agentleFS
lechithinhlechithinh/ba-claude-skills/AGENTS.md

ba-claude-skills

AGENTS.md1 starsChanged 5 days agoMITView on GitHub

This repository contains Business Analysis skills written as Markdown instructions. Any AI coding agent (Claude Code, Cursor, Codex, Gemini CLI, etc.) can use them.

The file

We split this AGENTS.md into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    When the user asks for one of the tasks below, read the matching SKILL.md and follow its process and output format exactly.

    line 6
  2. Very specific:

    If the context is a business domain below, ALSO read the domain SKILL.md and the reference files it points to (only the ones needed for the …

    line 22
  3. Very specific:

    Never invent business facts — use [value — confirm] placeholders.

    line 34

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

AGENTS.md

This repository contains Business Analysis skills written as Markdown instructions. Any AI coding agent (Claude Code, Cursor, Codex, Gemini CLI, etc.) can use them.

How to use the skills

When the user asks for one of the tasks below, read the matching SKILL.md and follow its process and output format exactly.

User intentRead
Extract requirements from meeting notes / transcriptskills/meeting-to-requirements/SKILL.md
Review, lint, score or validate requirements / user storiesskills/requirements-linter/SKILL.md
Functional decomposition, feature breakdown, module listskills/functional-decomposition/SKILL.md
Write user stories, acceptance criteria, Gherkin, Jira backlogskills/user-story-writer/SKILL.md
Model a business process in BPMN 2.0 (pools, lanes, gateways, events), run token scenarios, AS-IS / TO-BEskills/bpmn-modeling/SKILL.md
Draw use case, sequence, ERD, state or context diagrams (or a quick process draft)skills/ba-diagrams/SKILL.md
Write a screen/UI specification from a mockup image or descriptionskills/screen-spec/SKILL.md
Turn business rules into a decision table; find missing or conflicting rule combinationsskills/decision-table/SKILL.md
Find edge cases, challenge a requirement or story ("what if…")skills/edge-case-finder/SKILL.md
Draft an API contract / OpenAPI spec from requirementsskills/api-spec/SKILL.md

Domain packs

If the context is a business domain below, ALSO read the domain SKILL.md and the reference files it points to (only the ones needed for the task).

ContextRead
Bank, digital/mobile banking, transfers, cards, loans, deposits, eKYCskills/domain-banking/SKILL.md
Online store, marketplace, checkout, orders, vouchers, shipping, COD, returnsskills/domain-ecommerce/SKILL.md
E-wallet, payment gateway/PSP, QR payment, top-up, withdrawal, settlement, reconciliationskills/domain-payments/SKILL.md
Consumer loans, BNPL, installment, origination, repayment, collections, credit bureauskills/domain-lending/SKILL.md
Parcel delivery, courier, last mile, COD remittance, warehouse (WMS), fulfillmentskills/domain-logistics/SKILL.md

Conventions

  • Reply in the user's language (Vietnamese or English).
  • Never invent business facts — use [value — confirm] placeholders.
  • Diagrams are Mermaid code blocks.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.