communication-coach
PROACTIVE skill - Claude invokes automatically when user messages exhibit anti-patterns.
Skill by mahidalhan
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/mahidalhan-communication-coach
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/communication-coach
What's inside
- Skill name
communication-coach- Description
- PROACTIVE skill - Claude invokes automatically when user messages exhibit anti-patterns. Detects recursive nesting, scope creep, buried asks, assumed context, stream dumps, imprecise descriptions. Disable with "coach off" or "raw mode".
- License
- MIT
- Instructions
- 60 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Communication Coach Claude MUST invoke this skill when detecting anti-patterns. This is not user-called—Claude applies it automatically. ## Skill Thinking - **Pattern**: Which anti-pattern? Nesting, scope creep, buried ask, assumed context, stream dump, or imprecise description? - **Severity**: Genuinely unclear or just messy style? Only intervene when blocked. - **Restructure**: Prepare the clear version before intervening. - **Toggle**: "coach off" or "raw mode" in recent messages? Skip intervention. ## CRITICAL **Intervene surgically, not pedantically.** One-line intervention, offer restructured version, confirm, proceed. Never lecture. If you understand intent despite style, proceed silently. Goal is unblocking, not teaching. ## Detection Patterns | Pattern | Signal | Intervention | |---------|--------|--------------| | Recursive nesting | `"do X (but first Y (but first Z))"` | `⚡ Nesting. Reordered: 1.Z 2.Y 3.X. Correct?` | | Scope creep | Starts A, ends A+B+C+D | `⚡ 4 asks detected. Priority?` | | Buried ask | Main request in parenthetical | `⚡ Main ask: [X]. Confirming.` | | Assumed context | "the paper", "that thing" | `⚡ Which [X] specifically?` | | Stream dump | Long unpunctuated block | `⚡ Parsed: [list]. Correct?` | | Imprecise description | Emotion without spec | `⚡ Clarifying: [precise reframe]. Correct?` | ## Imprecise Description Handling When user describes with emotion/vague terms but lacks spatial/technical precision: | Vague | Precise Reframe | |-------|-----------------| | "sharp corner near shoulder" | "Hard edge at [location] - should use [gradient type] to [target color]" | | "submerge" | "Fade/blend/overlap? Specify transition type" | | "feels wrong" | "What specifically: spacing, color, alignment, or animation?" | | "make it pop" | "Increase contrast, scale, shadow, or saturation?" | | "bar in middle" | "Scrollbar on right edge? Or horizontal divider at [y]?" | **Formula for one-shot UI fixes:** ``` [SCREEN] + [ELEMENT] + [CURRENT STATE] + [DESIRED STATE] + [REFERENCE] ``` Example reframe: > "Screen 2: Hero left edge has hard gradient cutoff. Should fade radially to #0e1216 like Figma node-XXX." ## Guidelines Focus on: - **One-line interventions**: `⚡` + pattern + restructure + `Correct?`. Max 2 lines. - **Positive signal**: Clear message → `✓ Clear.` then proceed. - **Toggle respect**: "coach off"/"raw mode" = silent. "coach on"/new session = resume. - **Precision upgrade**: When user describes visually, offer the precise technical version. No jargon—simple terms like "fade", "edge", "x-position", "contrast". - **No meta-commentary**: Never explain coaching or reference skill name. ## NEVER Lecture about communication, intervene when intent is clear, exceed 2 lines, be condescending, intervene after "coach off", use jargon when simple terms work, turn every message into coaching, or explain why you're asking for precision.
From mahidalhan/claude-hacks, MIT.
More from mahidalhan/claude-hacks
- 0.502score
swift-concurrency-expert
mahidalhan
Swift Concurrency review and remediation for Swift 6.2+.
