MicrotronX
UserSelf-hosted MCP server for AI coding assistants. Persistent knowledge base with 45 tools, 12 skills, institutional memory.
Categories
Indexed Skills (24)
mxorchestrate
Persistent session orchestrator for mxLore. This skill should be used when the user says "park", "resume", "what's my workflow status", "/mxOrchestrate start/track/park/resume/status/suggest", "start a new feature/bugfix workflow", "track this as ad-hoc", "spawn a team agent", or when a session begins and workflow state must be loaded. Always-on via SessionStart/UserPromptSubmit hooks. Manages workflow stack (LIFO), ad-hoc tasks, team agents, and skill chains.
mxsave
Use when the user says "save state", "/mxSave", "session end", "before /compact", "wrap up", or otherwise wants to persist the current mx-project state (clean settings, update CLAUDE.md + docs/status.md, create session notes in MCP-DB, sync orchestrate-state deltas, emit clear-cycle tip). Loop-capable. Fires at natural session-end boundaries.
mxsetup
This skill should be used when a developer sets up mxLore on a new PC, runs a fresh Claude Code install, updates the global mx-rules block in ~/.claude/CLAUDE.md, refreshes skills/hooks from GitHub, or reinstalls the mxMCPProxy. Triggers "neuer PC", "fresh install", "onboard me", "/mxSetup", "update mx-rules", "mx-rules block veraltet", "reinstall proxy", "skills aktualisieren".
mxbugchecker
Use when the user says "/bugcheck", "/mxBugChecker", "check for bugs", "find bugs", "audit for vulnerabilities", "verify the code", "look for issues in this file", or otherwise requests bug analysis on VCS changes or specific files. Verified-knowledge bug finder — every finding requires concrete code proof. Analyzes logic errors, runtime issues, edge cases, error handling, concurrency, resource leaks, security vulnerabilities, and performance regressions. Loads project context from the mxLore Knowledge-DB via MCP and persists findings via Skill Evolution.
mxdecision
Use when the user says "/decision", "/mxDecision", "document decision", "write an ADR", "record a decision", "architectural decision", "ADR", or otherwise wants to capture a significant technical choice made in the conversation. Creates or updates Architecture Decision Records (ADRs) via MCP-Tools in the mxLore knowledge DB; maintains supersedes chain and status transitions.
mxdesignchecker
Use when the user says "/designcheck", "/mxDesignChecker", "review the design", "check the spec", "review this ADR", "audit architecture", "second opinion on this code", or otherwise requests design/spec/ADR review or code-vs-design audit. Verified-knowledge design reviewer — every finding requires concrete proof from spec or code. Loads specs/designs from the mxLore Knowledge-DB via MCP and persists findings via Skill Evolution. NO automatic corrections — all fixes require user confirmation.
mxhealth
Use when the user says "/health", "/mxHealth", "health check", "check knowledge db", "verify consistency", "db health", or otherwise wants to verify Knowledge-DB and docs/ consistency via MCP. Runs 14 consistency checks (document metadata, cross-references, orphaned relations, status consistency, CLAUDE.md weight, local/DB sync, AI-Steno format, skill-evolution metrics, AI-Batch status) and persists findings via Skill Evolution. Loop-capable. ⚡ MCP-required — aborts if Knowledge-DB is unreachable.
mxhelp
Use when the user says "/mxHelp", "/mxHelp <name>", or asks which mx-skill does what. Lists all installed mx*-skills grouped by category, or explains one skill in detail. Pure reader — no side effects.
mxinitproject
Use when the user says "/mxInitProject", "bootstrap project", "init project", "setup ai config", "initialize claude config", "scaffold project", or otherwise wants to bootstrap a new repository with the mxLore AI-documentation structure (CLAUDE.md, docs/ layout, optional MCP project registration). Idempotent — safe to re-run. Detects MCP mode vs local fallback. NEVER overwrites existing content.
mxmigratetodb
Use when the user says "/mxMigrateToDb", "migrate to db", "migrate local docs to mcp", "sync local docs", "import docs to knowledge db", "--extract-backlog", "extract legacy backlog", or otherwise wants to import local `docs/*.md` fallback files into the MCP Knowledge-DB. Runs after MCP outages (when offline-fallback created local files) or once after initial MCP setup. Supports dry-run, cleanup, sync, scan, and --extract-backlog modes. ⚡ MCP-required — aborts if Knowledge-DB is unreachable.
mxplan
Use when the user says "/plan", "/mxPlan", "create a plan", "update the plan", "write a plan for X", "plan this feature", or otherwise wants to structure a multi-step implementation task before coding. Creates or updates plans via MCP-Tools in the mxLore knowledge DB; maintains task checklists with auto-archive on completion.
mxspec
Use when the user says "/spec", "/mxSpec", "write a spec", "write a specification", "requirements doc", "acceptance criteria", "define requirements", or needs to specify a feature or component before planning or implementation. Creates or updates specifications via MCP-Tools in the mxLore knowledge DB; tracks acceptance criteria with auto-archive on full completion.
