Claude Skills by monoes

Automatically select the optimal monoswarm topology based on task complexity — use pre-task hook recommendations, monoswarm init flags, and performance optimize CLI

Analyze and apply system-level performance optimizations — memory, CPU, and latency using npx monomind performance optimize

Real-world pair programming scenarios — JWT auth, memory leak debugging, TDD, code review, and refactoring with effective prompt patterns

Pair programming collaboration modes — driver, navigator, TDD, review, and debug modes with effective prompts for each

Pair programming session lifecycle — pre-session setup, context setting, mid-session quality checks, breakpoints, end-of-session recording, and multi-session continuity

Execute predefined stream-chain pipelines for common development workflows — analysis, refactor, test, optimize. Each step feeds full context into the next.

Execute custom stream chains where you define the prompt sequence. Each step receives the full output of the previous step as context.

Show the Monomind token usage dashboard — reports spend and call counts for today, week, 30days, or month

Truth skill — assess system health, agent reliability, and task quality using real MCP metrics tools. Use when you want a holistic picture of how well the system is performing.

Toggle the Monomind statusline panel between full (multi-line dashboard) and compact (single-line) mode

Development workflow coordination pattern — hierarchical swarm for structured implementation tasks using real MCP tools and npx monomind workflow run -t development

Research workflow coordination pattern — mesh swarm for comprehensive exploration using real MCP tools and npx monomind workflow run -t research

Create and save custom workflow templates using npx monomind workflow template create — save successful workflows for reuse

Run multi-agent workflows using built-in templates (development, research, testing, security-audit, etc.) via real npx monomind workflow run CLI

Browse, inspect, and manage workflow templates — list built-in templates, show template details and stages, validate workflow files

Find the single best specialized agent from the verified ~98-agent roster using two-stage LLM domain→agent selection

Comprehensive truth scoring, code quality verification, and automatic rollback system with a 0.95 confidence threshold for ensuring high-quality agent outputs and codebase reliability.

Comprehensive UI QA and browser automation using the native monomind browse CDP client — full test lifecycle from discovery through performance profiling, with structured pass/fail/warn reporting.

Self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination. Wraps the separate `agentic-jujutsu` npm package.

GitHub workflow guidance for monomind projects — issues, PRs, releases, repo structure, and multi-package sync. Trigger on "open a PR", "manage issues", "cut a release", "sync packages", or any GitHub Actions/repo automation request. All GitHub operations use the `gh` CLI plus monomind's MCP GitHub tools — there is no `monomind github` CLI command group.

Automated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration. Includes pre/post task hooks, session management, Git integration, memory coordination, and neural pattern training for enhanced development workflows.

Mastermind access — manage org membership roles (owner/admin/operator/viewer), granular permission grants, invite tokens, and pending join requests. Controls who can do what inside an org.

Mastermind activity — full activity feed for an org with event-type filtering, actor lookups, and entity name resolution. Fetches up to 200 recent events across issue, project, goal, agent, and routine entity types. Mirrors Activity.tsx.

Mastermind adapter-manager — global instance-level adapter catalog. Lists all built-in and npm-installed adapters, enables/disables them in menus, reinstalls from npm to pick up updates, adds custom HTTP adapters, and removes custom ones. Complements mastermind:adapters (per-org) with the global registry. Mirrors AdapterManager.tsx.

Mastermind adapters — install, enable, disable, reload, and remove LLM adapter plugins per org. Supports claude-local, gemini-local, codex-local, cursor, hermes, http, and custom adapters.

Mastermind agent-detail — deep per-agent inspection: show config, run history, budget usage, heartbeat status, assigned skills, and reset/reconfigure a single agent within an org.

Shared utility — registry-aware agent selection for mastermind domain skills. Reads .monomind/registry.json and returns ranked agent slugs/names for a given task, prompt, and category filter. Include this logic wherever a domain skill needs to pick the best agent(s) instead of hardcoding types.

Mastermind agents — list, inspect, hire, pause, and remove agents in a running org. Shows status, last heartbeat, adapter config, and burn rate per agent.

