By cadrianmae
Automatic reference and prompt tracking via hooks. Tracks WebSearch/WebFetch/Read/Grep sources and major prompts to claude_usage/ directory with configurable verbosity. Supports export to bibliography, methodology, BibTeX, and timeline formats.
This skill should be used when the user asks to enable tracking, disable tracking, toggle auto-tracking, turn on/off automatic tracking, pause tracking, resume tracking, or control hooks-based tracking state. Manages .claude/.ref-autotrack marker file to activate/deactivate PostToolUse and SessionEnd hooks for automatic source and prompt tracking.
**Prompts Verbosity**: !`grep PROMPTS_VERBOSITY .claude/.ref-config 2>/dev/null | cut -d= -f2 || echo "major (default)"`
This skill should be used when the user asks to export tracked data, generate bibliography, create methodology section, export to BibTeX, generate citations, create timeline, or produce formatted output from tracked sources and prompts. Supports formats: bibliography (Markdown numbered list), methodology (Markdown sections), bibtex (BibTeX entries), citations (numbered citations), and timeline (chronological activity log). Exports to configurable path from .claude/.ref-config.
This skill should be used when the user asks for help with tracking, how to use the track plugin, tracking documentation, what tracking commands are available, how hooks-based tracking works, track plugin overview, or explanation of verbosity settings. Displays comprehensive documentation covering commands, file formats, verbosity settings, academic workflow examples, v2.0 architecture, and migration from v1.x.
This skill should be used when the user asks to initialize tracking, set up reference tracking, enable automatic source tracking, create tracking files, or start using the track plugin for the current project. Creates claude_usage/ directory with sources.md and prompts.md files, configures hooks-based automatic tracking with verbosity settings, and enables PostToolUse and SessionEnd hooks.
This skill should be used when the user asks to enable tracking, disable tracking, toggle auto-tracking, turn on/off automatic tracking, pause tracking, resume tracking, or control hooks-based tracking state. Manages .claude/.ref-autotrack marker file to activate/deactivate PostToolUse and SessionEnd hooks for automatic source and prompt tracking.
**Prompts Verbosity**: !`grep PROMPTS_VERBOSITY .claude/.ref-config 2>/dev/null | cut -d= -f2 || echo "major (default)"`
This skill should be used when the user asks to export tracked data, generate bibliography, create methodology section, export to BibTeX, generate citations, create timeline, or produce formatted output from tracked sources and prompts. Supports formats: bibliography (Markdown numbered list), methodology (Markdown sections), bibtex (BibTeX entries), citations (numbered citations), and timeline (chronological activity log). Exports to configurable path from .claude/.ref-config.
This skill should be used when the user asks for help with tracking, how to use the track plugin, tracking documentation, what tracking commands are available, how hooks-based tracking works, track plugin overview, or explanation of verbosity settings. Displays comprehensive documentation covering commands, file formats, verbosity settings, academic workflow examples, v2.0 architecture, and migration from v1.x.
This skill should be used when the user asks to initialize tracking, set up reference tracking, enable automatic source tracking, create tracking files, or start using the track plugin for the current project. Creates claude_usage/ directory with sources.md and prompts.md files, configures hooks-based automatic tracking with verbosity settings, and enables PostToolUse and SessionEnd hooks.
No model invocation
Executes directly as bash, bypassing the AI model
Runs pre-commands
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Contains inline bash commands via ! syntax
Contains inline bash commands via ! syntax
Bash prerequisite issue
Uses bash pre-commands but Bash not in allowed tools
Bash prerequisite issue
Uses bash pre-commands but Bash not in allowed tools
Personal marketplace for Mae's custom Claude Code plugins.
Supported: Linux, macOS, Windows (via Git Bash)
Note for Windows users: Context files default to /tmp/claude-ctx/ which maps to your Git Bash temp directory. You can specify a custom path using the optional path parameter if needed (e.g., /context:send child subject /c/Temp/).
Flat session management system with .current-session tracking.
Commands:
/session:start - Start new session/session:end - End with comprehensive summary/session:update - Add notes to current session/session:current - Show current status/session:list - List all sessions/session:resume - Resume previous session/session:help - Show helpGeneric hierarchical parent-child session context handoff.
Commands:
/context:receive - Receive context from parent/child session/context:send - Send context before switching sessionsFile pattern:
/tmp/claude-ctx/ctx-parent-to-child-{subject}.md/tmp/claude-ctx/ctx-child-to-parent-{subject}.mdFeatures:
/tmp/claude-ctx/ directory with minimal READMEReference and research tracking for academic work and project documentation.
Commands:
/track:init - Initialize tracking (run first)/track:update - Retroactive scan of history/track:auto - Toggle auto-tracking on/off/track:config - View or update verbosity settings/track:help - Show comprehensive helpFiles created:
CLAUDE_SOURCES.md - Research sources (KV format)CLAUDE_PROMPTS.md - Major prompts and outcomes.claude/.ref-autotrack - Auto-tracking marker.claude/.ref-config - Verbosity configurationSkills:
ref-tracker - Automatic tracking when enabledNatural language date/time parsing and calculations using native GNU date command.
Commands:
/datetime:now - Get current date/time/datetime:parse - Parse natural language expressions/datetime:calc - Calculate date differencesFeatures:
date command)Skills:
datetime - Auto-invoked for proactive temporal awarenessClaude-only skill that opens files in VSCode at specific line and column positions.
Auto-invoked when:
Features:
Skills:
code-pointer - Auto-invoked when Claude needs to show exact file locationsRequirements:
code CLI installed in PATHSession management wrapper for Claude CLI with AI-powered summaries and accurate timestamp tracking.
Features:
github.com) and list-type contentInstallation:
cp scripts/claude-session ~/.local/bin/
chmod +x ~/.local/bin/claude-session
Usage:
# Session management
claude-session # Start new session
claude-session -r # Resume with enhanced picker (shows tags/summaries)
claude-session list # List sessions with created/modified dates
claude-session stats # Show statistics
# Metadata management
claude-session tag <ID> <tags...> # Add tags
claude-session note <ID> <text> # Add note
claude-session summary <ID> <text> # Manual summary
# AI-powered summaries
claude-session summary --generate # Generate for current session
claude-session summary --generate <ID> # Generate for specific session
claude-session summary --generate <ID> --force # Overwrite existing summary
claude-session --help # Show complete help
npx claudepluginhub cadrianmae/claude-marketplace --plugin trackNeovim Remote integration for Claude Code - automatically open files in the correct neovim instance based on working directory
Enables Claude to open files at specific lines in VSCode when explaining code, debugging, or referencing specific locations. Auto-invoked skill that uses the `code` CLI to point users to exact file positions.
Document conversion toolkit for Pandoc with templates, validation, and format-specific helpers. Convert markdown to PDF, DOCX, HTML, and presentations with smart defaults and YAML frontmatter validation.
Flat session management system with .current-session tracking. Adapted from iannuttall/claude-sessions.
Hierarchical parent-child session context handoff system. Pass context between sessions using /context:send and /context:receive.
Shows the local time on every message and tells Claude when each prompt was sent — so you can scan a conversation, see how long things took, and reference earlier blocks.
Persistent local memory for Claude Code. Every tool call, every file edit, every thinking block from every session — stored verbatim on your machine. Semantic recall in ~126ms with zero API calls.
Personal AI Infrastructure — persistent memory, session continuity, and knowledge graph for Claude Code
Meta-Cognition tool for Claude Code: session history analysis, workflow optimization, and 21 MCP tools for deep session insights.
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.