How long does the integration take?

Change one base URL in an OpenAI-compatible client, or install the Python or TypeScript SDK; the quickstart routes a first request in a few minutes.

Will this lock us into another vendor?

No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.

What happens when a provider fails?

The router falls back to the next model your policy allows and records the fallback in the trace, so an outage costs a retry, not an incident.

next - Prompt - OpenSmartRoute

Name: next
Author: troylar

Prompt file imported from troylar/devsync (.claude/commands/next.md). Copyright stays with the author.

/next Skill

Show a prioritized work queue of open issues, sorted by priority labels and grouped by VISION.md direction areas.

Usage

/next                      # Prioritized queue (excludes in-progress/blocked)
/next --all                # Include in-progress and blocked issues
/next --area mcp           # Filter by vision direction area

Workflow

Step 1: Ensure Labels Exist

Create all lifecycle labels idempotently:

gh label create "priority:critical" --color "B60205" --description "Blocking other work" --force
gh label create "priority:high" --color "D93F0B" --description "Important, should be next" --force
gh label create "priority:medium" --color "FBCA04" --description "Standard priority" --force
gh label create "priority:low" --color "0E8A16" --description "Nice to have" --force
gh label create "in-progress" --color "6F42C1" --description "Actively being worked on" --force
gh label create "ready-for-review" --color "0075CA" --description "PR submitted" --force
gh label create "blocked" --color "9E9E9E" --description "Blocked by something" --force

Step 2: Fetch Data (parallel)

A — All open issues:

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

B — VISION.md direction areas: Read VISION.md and extract the "Direction (Current)" section. Identify the 5 direction areas:

AI Tool Integration
Package Management
MCP Integration
CLI & UX
Docs & Quality

C — In-progress and blocked issues:

gh issue list --label "in-progress" --state open --json number,title,labels,assignees
gh issue list --label "blocked" --state open --json number,title,labels,assignees

Step 3: Categorize Each Issue

For each open issue:

Priority — from priority:* labels:
- priority:critical -> Critical
- priority:high -> High
- priority:medium -> Medium
- priority:low -> Low
- No priority label -> Medium (default)
Vision area — keyword match the issue title and body against direction areas:
- AI Tool Integration: ai tool, IDE, cursor, claude, windsurf, copilot, kiro, roo, cline, codex, translator, detection
- Package Management: package, manifest, template, version, dependency, bundle, component
- MCP Integration: MCP, server config, credential, sync
- CLI & UX: CLI, command, TUI, Typer, Rich, output, error, UX
- Docs & Quality: doc, test, CI, coverage, lint, quality, README
- Other: anything that doesn't match
Status:
- in-progress label -> In Progress
- blocked label -> Blocked
- ready-for-review label -> Ready for Review
- None -> Ready
Dependencies — scan issue body for "depends on #N" / "blocked by #N"

Step 4: Filter

Default: exclude issues with in-progress, blocked, or ready-for-review labels
With --all: include everything
With --area <area>: only show issues matching that vision area

Step 5: Display Queue

Sort by priority tier (critical -> high -> medium -> low), then by issue number.

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
  📋 Work Queue
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

📋 AI Tool Integration
  🟡 #83 — Add Zed AI tool support
  🟢 #91 — Improve cursor rule translation

📋 Package Management
  🟡 #95 — Add version constraint support
  🟢 #110 — Template system for packages

📋 MCP Integration
  🟡 #88 — Credential sync improvements

📋 CLI & UX
  🟡 #102 — Better error messages for install failures

📋 Docs & Quality
  🟢 #115 — Increase test coverage

────────────────────────────────────────────

  🔴 Critical: 0  🟠 High: 0  🟡 Medium: 4  🟢 Low: 3
  📊 Total: 7 issues ready to work

────────────────────────────────────────────

Step 6: Recommend Next Item

  ⭐ Recommended: #83 — Add Zed AI tool support
     Rationale: Highest priority in AI Tool Integration,
     no dependencies, aligns with IDE-agnostic principle.