Mastermind approval-detail — deep inspection and action on a single approval request. View approval metadata, payload, comments, linked issues, and perform approve/reject/revision/resubmit actions. Mirrors ApprovalDetail.tsx.

Mastermind backup — create, list, and restore compressed org backups. Archives all org data files (config, goals, routines, approvals, projects, members, issues, workspaces, worktrees, environments, plugins, adapters, threads, budgets, bootstrap, and activity log) into a timestamped tarball.

Mastermind bootstrap — one-time org initialization that primes the CEO/boss agent with org context, goal hierarchy, and a signed invite token. Run after createorg before first runorg.

Mastermind budgets — view, set, and track token/cost budgets for agents and the entire org. Shows current spend vs. limits, alerts on overages, and lets board members adjust per-agent or org-wide budgets. Reads from -budgets.json org state files.

Mastermind createorg — design and persist an autonomous agent organization (Org Runtime v2) as a `.monomind/orgs/<name>.json` config that `monomind org run/serve` loads directly. Supports optional --schedule flag for daemon-scheduled orgs.

Systematic root-cause debugging protocol. Use before ANY fix attempt — for test failures, bugs, unexpected behavior, build failures, performance regressions.

Agent Delegation Capability — injected into every spawned agent prompt so subagents can further delegate specialized work. Never invoked directly; referenced by mastermind-protocol/SKILL.md and domain skills.

MUST use before any creative work — creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements, and design through collaborative dialogue before any implementation.

Mastermind diagnose — forensic procedure for investigating why agent work stalled, looped, or went too deep. Surfaces the exact stop-point in the issue tree, frames the fix as a product rule respecting three invariants (productive work continues / only real blockers stop work / no infinite loops), and delivers an approved plan before any code changes. Mirrors diagnose-why-work-stopped Paperclip skill.

Mastermind env — audit and configure the runtime environment for an org. Shows LLM provider config, memory backend, agent JWT settings, logging, and storage — highlighting missing or misconfigured values.

Mastermind environments — manage execution environments (local, SSH, sandbox) for an org. Controls where agent workloads run, SSH connection details, and which environment is the default.

Load a written implementation plan, review it critically, execute all tasks step by step, and hand off to mastermind:review when complete.

Mastermind export — full org portability. Export an org to a compressed archive (tar.gz or zip) with file tree selection, and import from an archive with collision strategy and adapter override. Mirrors Paperclip's CompanyExport/CompanyImport pages.

Mastermind goal-detail — deep per-goal inspection and management. Show sub-goal tree, linked projects, edit title/status/description/priority, add child goals, and close or reopen a single goal within an org.

Mastermind goals — define, track, and visualize hierarchical goals for an org. Goals link to tasks, have progress metrics, and form a goal tree.

Mastermind idea domain — product ideation, feature brainstorming, pivot exploration. Spawns an Idea Manager agent for divergent thinking, then validates, elaborates, and decomposes approved ideas into actionable subtasks on separate dev and ops task boards.

Mastermind import — import an org from a portable ZIP archive exported by mastermind:export. Previews the archive contents, shows agent plans (create/update/skip), lets you choose a collision strategy, and applies the import to the local .monomind/orgs/ directory. Mirrors CompanyImport.tsx.

Mastermind inbox — unified view of everything that needs human attention across all orgs: pending approvals, running heartbeats, active task assignments, and budget alerts. The single place to check before starting work.

Mastermind instance — global instance-level settings including scheduler heartbeat management across all orgs, system-wide configuration, and cross-org health overview.

Shared intake protocol for mastermind — rich-prompt detection, comprehensive intake questions asked one at a time, and LLM-decide logic. Never invoked directly; called by master and standalone domain commands.

Mastermind invite-landing — accept an org invite as a human member or as an agent. Validates the invite token, presents org/role info, and processes join as human (name/email) or as an agent (adapter type, model, agent name, config). Mirrors InviteLanding.tsx.

Mastermind invites — manage org invitations and join request queue. Create/revoke invites with role assignment, view invite history, review pending join requests (human and agent), and approve or reject them. Merges CompanyInvites and JoinRequestQueue pages.