Sparkey Reflect — AI coding advisor with industry-benchmarked scoring
npx claudepluginhub sparkey-ai/sparkey-reflectSparkey Reflect — AI coding advisor that analyzes your sessions and generates coaching insights with smooth, industry-benchmarked scoring
AI coding advisor that analyzes your Claude Code sessions and generates personalized coaching insights. Runs 100% locally — your conversation data never leaves your machine.
Requires Claude Code 1.0.33+ and Python 3.11+.
# Step 1: Add the marketplace source
/plugin marketplace add Sparkey-AI/sparkey-reflect
# Step 2: Install the plugin
/plugin install sparkey@sparkey-reflect
The plugin auto-installs the sparkey-reflect PyPI package on first run.
pip install sparkey-reflect
/sparkey:reflect # Weekly report (last 7 days)
/sparkey:reflect daily # Yesterday's sessions
/sparkey:reflect monthly # Last 30 days
/sparkey:reflect full # Full quarter (90 days)
/sparkey:reflect 14 # Custom day count
/sparkey:reflect deep-dive prompt_engineering # Skill deep-dive
/sparkey:reflect update-rules # Improve your CLAUDE.md
sparkey-reflect analyze --tool claude-code --days 7
sparkey-reflect analyze --tool cursor --days 30 --format json
sparkey-reflect status
sparkey-reflect rules
sparkey-reflect trends --days 30
sparkey-reflect learning-path
| Parameter | Description |
|---|---|
daily | Analyze yesterday's sessions |
weekly (default) | Last 7 days |
monthly | Last 30 days |
full | Full quarter — 90 days |
<number> | Custom number of days |
deep-dive <skill> | In-depth analysis of one skill |
update-rules | Improve CLAUDE.md based on insights |
| Skill | What it analyzes |
|---|---|
prompt_engineering | Prompt clarity, specificity, structure |
context_management | How you manage context window and file references |
tool_mastery | Usage of available tools and features |
conversation_flow | Session structure and conversation patterns |
session_habits | Session length, time-of-day, and workflow patterns |
rule_file_quality | CLAUDE.md and instruction file effectiveness |
outcome_quality | Success rate and task completion quality |
Get version code + project management integrations, trend tracking, usage analytics, and industry benchmarks at sparkey.ai.
Scoring grounded in industry-standard frameworks (DORA, SPACE, DevEx) and validated against published research from GitClear and METR.
DORA is a program of Google Cloud. GitClear and METR are independent organizations. Sparkey is not affiliated with or endorsed by any of these entities.
MIT
Open Design — local-first design app exposed to coding agents over MCP. Install once with your agent's plugin command and projects/files/skills are reachable through stdio.
Claude Code plugins for the Slidev presentation framework
Bundled plugins for actuating and debugging the Chrome browser.