Coach

Name: Coach
Author: netresearch

netresearch/claude-coach-plugin

76 installs
13 repo stars
Updated July 12, 2026
netresearch/claude-coach-plugin

Helps with ai & agent building tasks.

About

coach is a Claude Code skill for ai & agent building. It helps solo builders move faster with AI-assisted coding.

coach
AI & Agent Building
AI-coding skill

Coach by the numbers

76 all-time installs (skills.sh)
+3 installs in the week ending Aug 4, 2026 (Skillselion tracking)
Ranked #5,442 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
Data as of Aug 4, 2026 (Skillselion catalog sync)

npx skills add https://github.com/netresearch/claude-coach-plugin --skill coach

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

[![Listed on Skillselion](https://skillselion.com/badge/skills/netresearch/claude-coach-plugin/coach.svg)](https://skillselion.com/skills/netresearch/claude-coach-plugin/coach)

Installs	76
repo stars	★ 13
Last updated	July 12, 2026
Repository	netresearch/claude-coach-plugin ↗

What it does

Helps with ai & agent building tasks.

Files

SKILL.mdMarkdownGitHub ↗

Coach - Self-Improving Learning System

Coach enables Claude to learn from friction and improve over time. It detects learning opportunities (user corrections, repeated instructions, tool failures, tone escalation), extracts actionable improvement candidates, and proposes changes requiring explicit user approval.

Core Principle: No silent writes. All improvements require user approval via /coach approve.

Activation Triggers

Activate when: user corrections ("no", "stop", "don't"), repeated instructions, tool/command failures, tone escalation (ALL CAPS, "!!!"), skill supplements ("also remember..."), deprecated-tool warnings, explicit /coach commands, or session end.

Signal Categories (Priority Order)

1. COMMAND_FAILURE (Highest) - Non-zero exit, stderr patterns 2. USER_CORRECTION (High) - Explicit correction language 3. SKILL_SUPPLEMENT (High) - Additional guidance for a skill 4. VERSION_ISSUE (Medium-High) - Deprecated/outdated warnings 5. REPETITION (Medium) - Semantically similar instruction repeated 6. TONE_ESCALATION (Low) - Frustration indicators

Candidate Types

Type	Description	Example
`rule`	Stable constraint	"Never edit generated files"
`checklist`	Workflow step	"Run tests after code change"
`snippet`	Repeatable command	"Preflight check script"
`skill`	Skill update suggestion	"Add X guidance to Y skill"
`antipattern`	Things to never do	"Never assume tool exists"

Workflow Summary

1. Detection — hooks capture events → ~/.claude-coach/events.sqlite 2. Generation — aggregate signals into proposals (fingerprints dedupe) 3. Scope — project vs global per path/language 4. Review — /coach review approves/rejects/edits 5. Apply — approved rules → ~/.claude/CLAUDE.md (global) or repo AGENTS.md (project) 6. Retro — /coach retro maps manual work to skill gaps, opens PRs at source repos

File Locations

~/.claude-coach/
├── events.sqlite      # Raw friction events
├── candidates.json    # Pending proposals
└── ledger.sqlite      # Cross-repo fingerprints

~/.claude/CLAUDE.md     # Global rules destination
<repo>/AGENTS.md        # Project rules destination

~/.claude/ or <repo>/.claude/
├── checklists/        # Workflow checklists
└── snippets/          # Reusable commands

Scripts

Execute from ${CLAUDE_PLUGIN_ROOT}/scripts/:

Script	Purpose
`init_coach.py`	Initialize coach system
`detect_signals.py`	Pattern detection for friction
`aggregate.py`	Turn signals into candidates
`skill_analyzer.py`	Analyze skills and scan for outdated tools
`apply.py`	Apply approved proposals

Proactive Commands

/coach scan — Check for outdated CLI tools and dependencies
/coach retro — Session retrospective: analyze manual work, create PRs to improve skills at source

For detailed architecture, schemas, and patterns, see references/ directory.