agentleFS
jame-hvjame-hv/brse-toolkit/skills/business-explain/SKILL.md

business-explain

Skill0 starsChanged 5 days agoMITView on GitHub

Use this when a feature, screen or business flow must be explained to someone who does not know the system — a new member, a manager, a sales person or a non-technical client — in plain words, from the project's documents (doc-to-md output) and/or code, with every statement traceable to its source.

The file

We split this skill 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:

    Run <py> ${CLAUDE_PLUGIN_ROOT}/scripts/brse.py config and read its JSON:

    line 14
  2. Very specific:

    Collect facts with sources: Read .brse/knowledge/docs/ (run doc-to-md first if missing).

    line 35
  3. Very specific:

    Plain-language check: no sentence over ~25 words for non-tech.

    line 55

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill 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
SKILL.md

Before running

<py> below = the Python recorded by /brse-toolkit:setup (runtime.python in ~/.config/brse-toolkit/config.json — read that file directly), else the first of python3, python, py -3 that runs. No Python at all → tell the user to run /brse-toolkit:setup, and continue only with steps that need no script, saying which checks were skipped.

Run <py> ${CLAUDE_PLUGIN_ROOT}/scripts/brse.py config and read its JSON:

  • error → show it to the user and stop; the config file must be fixed first.
  • workspace_root is null → the folder isn't initialized. Ask once: run /brse-toolkit:init first (recommended — memory and knowledge get saved for next time) or continue once without saving. Running as a subagent dispatched by a main agent → the parent already resolved this; proceed.
  • Otherwise use config.paths (sources, templates, outputs — relative to workspace_root), config.style, config.translation, and the files in .brse/memory/long/. Never assume a folder name the config doesn't list.
  • warnings not empty → mention them in one line (likely a typo in the config).

When to use

"Explain what this feature does", onboarding a new member, a summary for a manager or client who doesn't read specs. For a technical explanation from code for developers, use code-to-business.

Steps

  1. Reader first. Pick one: non-tech (client/manager/sales), new member (knows software, not this system), new developer. State it at the top; it decides vocabulary and depth. Output language from the request or config.
  2. Collect facts with sources. Read .brse/knowledge/docs/ (run doc-to-md first if missing); for behaviour only visible in code, run code-to-business and reuse its cited facts. Every fact keeps its source (file + sheet/heading/row, or file:line). Gaps → "cần xác nhận / 要確認", never filled by guessing.
  3. Write in this order (draft facts only — wording is done by Comtor):
    1. In one sentence: what it is for and who uses it.
    2. Why it exists: the business problem it solves.
    3. Who and when: roles, triggers, frequency.
    4. Step by step: the business flow in plain words, one action per step, no field IDs or table names for non-tech readers.
    5. A real-life example: one concrete scenario with sample values from the spec (say they are examples).
    6. Rules that matter: limits, validations, statuses, what is blocked and why — as "if … then …".
    7. Glossary: every term the reader would trip on → plain meaning (project glossary first).
    8. FAQ / what to watch out for and the open questions. Optional: a simple flow diagram (ask System Engineer, diagram skill, flow or flow-lanes type) — at most ~10 boxes for non-tech readers.
  4. Plain-language check: no sentence over ~25 words for non-tech; no unexplained acronym; no screen/table/variable names unless the reader is a developer. Every paragraph still has its source tag.
  5. Wording: send the draft + sources + reader + language to Comtor; check back that no fact, number or rule changed meaning.

Output

The explanation (Markdown, or Word/Slide via report-gen when asked), saved in config.paths.outputs, with the source list at the end and the open questions inline in the reply.

Handoff

Finish with review-gate (runs verify-output).

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.