OpenClaw-MAS

Scan installed skills to extract cross-cutting principles and distill them into rules — append, revise, or create new rule files.

Audit all installed OpenClaw skills for quality: content overlap, freshness, and uniqueness. Supports Quick Scan (changed only) and Full Stocktake modes.

Cluster MEMORY.md entries by theme and optionally generate SKILL.md drafts.

Export MEMORY.md to a timestamped markdown file for sharing or backup.

Import memory entries from a markdown export file, merging with MEMORY.md without duplicating.

Show current workspace memory: MEMORY.md contents, pending recalls, and index status.

List all OpenClaw agent workspaces with memory and session statistics.

Promote top short-term recalls to MEMORY.md using openclaw memory promote --apply.

Remove stale session files from the workspace sessions/ directory older than a given age.

Load the most recent session file from ~/.openclaw/workspace-main/sessions/ and resume work with full context from where the last session ended.

Save current session state to a dated file in ~/.openclaw/workspace-main/sessions/ so work can be resumed in a future session with full context.

List and inspect OpenClaw session files from the workspace sessions/ directory.

Audit all installed OpenClaw skills for missing frontmatter fields, stub descriptions, and format compliance. Reports a health dashboard.

Incrementally fix build and type errors with minimal, safe changes. Detects build system, parses errors, and fixes one at a time.

Create, verify, or list workflow checkpoints to save progress and enable safe resumption of long-running tasks.

GAN pipeline: run gan-planner → gan-generator → gan-evaluator in sequence. Loops until evaluator score ≥ 7.0.

GAN design pipeline: run gan-generator → gan-evaluator in sequence. Loops until evaluator score ≥ 7.0.

Audit the Claude Code harness configuration for reliability, cost, and throughput via the harness-optimizer agent.

Analyze the current session and extract reusable patterns worth saving as skills or instincts.

Start an autonomous agent loop (sequential, continuous-pr, rfc-dag, or infinite) via the loop-operator agent.

Inspect active loop state, progress, iteration count, and failure signals.

Recommend the best model tier (haiku/sonnet/opus) for the current task by complexity and budget.

Backend-focused multi-model workflow: Research → Ideation → Plan → Execute → Optimize → Review, Codex-led.

Multi-model collaborative execution: prototype from plan → Claude refactors and implements → multi-model audit and delivery.

Frontend-focused multi-model workflow: Research → Ideation → Plan → Execute → Optimize → Review, Gemini-led.

Multi-model collaborative planning: context retrieval + dual-model analysis → step-by-step implementation plan.

Full multi-model collaborative development workflow with intelligent routing: Frontend → Gemini, Backend → Codex.

Auto-analyze project and generate PM2 service configuration and startup commands.

Run the ECC quality pipeline on demand: lint, format, and type-check a file or project scope.

Remove dead code, unused exports, and stale dependencies via the refactor-cleaner agent.

Analyze test coverage, identify gaps, and generate missing tests to reach 80%+ coverage.

Regenerate CODEMAPS documentation for the codebase or specific modules via the doc-updater agent.

Update README, CHANGELOG, API reference, and guides to reflect recent changes via the doc-updater agent.

Classify ECC surfaces as DAILY vs LIBRARY to guide selective agent installation

Answer a quick side question without interrupting or losing context from the current task. Resume work automatically after answering.

Legacy slash-entry shim for the nanoclaw-repl skill. Prefer the skill directly.

Code review — local uncommitted changes or GitHub PR (pass PR number/URL for PR mode)

Legacy slash-entry shim for the context-budget skill. Prefer the skill directly.

Fix C++ build errors, CMake issues, and linker problems incrementally. Invokes the cpp-build-resolver agent for minimal, surgical fixes.

Comprehensive C++ code review for memory safety, modern C++ idioms, concurrency, and security. Invokes the cpp-reviewer agent.