CtrlK
BlogDocsLog inGet started
Tessl Logo

internal-comms

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

Install with Tessl CLI

npx tessl i github:davepoon/buildwithclaude --skill internal-comms
What are skills?

87

1.58x

Quality

83%

Does it follow best practices?

Impact

95%

1.58x

Average score across 3 eval scenarios

SKILL.md
Review
Evals

Evaluation results

100%

54%

Weekly Leadership Update for the Mobile Features Team

3P update strict format

Criteria
Without context
With context

Emoji in header

0%

100%

Team name in header

100%

100%

Date range in header

100%

100%

Three section labels

0%

100%

Section length limit

46%

100%

Metrics included

100%

100%

Matter-of-fact tone

90%

100%

No extra formatting

0%

100%

Without context: $0.1227 · 26s · 8 turns · 11 in / 1,372 out tokens

With context: $0.2918 · 1m 11s · 17 turns · 318 in / 3,332 out tokens

95%

30%

Company Newsletter — This Week at Meridian

Company newsletter structure and tone

Criteria
Without context
With context

We tense usage

10%

75%

Emoji section headers

0%

100%

Bullet count

100%

100%

Bullet length

80%

100%

Multiple themed sections

100%

100%

Company-wide scope

100%

100%

Links or references included

100%

100%

Without context: $0.1994 · 57s · 13 turns · 20 in / 2,495 out tokens

With context: $0.2108 · 54s · 12 turns · 1,147 in / 2,370 out tokens

90%

21%

Employee FAQ Document — Addressing Company Questions

FAQ response format and holistic coverage

Criteria
Without context
With context

Question/Answer format

12%

60%

Answer length

10%

100%

Question length

100%

100%

Company-wide topic coverage

100%

100%

Uncertainty flagged

100%

100%

Broad employee impact

100%

100%

Authoritative sourcing

100%

100%

Without context: $0.1281 · 44s · 8 turns · 13 in / 2,209 out tokens

With context: $0.2795 · 58s · 16 turns · 733 in / 2,810 out tokens

Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.