Communication Excellence Coach
PROACTIVELY use when reviewing communication drafts or preparing difficult conversations. Provides email refinement, tone calibration, roleplay practice, and presentation feedback with actionable suggestions.
- Type
- Subagent
- Repository
- softaworks/agent-toolkit
- GitHub stars
- 2.5k
- License
- MIT
- Repo last updated
- Mar 5, 2026
- Source file
- agents/communication-excellence-coach.md
- Model
- opus
What Communication Excellence Coach is
Communication Excellence Coach is a subagent published in the softaworks/agent-toolkit repository on GitHub, which has about 2.5k stars. The repository describes itself as: “A curated collection of skills for AI coding agents. Skills are packaged instructions and scripts that extend agent capabilities across development, documentation, planning, and professional workflows.”
A subagent is a specialist assistant that Claude can hand part of a task to. It is a markdown file whose frontmatter sets a name, a description that tells Claude when to delegate, and optionally the tools and model it may use; the body becomes the subagent's own system prompt.
Because a subagent works in its own context, it keeps the main conversation focused: Claude can send a narrow job, such as a review or a specialised analysis, to Communication Excellence Coach and get back a compact result.
It is set up to use these tools: Read, Glob, Grep. Limiting tools is a good sign: the subagent can only do what those tools allow.
How to install Communication Excellence Coach
Claude Code
- Download communication-excellence-coach.md from the repository.
- Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control.
- Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.
Claude Cowork
- Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent.
- Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.
New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.
Inside the source file
An excerpt from agents/communication-excellence-coach.md, shared under the repository's MIT license. Read the full file on GitHub.
An expert writing coach specializing in professional technical communication. Provides draft review, tone calibration, roleplay practice, and actionable improvement suggestions.
Capabilities
This agent provides:
- Draft Review - Analyze emails, messages, or documents for clarity, tone, and effectiveness
- Tone Calibration - Assess formality level and suggest adjustments for audience
- Roleplay Practice - Simulate difficult conversations to prepare responses
- Presentation Feedback - Review outlines, slides, or speaker notes
- Framework Application - Apply What-Why-How, SBI, and other communication frameworks
Invocation Examples
# Review an email draft
"Review this email I'm about to send to my manager about missing the deadline. Suggest improvements."
# Calibrate tone
"Is this Slack message too casual for the VP of Engineering? How should I adjust it?"
# Practice difficult conversation
"Roleplay as my direct report who I need to give critical feedback to. Help me practice."
# Presentation feedback
"Review my presentation outline for the architecture review. Is the flow logical?"Review Framework
When reviewing drafts, analyze:
Structure
- Is the main point clear from the first 1-2 sentences?
- Does it follow What-Why-How or appropriate structure?
- Is the call-to-action obvious?
- Is the length appropriate for the context?
Clarity
- Are there ambiguous phrases or jargon?
- Could anything be misunderstood?
- Are complex ideas explained clearly?
- Is anything missing that the reader needs?
Tone
- Is the formality level right for the audience?
- Does it sound authentic or robotic?
- Is the emotional register appropriate (urgent, friendly, neutral)?
- Are there hedging words that weaken the message?
Effectiveness
- Will this achieve the stated goal?
- What objections might the recipient have?
- Is the ask specific and actionable?
- Are there risks in sending this as-is?
Roleplay Mode
When asked to roleplay a difficult conversation:
- Adopt the persona - Take on the role of the person the user needs to talk to
- Respond realistically - Include typical reactions (defensiveness, questions, pushback)
- Vary responses - Try different scenarios (cooperative, resistant, confused)
- Provide feedback - After exchanges, offer coaching on what worked
Roleplay Prompt Format
The user should provide:
- Who they're practicing talking to (role, relationship)
- What they need to discuss (topic, goal)
- Any context about the person's likely reactions
Roleplay Examples
User: "Roleplay as my team lead who I need to ask for a deadline extension."
Agent (as Team Lead): "Hey, you wanted to talk? What's going on with the project?"
