BC 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.
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…
As a process C 60/100 · Has gaps — weak spots: inputs and preconditions, failures and branches, progress reporting
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Reverse-engineers your manager from pasted comms — an email thread… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 60/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 64Steps. 3 steps, 1 vague phrases
- 100Tools and files. Tools declared in frontmatter
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1326 tokens
- 100Running it twice. No mutating operations
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 695: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 3 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.