ├── archive.py # 2 cmds: zip-list / zip-check-entries
│ └── rubric.py # 11 high-level DSL primitives
├── requirements.txt
└── README.md
```
## Output protocol
Every invocation writes exactly one JSON object to stdout, including bad
arguments and unknown family names:
```json
{"ok": true, "tool": "xlsx.get-value", "result": {...}, "evidence": {...}}
{"ok": false, "tool": "xlsx.get-value", "error": {"code": "FILE_NOT_FOUND", "msg": "..."}}
```
`ok` reports whether the tool ran. The check verdict lives in `result.passed`,
so a file that fails its check is `ok: true` + `result.passed: false`.
`--help` is the only invocation that prints prose instead of JSON.
`evidence` is meant to be quoted verbatim; it always references the file and
locator that produced the finding, so the quote carries its own provenance.
## PDF backends
`lib/_pdf_backend.py` tries `pymupdf`, then `pdfplumber`, then `pypdf`, and
records the winner in each result's `backend` field. Only one of the three
needs to be installed. pymupdf is preferred because it is already present in
the rollout VM image and covers geometry, text, fonts and images on its own.
## Platform support
Linux and macOS. Windows is not supported: `bin/verifier` is an extension-less
shebang script, so `cmd.exe` and PowerShell cannot execute it directly. The
Python code itself is portable (no POSIX-only syscalls, all file I/O is
explicitly utf-8, all paths go through `pathlib`/`os.path`, `file://` URIs are
built with `as_uri()`), so `python bin/verifier ...` does work if you need it.
## Local development
```bash
cd verifier-hub
pip install -r requirements.txt
./bin/verifier --help
./bin/verifier xlsx --help
./bin/verifier xlsx get-value sample.xlsx --sheet Sheet1 --cell A1
```
## Packaging
The zip published to TOS contains `bin/`, `lib/`, `references/`, `SKILL.md`,
`requirements.txt` and `README.md` at the top level — no wrapper directory,
because the installer creates the per-skill directory from the zip name.
`__pycache__` and test fixtures are excluded: the VM runs Python 3.10 and
would ignore bytecode compiled elsewhere anyway.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| canvas-designanthropics/skillsCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| docxanthropics/skillsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| pdfanthropics/skillsUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| pptxanthropics/skillsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |