Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →notque/professional-communication
Draft interpersonal and meeting messages: emails, memos, status updates, structured pushback or disagreement.
Passed 19 of 22 test cases with the skill, and 9 of 22 without it.
and 14 more in the full report
13 fixed6 passed either way0 still failing3 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
Extract and structure these incident notes: '1. Kafka queue consumer lagged by 50k messages. 2. Auto-scaling group failed to spin up new EC2 instances due to AWS quota limits. 3. Increased quota request submitted to AWS support. 4. Manual worker nodes added to drain queue.' Ensure no facts are dropped.
| Checked | Without skill | With skill |
|---|---|---|
| Lists 4 distinct propositions in Extracted Propositions section | Missed | Passed |
The instructions your model reads when the skill loads.
This skill transforms dense technical communication into clear, structured business formats using proposition extraction (identify all facts and relationships) and deterministic templates (apply consistent structure). It extracts every detail without loss, categorizes by business relevance, applies a standard template with professional tone, and verifies completeness before delivery.
Core principle: Transformation ≠ creation. Only restructure existing input; always extract from existing input and restructure it for executive clarity with preserved technical accuracy.
| Signal | Load These Files | Why |
|---|---|---|
| transforming raw engineer notes: stream-of-consciousness debugging, blockers, crisis updates | examples.md | Loads detailed guidance from examples.md. |
| drafting from section templates; phrase transformations | templates.md | Loads detailed guidance from templates.md. |
Goal: Extract every proposition from the input before structuring anything. This prevents information loss and ensures technical accuracy is preserved.
Step 1: Classify input type
Identify the communication type (this determines categorization strategy in Phase 2):
Step 2: Extract all propositions
Parse each sentence systematically. Extract all propositions before summarizing — summarizing skips propositions and loses facts:
test cases passed, vs 9 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.