About this skill

What It Solves

When a short reply like “fine,” “we’ll get back to you soon,” or “hahaha” appears in a chat thread, readers often over-interpret the signal: Is the other person cold, rejecting, or hinting at something else? chat-subtext-translator addresses this ambiguity by treating a single message or a short transcript as a context-dependent text signal, especially when tone, facial expression, and body language are absent.

How It Works

The skill first gathers the key inputs: the exact message, the relationship type, what was discussed just before, the other person’s usual expression style, and optional timing cues such as response speed or send time. It then produces a layered reading:
- Literal layer: the direct meaning;
- Subtext layer: the most likely intended meaning given context;
- Alternative layer: other plausible readings, with high, medium, or low confidence.
It also inspects punctuation, emoji usage, message length, tone particles, and reply intervals, then closes with a balanced conclusion, a reminder against over-reading, and 2–3 appropriate reply options.

Boundaries And Caveats

It does not predict romantic outcomes, provide PUA tactics, or help monitor or manipulate others. Because text omits much nonverbal information, its interpretations are probabilistic aids rather than diagnoses. Privacy, fraud risk, or relationship fixation should be handled through direct communication, anti-fraud resources, or professional support instead.

Screenshots

Use Cases

A sales rep receives a client saying the proposal needs review and infers delay, comparison, or refusal, then drafts a follow-up.
A PM sees a teammate reply only that they received the message and uses task urgency and history to judge acceptance or objection.
A support agent reads a user’s brief fine then after a complaint and decides whether to reassure, apologize, or close the conversation.
A new employee receives think about it first from a manager and interprets whether the manager wants time, a plan, or signals concern.

Best For

Sales reps who need to infer whether client replies such as review again or talk later signal a stall
New employees who need to read manager cues in short replies such as got it or think about it
Customer support agents who need to distinguish approval, indifference, or dissatisfaction in brief user replies
Project leads who need to interpret team tone in collaboration channels and avoid misreading priorities

Related Skills

Scholar Reasoning Distiller

@user_231765ee/django-plus

Extracts an eight-layer reasoning fingerprint from scholar texts and applies a nine-module constraint to run peer review, supervision, lecturing, or panel discussion with quantitative scores and qualitative comments.

Knowledge Management 2026.08.30 ↓ 608