mxorchestrate
Persistent session orchestrator for mxLore. This skill should be used when the user says "park", "resume", "what's my workflow status", "/mxOrchestrate start/track/park/resume/status/suggest", "start a new feature/bugfix workflow", "track this as ad-hoc", "spawn a team agent", or when a session begins and workflow state must be loaded. Always-on via SessionStart/UserPromptSubmit hooks. Manages workflow stack (LIFO), ad-hoc tasks, team agents, and skill chains.
mxsave
Use when the user says "save state", "/mxSave", "session end", "before /compact", "wrap up", or otherwise wants to persist the current mx-project state (clean settings, update CLAUDE.md + docs/status.md, create session notes in MCP-DB, sync orchestrate-state deltas, emit clear-cycle tip). Loop-capable. Fires at natural session-end boundaries.
mxsetup
This skill should be used when a developer sets up mxLore on a new PC, runs a fresh Claude Code install, updates the global mx-rules block in ~/.claude/CLAUDE.md, refreshes skills/hooks from GitHub, or reinstalls the mxMCPProxy. Triggers "neuer PC", "fresh install", "onboard me", "/mxSetup", "update mx-rules", "mx-rules block veraltet", "reinstall proxy", "skills aktualisieren".
mxbugchecker
Use when the user says "/bugcheck", "/mxBugChecker", "check for bugs", "find bugs", "audit for vulnerabilities", "verify the code", "look for issues in this file", or otherwise requests bug analysis on VCS changes or specific files. Verified-knowledge bug finder — every finding requires concrete code proof. Analyzes logic errors, runtime issues, edge cases, error handling, concurrency, resource leaks, security vulnerabilities, and performance regressions. Loads project context from the mxLore Knowledge-DB via MCP and persists findings via Skill Evolution.
mxdecision
Use when the user says "/decision", "/mxDecision", "document decision", "write an ADR", "record a decision", "architectural decision", "ADR", or otherwise wants to capture a significant technical choice made in the conversation. Creates or updates Architecture Decision Records (ADRs) via MCP-Tools in the mxLore knowledge DB; maintains supersedes chain and status transitions.
mxdesignchecker
Use when the user says "/designcheck", "/mxDesignChecker", "review the design", "check the spec", "review this ADR", "audit architecture", "second opinion on this code", or otherwise requests design/spec/ADR review or code-vs-design audit. Verified-knowledge design reviewer — every finding requires concrete proof from spec or code. Loads specs/designs from the mxLore Knowledge-DB via MCP and persists findings via Skill Evolution. NO automatic corrections — all fixes require user confirmation.
mxhealth
Use when the user says "/health", "/mxHealth", "health check", "check knowledge db", "verify consistency", "db health", or otherwise wants to verify Knowledge-DB and docs/ consistency via MCP. Runs 14 consistency checks (document metadata, cross-references, orphaned relations, status consistency, CLAUDE.md weight, local/DB sync, AI-Steno format, skill-evolution metrics, AI-Batch status) and persists findings via Skill Evolution. Loop-capable. ⚡ MCP-required — aborts if Knowledge-DB is unreachable.
mxhelp
Use when the user says "/mxHelp", "/mxHelp <name>", or asks which mx-skill does what. Lists all installed mx*-skills grouped by category, or explains one skill in detail. Pure reader — no side effects.
mxinitproject
Use when the user says "/mxInitProject", "bootstrap project", "init project", "setup ai config", "initialize claude config", "scaffold project", or otherwise wants to bootstrap a new repository with the mxLore AI-documentation structure (CLAUDE.md, docs/ layout, optional MCP project registration). Idempotent — safe to re-run. Detects MCP mode vs local fallback. NEVER overwrites existing content.
mxmigratetodb
Use when the user says "/mxMigrateToDb", "migrate to db", "migrate local docs to mcp", "sync local docs", "import docs to knowledge db", "--extract-backlog", "extract legacy backlog", or otherwise wants to import local `docs/*.md` fallback files into the MCP Knowledge-DB. Runs after MCP outages (when offline-fallback created local files) or once after initial MCP setup. Supports dry-run, cleanup, sync, scan, and --extract-backlog modes. ⚡ MCP-required — aborts if Knowledge-DB is unreachable.
mxplan
Use when the user says "/plan", "/mxPlan", "create a plan", "update the plan", "write a plan for X", "plan this feature", or otherwise wants to structure a multi-step implementation task before coding. Creates or updates plans via MCP-Tools in the mxLore knowledge DB; maintains task checklists with auto-archive on completion.
mxspec
Use when the user says "/spec", "/mxSpec", "write a spec", "write a specification", "requirements doc", "acceptance criteria", "define requirements", or needs to specify a feature or component before planning or implementation. Creates or updates specifications via MCP-Tools in the mxLore knowledge DB; tracks acceptance criteria with auto-archive on full completion.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.