Session persistence for Claude Code. Auto-injects context at session start, preserves state across memory compaction.
npx claudepluginhub tmsjngx0/mindcontext-core --plugin mindcontext-coreOne-page project orientation after a long break. Summarizes recent git history, beads state, memory, and worktree status.
Update CHANGELOG.md following Keep a Changelog format
Smart commit using Conventional Commits format - delegates analysis to commit-worker agent
Safe git sync workflow with bare repo + worktree awareness. stash → pull → stash pop → commit → push with conflict diagnosis.
Generate a self-contained context prompt for the next Claude session. Analyzes conversation for decisions, key files, next steps.
Autonomous beads task implementation - spawns background workers to implement, commit, and verify
Decompose a plan or feature description into a beads epic with iteration-aware subtasks and blocking dependencies
Initialize project with context management and workflow selection
Enrich ad-hoc bead descriptions into self-contained, implementation-ready format. Takes a title and brief context, explores codebase, returns description with 6 structural layers. Used automatically when PreToolUse hook blocks bare br create.
Create implementation-ready, self-contained beads from OpenSpec changes. Each bead is implementable with ONLY its description - no external lookups needed. Adapted from cc-architect beads-default agent by Carlo Nicora.
Analyze git changes and produce granular conventional commits. Returns structured JSON with commit groups, messages, and warnings.
Classify session files into HOT/WARM/COLD tiers for context continuation. HOT files are read first on resume, WARM on demand, COLD skipped.
Implement code changes from self-contained beads task description. Returns structured JSON with status and summary.
Generate session progress notes from conversation context. Returns structured markdown for beads comments.
Converts a plan or feature description directly into beads epic + subtasks + blocking deps. Skeleton-first: ALL tasks get lightweight descriptions. Self-contained descriptions are created separately via /enrich when a task's iteration starts.
Find untracked work: commits without beads issues, TODO/FIXME comments, and new files not covered by any specification.
Audit synchronization gaps between OpenSpec changes and beads epics. Returns structured JSON with tracked, untracked, orphaned, drift, and quality reports.
Lite-mode importer. Creates lightweight tracking beads from OpenSpec changes. For implementation-ready beads, the SKILL routes to beads-builder agent instead. Reads proposal/tasks/design, executes br create commands, returns import summary.
Synchronize existing beads epic with updated tasks.md content. Creates missing tasks, updates checkboxes bidirectionally.
Validate committed code by running type-checks, linting, and tests for modified files. Returns structured JSON with pass/fail and specific issues.
Unified audit skill. Runs project health checks, code quality analysis, or CLAUDE.md restructuring. Use when asked to "audit", "check health", "review code quality", or "prepare for production".
Synchronize OpenSpec changes with beads epics. Audit gaps, import changes, update existing epics, find untracked work.
Add a comment to the current in-progress task. With no arguments, uses note-generator to create a session summary from conversation context. With text argument, saves it directly.
Reference for Conventional Commits 1.0.0 format. Auto-loads when user asks "how to write commits", "commit message format", "what is conventional commits", "commit best practices".
Enrich a lightweight (iteration:future) bead into a self-contained, implementation-ready description
Reference for Keep a Changelog format. Auto-loads when user asks "how to write changelog", "changelog format", "what goes in changelog", "changelog best practices".
Find and display the next task from beads issues. Shows in-progress work or recommends ready tasks by impact score.
Decompose a plan or feature description into a beads epic with lightweight skeleton subtasks
Load context from vault memory. Temporal queries (yesterday, last week, session history) use native JSONL timeline. Topic queries use QMD BM25 search. "recall graph" generates interactive temporal graph of sessions and files. Every recall ends with "One Thing" - the single highest-leverage next action synthesized from results. Use when user says "recall", "what did we work on", "load context about", "remember when we", "prime context", "yesterday", "what was I doing", "last week", "session history", "recall graph", "session graph".
Summarize current project state after a long break. Analyzes recent git history, beads issues, and memory to produce a one-page orientation. Use when returning to a project cold, or when asking "what was I doing", "where did I leave off".
Analyze current session and generate a self-contained context prompt for the next Claude session. Includes project context, decisions, next steps, and tech stack. Use when ending a work session.
Test-Driven Development workflow following Kent Beck's methodology. Auto-loads when user asks about "tdd", "test driven", "red green refactor", "write tests first".
AI-native product management for startups. Transform Claude into an expert PM with competitive research, gap analysis using the WINNING filter, PRD generation, and GitHub Issues integration.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Intelligent prompt optimization using skill-based architecture. Enriches vague prompts with research-based clarifying questions before Claude Code executes them
Persistent memory system for Claude Code - seamlessly preserve context across sessions
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, rules, and legacy command shims evolved over 10+ months of intensive daily use