Sep

What it does

When your agent uses it

• : delimited data needs are performance-sensitive and allocation-aware
• Project needs explicit control over separator inference
• Header behavior
• : unrelated stacks

Example prompts

• “/sep”

Requirements

• Compatibility (from SKILL.md): Requires a .NET project that can reference the `Sep` package and accept span/ref-struct row/column APIs for row-by-row processing.

Workflow steps

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

1. 1Decide schema shape
2. 2Build reader with Sep.Reader(...) and explicit options only where needed
3. 3Read rows and map columns as ReadOnlySpan first, convert only when needed.
4. 4For output, use reader.Spec.Writer() when you need the same separator/culture as input.
5. 5Control writer behavior with Sep.Writer(...) and SepWriterOptions (WriteHeader, Escape, DisableColCountCheck).
6. 6Add async only where it brings value and your runtime is C# 13 / .NET 9+ for await foreach over async reader rows.
7. 7Use ParallelEnumerate for CPU-heavy transformations only after benchmarking single-threaded baseline.

What it can do on your machine

Read from SKILL.md and the folder at commit 535dd55. 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:

  • dotnet

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

• Network

  Links to these hosts (documentation or services it may open):

  • nuget.org
  • github.com

  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.

• Compatibility

  Requires a .NET project that can reference the `Sep` package and accept span/ref-struct row/column APIs for row-by-row processing.

  From compatibility in the SKILL.md frontmatter.

Context cost

Sep loads about 1.4k tokens when it runs, and up to ~1.7k if it reads all its reference files. Until then it costs about 148 tokens; SKILL.md has 430 words of instructions outside code blocks.

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

~148

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

~1.4k

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

~1.7k

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 managedcode/dotnet-skills at commit 535dd55, republished under its MIT licence (© managedcode). 430 words, ~1,388 tokens.

name

sep

description

Use Sep for high-performance separated-value parsing and writing in .NET, including delimiter inference, explicit parser/writer options, and low-allocation row/column workflows. USE FOR: delimited data needs are performance-sensitive and allocation-aware; project needs explicit control over separator inference, escaping, trimming, and header behavior;. DO NOT USE FOR: unrelated stacks; generic tasks that do not need this specific guidance. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.

compatibility

Requires a .NET project that can reference the `Sep` package and accept span/ref-struct row/column APIs for row-by-row processing.

flowchart LR
  A[Input source: file/text/stream] --> B[Sep.Reader or Sep.New(...).Reader]
  B --> C[SepReaderOptions]
  C --> D[Rows -> Cols -> Span/Parse]
  D --> E[Transform and validate]
  E --> F[SepWriter via SepWriterOptions]
  F --> G[To file/text output]

using var reader = Sep.Reader(o => o with
{
    HasHeader = true,
    Unescape = true,
    Trim = SepTrim.Both
}).FromText(data);

foreach (var row in reader)
{
    var id = row["Id"].Parse<int>();
    var name = row[1].ToString();
    // process row
}

using var reader = Sep.Reader().FromFile("input.csv");
using var writer = reader.Spec.Writer().ToFile("output.csv");

foreach (var row in reader)
{
    using var writeRow = writer.NewRow(row);
    writeRow["Amount"].Format(row["Amount"].Parse<double>() * 1.2);
}

var text = "A;B\n1;hello\n";

using var reader = await Sep.Reader().FromTextAsync(text);
await using var writer = reader.Spec.Writer().ToText();

await foreach (var row in reader)
{
    await using var writeRow = writer.NewRow(row);
    var normalized = row["B"].ToString().ToUpperInvariant();
    writeRow["B"].Set(normalized);
}

© managedcode, MIT. 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 catalog/Libraries/Sep/skills/sep of managedcode/dotnet-skills.

• SKILL.md
• manifest.json
• references/overview.md

Open the folder on GitHubat commit 535dd55