Comp3 Packed Decimal logo

Comp3 Packed Decimal

OrganizationPopular
benchflow-ai
comp3-packed-decimal

Reference for COBOL COMP-3 (packed decimal / BCD) numeric storage -- layout on disk, declaring it in the FD, and pitfalls when carrying the decoded value through working storage and into later arithmetic. Useful when an input record holds a balance, rate, or carry-forward as packed decimal rather than a printable digit string.

Overview

Publisherbenchflow-ai
Repositoryskillsbench
Skill namecomp3-packed-decimal
Stars
1.8K
Forks
367
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by benchflow-ai on GitHub. Read the source before you install it.

Installation

Install the Comp3 Packed Decimal AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/benchflow-ai/skillsbench.git /tmp/skillsbench
mkdir -p .claude/skills
cp -r /tmp/skillsbench/tasks-extra/cobol-gl-batch-reconcile/environment/skills/comp3-packed-decimal .claude/skills/comp3-packed-decimal
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Comp3 Packed Decimal in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Comp3 Packed Decimal on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Comp3 Packed Decimal is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

COMP-3 / packed decimal storage

USAGE COMP-3 (a.k.a. PACKED-DECIMAL) stores a signed numeric field as binary-coded-decimal nibbles: each byte holds two decimal digits, except the last byte whose low nibble is the sign:

PIC S9(11)V99 USAGE COMP-3
+--+--+--+--+--+--+--+
|D1|D2|D3|D4|D5|D6|D7|   7 bytes total for 13 digits
+--+--+--+--+--+--+--+
              ^^-- sign nibble in the LOW half of the last byte

Bytes-on-disk = ceil((digit_count + 1) / 2). For PIC S9(11)V99 that is ceil(14 / 2) = 7 bytes. The high nibble of the first byte holds the first decimal digit; the implied decimal point is not stored.

Sign nibbles:

NibbleMeaning
Cpositive (some shops emit F for unsigned, but C is standard for SIGNED)
Dnegative
Funsigned / non-S PIC

Declaring COMP-3 in an FD

The record layout must match the byte budget. If the data in the file is packed but you declare the field as PIC X(n) or as an unpacked decimal, the COBOL runtime will not decode it and the value will look like binary garbage when displayed.

cobol
FD  MAST-FILE
    RECORD CONTAINS 80 CHARACTERS.
01  MAST-REC.
    05  M-ACCT     PIC X(6).
    05  M-TYPE     PIC X.
    05  M-STATUS   PIC X.
    05  M-CCY      PIC X(3).
    05  M-CARRY    PIC S9(11)V99 USAGE COMP-3.   *> 7 bytes
    05  FILLER     PIC X(62).                    *> remainder of 80

Use a runtime check: cobc -x -free -o prog PROG.cbl && ./prog and DISPLAY one record's COMP-3 field before relying on it. Common mistakes:

  • Forgetting the USAGE COMP-3 clause -> the field is read as 7 zoned ASCII characters; values look like control characters.
  • Wrong digit count -> the byte budget changes and subsequent fields slide.
  • Moving COMP-3 directly into a PIC X(7) workspace -> the bytes copy but no arithmetic translation happens; the value is unusable.

Carrying the value through working storage

A common defect when there is an opening balance / carry-forward column:

  1. The COMP-3 column is decoded correctly in the FD-side record (the master lookup returns the right number).
  2. But when the per-account accumulator row is created later in the program, the carry-forward seed is initialised to a constant (often zero) instead of being copied from the lookup result.
  3. Every account is then summed up correctly from the detail tape but the opening balance is silently dropped at output time.

The cure is structural, not a single magic line: when you allocate a new accumulator row, seed every column that has a meaningful starting value — including the decoded carry-forward — rather than leaving it at its INITIALIZE/VALUE ZERO default. Pseudocode with placeholder names (adapt to your own record and table identifiers):

cobol
       *> placeholders: <new-row> is the freshly allocated accumulator,
       *> <decoded-carry> is the COMP-3 value from the master lookup.
       IF row-not-yet-present
           allocate <new-row>
           MOVE <account-key>   TO key-of   (<new-row>)
           MOVE <currency>      TO ccy-of   (<new-row>)
           MOVE <decoded-carry> TO carry-of (<new-row>)   *> seed, don't zero
           MOVE <period-delta>  TO delta-of (<new-row>)
       END-IF

The point is to recognise which fields need a non-zero seed at row creation; the exact MOVE targets depend on how your program names its balance table.

Verification tip

od -An -tx1 ACCT.MASTER | head and confirm bytes 11-17 of one record match the expected packed nibbles for that account's known opening balance. A few hand-decoded rows are usually enough to confirm both the FD declaration and the carry-through logic.

References

  • IBM Enterprise COBOL Language Reference -- "USAGE PACKED-DECIMAL / COMP-3"
  • GnuCOBOL documentation on USAGE clauses and arithmetic on packed fields

Frequently asked questions

What does the Comp3 Packed Decimal AI skill do?

Reference for COBOL COMP-3 (packed decimal / BCD) numeric storage -- layout on disk, declaring it in the FD, and pitfalls when carrying the decoded value through working storage and into later arithmetic. Useful when an input record holds a balance, rate, or carry-forward as packed decimal rather than a printable digit string.

Why use Comp3 Packed Decimal on TypingMind?

Because you install it once and use it with any model. Comp3 Packed Decimal is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Comp3 Packed Decimal in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/benchflow-ai/skillsbench/tree/main/tasks-extra/cobol-gl-batch-reconcile/environment/skills/comp3-packed-decimal. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Comp3 Packed Decimal?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Comp3 Packed Decimal?

As many as you like. As long as a model supports skills, you can use Comp3 Packed Decimal with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Comp3 Packed Decimal AI skill free?

Yes. It is published on GitHub by benchflow-ai under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