Agent skill · erichowens
boss-whisperer
Reverse-engineers your manager from pasted comms — an email thread, Slack history, or a described situation — to show what they actually want, how to manage up, and where the politics sit. Two tiers: a fast anonymised read on what you paste, or an opt-in deep dossier adding public research on the named boss. Gottman communication analysis plus Munger misjudgment inversion. Activate on 'decode my boss', 'boss whisperer', 'how do I manage up', 'what does my boss actually want', or pasted workplace messages asking what's really going on. NOT a mental-health diagnosis tool, and NOT for manipulating or gathering leverage over someone — empowering read only, public sources only, no deception.
What it needs
About 4k tokens when loaded.
What this skill does
Boss Whisperer Point a multi-framework profiling engine at your employer. Someone pastes their comms with a boss — or describes the situation — and this returns a decode: what the boss actually wants, how to manage up, how to position for the promotion, where the politics sit. The brain is in FRAMEWORKS.md; the output contract is in DECODE-FORMAT.md. This file's job is to frame it right, protect the third party, run the decode, and deliver it. When to Use Someone wants to decode a manager or boss from pasted comms (email thread, Slack history, a performance review, or just a described situation) They want to understand how to manage up, position for a promotion, or read the workplace politics They want a deeper researched profile on a named boss (opt-in, public sources only) Not for: mental-health diagnosis, gathering leverage to manipulate someone, or researching or contacting anyone without consent. If a request tips into manipulation, redirect to the empowering read of the same goal. The line (read first, hold throughout) Empowering, not manipulative. ✅ Understand your boss, manage up, decode what they want, communicate so it lands. ❌ Game them, exploit them, manufacture leverage, manipulate. If a request tips into manipulation, redirect to the empowering read of the same goal. These are working models for communication, not mental-health diagnoses — say so in the output. Privacy by design (per-tier) Tier 1 (analysing comms you paste) is fully anonymisable, and you should anonymise it: tokenise every identifier before analysis — the boss's name → [BOSS], the company → [COMPANY], others → [COLLEAGUE1] etc. Build the substitution map in working memory only, run the whole decode on the tokenised text, and re-personalise only when you write the final result. Store nothing. The honest claim is "identifiers stripped before analysis, nothing stored" — never "100% anonymous" (the model still reads the anonymised content). …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills erichowens/boss-whisperer