abilities

Run a remote Trinity agent task in a sequential, bounded loop — a fixed number of iterations or until a stop signal, with optional response chaining. Fires server-side via run_agent_loop (caller can disconnect), then polls and renders progress. The remote, durable counterpart to Claude Code's local /loop. Add `local` to run the same bounded loop natively in this session instead — inline back-to-back iterations, or a hand-off to the built-in /loop when a cadence is given.

Make any agent a system-aware orchestrator — installs /discover-agents (discover the fleet from live Trinity and/or a repo list into a descriptive fleet/system-map.yaml), /compose-system (turn the map into a Trinity SystemManifest and deploy_system), and /orchestrate (route, fan out, and run ephemeral agents via Trinity MCP). Aligns with Trinity's existing SystemManifest; no parallel standard.

Create a new skill or playbook. Guides through requirements gathering and generates the appropriate template based on complexity.

Create an executive chief of staff agent — asks about your tools, team, and priorities, then scaffolds a Trinity-compatible agent for daily briefings, meeting prep, and decision tracking

Create a personal medical-records agent — bootstraps a profile from your existing health documents, then ingests new files, maintains structured memory, tracks lab trends, prepares doctor visits, and runs an evidence-based nutrition + supplement framework

Create a content writer agent — asks about your brand voice, platforms, and topics, then scaffolds a Trinity-compatible ghostwriter agent that writes in your voice

Create a knowledge-base agent — asks a structured 6-question interview about the domain's ontology, then scaffolds a Cornelius-shaped Trinity-compatible KB agent with a typed graph, 7-layer vault, subagents, and scheduled coherence jobs

Create a B2B SaaS sales research agent — asks domain-specific questions and scaffolds a Trinity-compatible prospector agent customized to your sales stack

Create an email gateway agent — asks domain-specific questions and scaffolds a Trinity-compatible receptionist agent for public-facing email communication and request routing

Create a competitive intelligence agent — asks domain-specific questions and scaffolds a Trinity-compatible agent for tracking competitors, monitoring changes, and producing actionable intelligence

Create a website management agent — asks about your web development workflow and scaffolds a Trinity-compatible webmaster agent for building and deploying Next.js sites

Generate an agent-specific `/update-dashboard` skill that keeps `dashboard.yaml` current for Trinity. Analyzes the agent's purpose and data sources, proposes metrics, gets user approval, then scaffolds a schedulable skill.

Onboard this agent to Trinity platform. Creates required files, configures MCP connection, and optionally deploys to remote.

Scaffold a Trinity-compatible long-running pipeline inside any agent — creates projects/<slug>/{project.md, pipeline.yaml, instances/}, copies pipeline-tick/status/recover/pause/resume skills into .claude/skills/, sets up the ~/.trinity/ read surface, installs the heartbeat schedule, adds a dashboard section, and removes the harmful legacy pre-check hook if present.

Modify an existing playbook based on conversation context or explicit instructions. Use when user wants to update, fix, extend, or refine a playbook they already have.

Lint a pipeline.yaml — schema check, DAG acyclicity, referenced-skill existence, precondition kind registration. Pure linter — prints a report, writes no files. Heartbeat does not require validation to have run; this is a developer convenience.

Scaffold a new Trinity-compatible Claude Code agent from scratch on any topic. Creates directory, CLAUDE.md, skills, and Trinity files — ready for development.

Synchronize this agent with one or more remote instances on Trinity via GitHub. Supports multiple remotes and branch-based versioning.

Apply best-practice improvements to an existing agent — runs /review-agent to find issues, then proposes exact before/after changes to CLAUDE.md, skills, and Trinity files and applies the approved ones.

Review an existing agent against best practices and report findings — a read-only audit of CLAUDE.md, skills, composition integrity, and Trinity readiness. Produces a prioritized findings report and hands off to /adjust-agent or /adjust-playbook to apply fixes. Makes no changes itself.

Connect to a Trinity instance and configure MCP server. Authenticates via email OTP, provisions an MCP API key, and writes `.mcp.json` — no CLI installation required.

Add GitHub Issues backlog workflow to any agent — creates the full development cycle (backlog, claim, close, groom, roadmap, autoplan, commit, sprint, work-loop)

Add git-as-state hooks to an agent — auto-commits on Stop, rebases on SessionStart, snapshots on PreCompact. Gives agents durable cross-session memory through their own repo.

Add a memory system to an agent — file awareness, knowledge graph, structured state, or multi-session tracking

Scaffold a new instance (tenant / zone / case) of an existing pipeline — creates projects/<slug>/instances/<instance>/{config.yaml, state.json} and syncs state.json to ~/.trinity/pipeline-state/.

Append a new stage to an existing pipeline.yaml — asks for stage id, skill, timeout, retry policy, and position in the DAG. Validates DAG acyclicity and syncs the read surface.

Analyze a skill issue before implementing — reads the affected SKILL.md, identifies what changes are needed and any risks

Show current GitHub Issues backlog — what's in progress, what's next, priorities

Claim the next issue from the backlog — picks highest priority todo, moves it to in-progress

Close the current issue without a git commit — adds summary comment and marks done. Use /commit instead when skill files changed.

Commit changed skill files and close the in-progress issue — writes a traceability commit message referencing the issue number

Groom the backlog — tag untagged issues with skill:* labels, verify priorities, surface stale in-progress work

Plan and execute large multi-session projects. Analyzes scope, splits into ordered sessions, executes session-by-session with approval gates and state tracking.

Strategic view of the agent backlog — open issues grouped by skill, showing which areas have the most work

Human-supervised development cycle — orchestrates roadmap → claim → autoplan → implement → commit for one skill issue

Autonomous work loop — pick one backlog issue, execute it, close it, exit. Re-invoked by scheduler for the next.

Clone the Cornelius agent repository and guide the user to open Claude Code inside it

Discover and launch agent creation wizards — your single entry point for creating agents, websites, and projects

Scaffold a complete, self-contained Next.js 15 website with Tailwind CSS, TypeScript, and Vercel deployment. Creates production-ready project structure with design system, components, pages, SEO, and content management — ready to deploy in minutes.

Add a Testing section to a feature flow document using the standard template.