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.

2026-07-119

add-orchestrator

Abilityai/abilities

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.

2026-07-119

create-playbook

Abilityai/abilities

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

2026-07-099

install-chiefofstaff

Abilityai/abilities

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

2026-07-099

doctor

Abilityai/abilities

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

2026-07-099

install-ghostwriter

Abilityai/abilities

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

2026-07-099

name	roadmap
description	Strategic view of the agent backlog — open issues grouped by skill, showing which areas have the most work
allowed-tools	Bash, Read
user-invocable	true
metadata	{"version":"1.0","created":"2026-04-28T00:00:00.000Z","author":"Ability.ai","changelog":["1.0: Initial version — shows the agent backlog grouped by affected skill to reveal which areas have the most work"]}

Roadmap

ℹ️ First, set expectations: before anything else, print one short line with this skill's version and its most recent change — the top entry of metadata.changelog above — e.g. roadmap vX.Y — recent: <summary>. Then proceed.

Shows the agent backlog grouped by affected skill rather than by priority. Use this to understand which parts of the agent need the most work, and to choose a sprint focus area. For the day-to-day priority-ordered view, use /backlog.

State Dependencies

Source	Location	Read	Write	Description
GitHub Issues	Current repo	Yes	No	Open issues
GitHub Labels	skill:, priority:, status:*	Yes	No	Group and filter

Process

Step 1: Verify GitHub CLI

gh auth status 2>&1 | head -3

Step 2: Fetch Open Issues

gh issue list --state open --json number,title,labels,updatedAt --limit 100

Step 3: Group by Skill

Parse the skill:* label from each issue. Group issues into buckets:

One bucket per skill:<name> label present
A separate bucket for project-level issues (no skill label)

For each bucket, sort issues by priority (p0 → p1 → p2 → unset).

Step 4: Format Output

## Agent Roadmap

### skill:adjust-playbook (3 open)
| # | Title | Priority | Status |
|---|-------|----------|--------|
| 14 | Fix archive flag behavior | p0 | todo |
| 9  | Support batch adjustments | p1 | todo |
| 11 | Better breaking-change detection | p2 | todo |

### skill:work-loop (2 open)
| # | Title | Priority | Status |
|---|-------|----------|--------|
| 6  | Handle blocked issues more gracefully | p1 | todo |
| 3  | Add skill-routing by label | p1 | in-progress |

### skill:groom (1 open)
| # | Title | Priority | Status |
|---|-------|----------|--------|
| 18 | Support bulk priority assignment | p2 | todo |

### Project-level (2 open)
| # | Title | Priority | Status |
|---|-------|----------|--------|
| 1  | Add onboarding checklist to README | p2 | todo |
| 5  | Update plugin.json description | p2 | todo |

---
Total open: 8 issues across 3 skills + project-level

Tip: Run `/groom` to tag untagged issues, or `/claim` to start the highest priority item.

Step 5: Highlight Focus Recommendation

If there are p0 issues, note the urgency: "P0 items need immediate attention."

If a skill has many open issues, note it as a likely sprint focus.

Outputs

Skill-grouped issue view
Priority ordering within each group
Count of untagged (project-level) issues
Focus area recommendation

Error Handling

Error	Action
gh not authenticated	Tell user to run `! gh auth login`
No open issues	Report "No open issues — backlog is clear"
No skill labels used	Suggest running `/groom` first