To run this task you must have the following required information:

> Corporate text to translate (email, Slack message, meeting notes, etc.)

If you don't have all of this information, exit here and respond asking for any extra information you require, and instructions to run this task again with ALL required information.

---

You MUST use a todo list to complete these steps in order. Never move on to one step if you haven't completed the previous step. If you have multiple CONSECUTIVE read steps in a row, read them all at once (in parallel). Otherwise, do not read a file until you reach that step.

Add all steps to your todo list now and begin executing.

## Steps

1. [Read Corporate Translation Guide]: Read the documentation in: `skills/sauna/[skill_id]/references/humor.corporate.guide.md` (Load translation style and tone guidance)

2. [Read Corporate Jargon Reference]: Read the documentation in: `skills/sauna/[skill_id]/references/humor.corporate.jargon.md` (Load jargon dictionary for scoring)

3. If the user hasn't provided text yet, ask them to paste the corporate-speak they want decoded. Keep it casual: 'What corporate masterpiece should we translate today?' STOP and wait for input.

4. Create a full parallel translation of the entire text:

1. Break the original into logical sections (sentences or short paragraphs)
2. Quote EACH section in full as a blockquote
3. Write the plain English translation directly underneath
4. Continue until the entire original document is reproduced with translations

The output should contain the COMPLETE original text as quotes, interlaced with translations:

> "Thank you for your patience regarding this matter. We have been reviewing the situation internally."

Sorry this took forever. We've been arguing about this.

> "I believe there may be an opportunity to align our strategies going forward."

I think we should probably agree on something eventually.

The reader should be able to reconstruct the entire original from the quotes alone. Every word appears. Be witty but not cruel.


5. After the full translation, add a divider and present the analysis:

---

## Analysis

**BS Fluency Score: [X]% — [Title]**
How fluently they speak corporate, from "Refreshingly Human" to "CEO-Level Doublespeak"

**Accountability Index: [X]%**
How much responsibility is dodged. High = lots of "the team", "we should", passive voice. Low = clear ownership.

**Buzzword Density: [X] per sentence**
Average corporate jargon terms per sentence. Industry average is 1.2.

**Hedge Factor: [X]**
Count of softening words (perhaps, potentially, might, may, could, slight, minor). More hedges = less commitment.

**Action Clarity: [Vague / Mixed / Clear]**
Are there actual commitments or just corporate vapor? Look for specific actions, owners, and deadlines.

**Jargon Detected:** [list all corporate phrases found]

Then offer: "Want a shareable card image of this translation?"


6. [Read Translation Draft]: Read the file at `session/translation.json` into context (Get session file path)

7. Save the translation to `session/translation.json` as JSON:

{
  "original": "the full original text",
  "sections": [
    {"quoted": "full section text", "translation": "plain english version"}
  ],
  "analysis": {
    "bsScore": 75,
    "bsTitle": "Senior Management Material",
    "accountabilityIndex": 82,
    "buzzwordDensity": 2.3,
    "hedgeFactor": 7,
    "actionClarity": "Vague",
    "jargonDetected": ["circle back", "synergy", "stakeholders"]
  },
  "timestamp": "ISO date"
}