SkillDFreshness: D★ 33Claude Code +9 - 0.502score
architecture-introspector
mahidalhan
USE WHEN: analyzing existing architectures, evaluating architectural decisions, identifying technical debt, planning refactoring, assessing whether patterns…
SkillDFreshness: D★ 33Claude Code +9 - 0.502score
skill-creator
mahidalhan
USE WHEN: user asks to create a skill, scaffold a new capability, codify expertise into reusable instructions, or says "create skill", "new skill", "make a…
SkillDFreshness: D★ 33Claude Code +9 - 0.502score
threaded-explainer
mahidalhan
USE WHEN: teaching complex topics requiring chunked delivery, handling mid-explanation questions, preserving context across interrupts, deep-dive explanations…
SkillDFreshness: D★ 33Claude Code +9 - 0.502score
exa-code-context
mahidalhan
USE WHEN: needing real code examples from GitHub, finding API usage patterns, looking up framework setup, verifying library implementations, eliminating…
SkillDFreshness: D★ 33Claude Code +9 - 0.497score
mermaid-diagrams
mahidalhan
USE WHEN: user needs diagrams, flowcharts, ERDs, sequence diagrams, state machines, architecture visualizations, or says "visualize", "diagram", "chart"…
SkillDFreshness: D★ 33Claude Code +9 - 0.497score
task-orchestrator
mahidalhan
USE WHEN: planning complex multi-step tasks, organizing work with dependencies, identifying parallelization opportunities, breaking down large features into…
SkillDFreshness: D★ 33Claude Code +9 - 0.497score
algorithmic-art
mahidalhan
USE WHEN: user requests generative art, algorithmic art, procedural visuals, flow fields, particle systems, creative coding, or says "create art"…
SkillDFreshness: D★ 33Claude Code +9 - 0.497score
standup
mahidalhan
USE WHEN: returning to a project after time away (1 day to 30 days), needing project status briefing, understanding where work left off, determining next steps.
SkillDFreshness: D★ 33Claude Code +9 - 0.497score
ascii-art-explainer
mahidalhan
USE WHEN: visualizing algorithms, data structures, architecture, control flow with ASCII art, or when terminal-friendly diagrams are needed.
SkillDFreshness: D★ 33Claude Code +9 - 0.497score
xml-context-engineering
mahidalhan
USE WHEN: writing system prompts, structuring complex instructions, engineering context for Claude agents, optimizing attention efficiency in long prompts.
SkillDFreshness: D★ 33Claude Code +9 - 0.497score
explainer
mahidalhan
USE WHEN: user asks "explain", "teach me", "how does X work", "help me understand", or wants to learn concepts from first principles with interactive…
SkillDFreshness: D★ 33Claude Code +9
Signals
- Stars
- 33
- Forks
- 5
- Open issues
- 1
- Last commit (this folder)
- Jan 22, 2026 (9 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/mahidalhan/claude-hacks
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from mahidalhan
- 0.502score
skill-creator
mahidalhan
USE WHEN: user asks to create a skill, scaffold a new capability, codify expertise into reusable instructions, or says "create skill", "new skill", "make a…
SkillDFreshness: D★ 33Claude Code +9 - 0.502score
swift-concurrency-expert
mahidalhan
Swift Concurrency review and remediation for Swift 6.2+.
SkillDFreshness: D★ 33Claude Code +9 - 0.502score
exa-code-context
mahidalhan
USE WHEN: needing real code examples from GitHub, finding API usage patterns, looking up framework setup, verifying library implementations, eliminating…
SkillDFreshness: D★ 33Claude Code +9 - 0.502score
architecture-introspector
mahidalhan
USE WHEN: analyzing existing architectures, evaluating architectural decisions, identifying technical debt, planning refactoring, assessing whether patterns…
SkillDFreshness: D★ 33Claude Code +9 - 0.502score
threaded-explainer
mahidalhan
USE WHEN: teaching complex topics requiring chunked delivery, handling mid-explanation questions, preserving context across interrupts, deep-dive explanations…
SkillDFreshness: D★ 33Claude Code +9 - 0.497score
publish-skill
mahidalhan
USE WHEN: user wants to publish, port, or share a skill to a marketplace repo.
SkillDFreshness: D★ 33Claude Code +9
Cite this page
communication-coach skill. Agent Mart. https://agentmart.dev/skills/mahidalhan-communication-coach (last updated 2026-10-24)