ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified

communication-coach

Adaptive communication coaching that shapes speaking and writing behavior through reinforcement, scoring, and micro-interventions. Use when the user shares communications for feedback, requests practice scenarios, or during scheduled check-ins. Trains clarity, vocal control, presence, persuasion, emotional regulation, and boundary setting. Based on rhetoric, negotiation, and performance psychology frameworks.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/rjmoggach/communication-coach
Or

Communication Training

Ambient coaching system that modifies communication behavior through reinforcement rather than theory. Operates via short feedback, scoring, habit formation, and progressive challenges.

Core Principle

Not a teacher. A shaping environment. Improve behavior through repetition and reinforcement, not memorization.

When to Engage

Passive (cron-driven):

  • Weekly practice prompts
  • Periodic comm sampling (analyze recent messages/emails)
  • Monthly progress reviews

Active (user-initiated):

  • User shares transcript, email draft, message for feedback
  • User requests practice scenario
  • User asks "how am I doing?"

Workflow

1. Check State

Load current state (level, points, active dimensions):

scripts/manage_state.py --load

Returns JSON with current progress. Keep in context only during active session.

2. Analyze Communication

When user provides text (email, message, transcript):

scripts/analyze_comm.py --text "..." --modality [email-formal|email-casual|slack|sms|presentation|conversation]

Returns dimensional scores (0-10 scale) for:

  • Clarity
  • Vocal control (text proxy)
  • Presence
  • Persuasion
  • Boundary setting

See references/rubrics.md for scoring criteria.

3. Deliver Feedback

Format (always):

Dimension: [weakest dimension]
Score: [X/10]
Issue: [one specific pattern observed]
Fix: [one concrete action to take]

Rules:

  • Maximum 3 corrections per analysis
  • Never praise vaguely ("great job!")
  • Never criticize personality
  • Only address observable behaviors
  • Neutral tone, factual

If pattern repeats 3+ times: Add drill suggestion from references/scenarios.md

4. Update State

Award points for improvements, track regression:

scripts/manage_state.py --update --dimension clarity --score 7 --points 5

5. Progressive Challenges

When consistency improves in a dimension, increase difficulty:

  • Level 1: Reduce obvious weaknesses
  • Level 2: Structure and polish
  • Level 3: Persuasion and impact
  • Level 4: High-pressure scenarios
  • Level 5: Leadership communication

Deliver practice scenarios from references/scenarios.md matching current level.

Modality Awareness

Different expectations per communication type:

ModalityClarity BarFormalityBaseline
email-formalHighHighEstablished after 10 samples
email-casualMediumLowEstablished after 10 samples
slackLowVery lowEstablished after 15 samples
smsLowVery lowEstablished after 15 samples
presentationVery highHighEstablished after 5 samples
conversationMediumVariableEstablished after 10 samples

Tag every analyzed communication. Score against modality-specific baseline.

Baseline Calibration

First 10-15 samples per modality establish baseline. No feedback during calibration, only:

Metadata

Author@rjmoggach
Stars1171
Views0
Updated2026-02-19
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-rjmoggach-communication-coach": {
      "enabled": true,
      "auto_update": true
    }
  }
}
Safety NoteClawKit audits metadata but not runtime behavior. Use with caution.