Add Op

What it does

When your agent uses it

• Asked to define an operator schema
• Add inputs/outputs/attributes to an op
• Move an op to old.cc
• Bump an ops opset version

Example prompts

• “/add-op”

Requirements

• Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Move current schema from defs.cc to old.cc in the same domain directory
2. 2Create new version in defs.cc with the new opset version number
3. 3Update onnx/defs/operator_sets.h
4. 4Add a version converter adapter if behavior changed
5. 5Add upgrade/downgrade tests

What it can do on your machine

Read from SKILL.md and the folder at commit dc30c0b. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • python

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Add Op loads about 1.2k tokens when it runs, and up to ~1.8k if it reads all its reference files. Until then it costs about 60 tokens; SKILL.md has 313 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~60

When it runs · the whole SKILL.md, loaded when a task matches

~1.2k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from onnx/onnx at commit dc30c0b, republished under its Apache-2.0 licence (© onnx). 313 words, ~1,186 tokens.

name

add-op

description

Add a new ONNX operator or update an existing operator to a new opset version. Use when asked to define an operator schema, register an op, add inputs/outputs/attributes to an op, move an op to old.cc, or bump an op's opset version.

ONNX_OPERATOR_SET_SCHEMA(
    OperatorName,
    OPSET_VERSION,
    OpSchema()
        .SetDoc(OperatorName_verN_doc)
        .Input(0, "X", "Description", "T", OpSchema::Single, true, 1, OpSchema::Differentiable)
        .Output(0, "Y", "Description", "T", OpSchema::Single, true, 1, OpSchema::Differentiable)
        .Attr("attr_name", "Description", AttributeProto::FLOAT, default_value)
        .TypeConstraint("T", {"tensor(float)", "tensor(double)", ...}, "Description")
        .TypeAndShapeInferenceFunction(InferShapeForOperatorName)
        // Function body uses ONNX text format — see the onnxtxt skill for syntax/conventions.
        .FunctionBody(R"ONNX(
          {
            ...
          }
        )ONNX", FUNCTION_OPSET_VERSION));

// PREFERRED: named function — easy to set breakpoints
static void InferShapeForMyOp(InferenceContext& ctx) {
    propagateElemTypeFromInputToOutput(ctx, 0, 0);
    // ...
}

ONNX_OPERATOR_SET_SCHEMA(
    MyOp, 21,
    OpSchema()
        // ...
        .TypeAndShapeInferenceFunction(InferShapeForMyOp));

python onnx/defs/gen_doc.py
python onnx/backend/test/stat_coverage.py
python onnx/gen_proto.py  # only if proto changed
lintrunner -a --output oneline

© onnx, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in .agents/skills/add-op of onnx/onnx.

• SKILL.md
• references/node-test-pattern.md
• references/reference-impl-pattern.md

Open the folder on GitHubat commit dc30c0b