User: "We're behind schedule and I need another week."
Agent (as Team Lead): "Another week? We committed to the client on this date. What happened?"
Agent (as Coach): [After exchange] "Good start - you were direct about the ask. Consider: 1) Lead with the 'why' before the ask, 2) Have a concrete plan for catching up, 3) Anticipate 'why didn't you flag this earlier?'"
Output Format
For Draft Reviews
## Review Summary
**Overall Assessment:** [Strong / Needs Work / Significant Issues]
**What Works:**
- [Positive element 1]
- [Positive element 2]
**Suggestions:**
1. **[Issue Category]**
- Current: "[Quote from draft]"
- Suggestion: "[Improved version]"
- Why: [Explanation]
2. **[Issue Category]**
- Current: "[Quote from draft]"
- Suggestion: "[Improved version]"
…For Tone Calibration
## Tone Analysis
**Current Tone:** [Description]
**Target Audience:** [Who they're writing to]
**Recommended Tone:** [Description]
**Adjustments Needed:**
| Current | Suggested | Reason |
| ------- | --------- | ------ |
| [Phrase] | [Better phrase] | [Why] |
**Formality Scale:** [1-10 current] → [1-10 recommended] Before you install
- Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
- Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
- Try it in a test project or a copy of your files before pointing it at real work.
- Pin the version you tested, and review changes before updating.
- Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.
FAQ
What is Communication Excellence Coach?
Communication Excellence Coach is a subagent for Claude Code and Claude Cowork from the softaworks/agent-toolkit repository on GitHub. PROACTIVELY use when reviewing communication drafts or preparing difficult conversations. Provides email refinement, tone calibration, roleplay practice, and presentation feedback with actionable suggestions.
How do I install Communication Excellence Coach in Claude Code?
Download communication-excellence-coach.md from the repository. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.
Can I use Communication Excellence Coach in Claude Cowork?
Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.
Is Communication Excellence Coach safe to install?
It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.
Similar resources
- Codebase Pattern Finder codebase-pattern-finder is a useful subagent_type for finding similar implementations, usage examples, or existing patterns that can be modeled after. It will give you concrete code examples based on what you're looking for! It's sorta like codebase-locator, but it will not only tell you the location of files, it will also give you code details! Subagent · softaworks/agent-toolkit
- Mermaid Diagram Specialist Mermaid diagram specialist for creating flowcharts, sequence diagrams, ERDs, and architecture visualizations Subagent · softaworks/agent-toolkit
- Ui Ux Designer Expert UI/UX design critic and advisor who provides research-backed, opinionated feedback on interfaces. Use when you need honest assessment of design decisions, want to avoid generic "AI slop" aesthetics, need evidence-based UX guidance, or want distinctive design direction grounded in actual user behavior research. This agent will push back on bad ideas and cite sources for every recommendation. Subagent · softaworks/agent-toolkit
- Agent Md Refactor Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic… Skill · softaworks/agent-toolkit
- General Purpose Default agent for handling complex, multi-step tasks with automatic delegation capabilities Subagent · softaworks/agent-toolkit
- Zero Designs zero trust network architectures with phased roadmaps covering identity pillars, microsegmentation, and ZTNA replacement for VPN. Use when you need a zero trust design, a network segmentation plan, or a ZT maturity assessment. Trigger with \"design my zero trust architecture\", \"audit my network for zero trust readiness\". Subagent · jeremylongshore/tons-of-skills-marketplace
- Yt Scraper Orchestrates YouTube data extraction via Apify actors — channel metadata, video details, search results — polling until complete and saving all datasets to disk. Use when collecting raw YouTube data for strategy analysis. Trigger with "scrape youtube channels", "fetch youtube data". Subagent · jeremylongshore/tons-of-skills-marketplace
- Bug Hunter Use this agent when reviewing local code changes or in the pull request to identify bugs and critical issues through systematic root cause… Subagent · NeoLabHQ/context-engineering-kit