────────────────────────────────────────────
  👉 Next: /start-work 83
────────────────────────────────────────────

Guidelines

Always show #N — title for issue references
Default view should be actionable — only show issues you can start right now
If there are 0 issues ready, say so and suggest /triage --reassess or /new-issue
Priority indicators: 🔴 Critical, 🟠 High, 🟡 Medium, 🟢 Low

Install next and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

# /next Skill Show a prioritized work queue of open issues, sorted by priority labels and grouped by VISION.md direction areas. ## Usage ``` /next # Prioritized queue (excludes in-progress/blocked) /next --all # Include in-progress and blocked issues /next --area mcp # Filter by vision direction area ``` ## Workflow ### Step 1: Ensure Labels Exist Create all lifecycle labels idempotently: ```bash gh label create "priority:critical" --color "B60205" --description "Blocking other work" --force gh label create "priority:high" --color "D93F0B" --description "Important, should be next" --force gh label create "priority:medium" --color "FBCA04" --description "Standard priority" --force gh label create "priority:low" --color "0E8A16" --description "Nice to have" --force gh label create "in-progress" --color "6F42C1" --description "Actively being worked on" --force gh label create "ready-for-review" --color "0075CA" --description "PR submitted" --force gh label create "blocked" --color "9E9E9E" --description "Blocked by something" --force ``` ### Step 2: Fetch Data (parallel) **A — All open issues:** ```bash gh issue list --state open --limit 100 --json number,title,labels,assignees,body ``` **B — VISION.md direction areas:** Read `VISION.md` and extract the "Direction (Current)" section. Identify the 5 direction areas: - AI Tool Integration - Package Management - MCP Integration - CLI & UX - Docs & Quality **C — In-progress and blocked issues:** ```bash gh issue list --label "in-progress" --state open --json number,title,labels,assignees gh issue list --label "blocked" --state open --json number,title,labels,assignees ``` ### Step 3: Categorize Each Issue For each open issue: 1. **Priority** — from `priority:*` labels: - `priority:critical` -> Critical - `priority:high` -> High - `priority:medium` -> Medium - `priority:low` -> Low - No priority label -> Medium (default) 2. **Vision area** — keyword match the issue title and body against direction areas: - AI Tool Integration: ai tool, IDE, cursor, claude, windsurf, copilot, kiro, roo, cline, codex, translator, detection - Package Management: package, manifest, template, version, dependency, bundle, component - MCP Integration: MCP, server config, credential, sync - CLI & UX: CLI, command, TUI, Typer, Rich, output, error, UX - Docs & Quality: doc, test, CI, coverage, lint, quality, README - Other: anything that doesn't match 3. **Status:** - `in-progress` label -> In Progress - `blocked` label -> Blocked - `ready-for-review` label -> Ready for Review - None -> Ready 4. **Dependencies** — scan issue body for "depends on #N" / "blocked by #N" ### Step 4: Filter - Default: exclude issues with `in-progress`, `blocked`, or `ready-for-review` labels - With `--all`: include everything - With `--area <area>`: only show issues matching that vision area ### Step 5: Display Queue Sort by priority tier (critical -> high -> medium -> low), then by issue number. ``` ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 📋 Work Queue ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 📋 AI Tool Integration 🟡 #83 — Add Zed AI tool support 🟢 #91 — Improve cursor rule translation 📋 Package Management 🟡 #95 — Add version constraint support 🟢 #110 — Template system for packages 📋 MCP Integration 🟡 #88 — Credential sync improvements 📋 CLI & UX 🟡 #102 — Better error messages for install failures 📋 Docs & Quality 🟢 #115 — Increase test coverage ──────────────────────────────────────────── 🔴 Critical: 0 🟠 High: 0 🟡 Medium: 4 🟢 Low: 3 📊 Total: 7 issues ready to work ──────────────────────────────────────────── ``` ### Step 6: Recommend Next Item ``` ⭐ Recommended: #83 — Add Zed AI tool support Rationale: Highest priority in AI Tool Integration, no dependencies, aligns with IDE-agnostic principle. ──────────────────────────────────────────── 👉 Next: /start-work 83 ──────────────────────────────────────────── ``` ## Guidelines - Always show `#N — title` for issue references - Default view should be actionable — only show issues you can start right now - If there are 0 issues ready, say so and suggest `/triage --reassess` or `/new-issue` - Priority indicators: 🔴 Critical, 🟠 High, 🟡 Medium, 🟢 Low

{ "prompt": "# /next Skill\n\nShow a prioritized work queue of open issues, sorted by priority labels and grouped by VISION.md direction areas.\n\n## Usage\n\n```\n/next # Prioritized queue (excludes in-progress/blocked)\n/next --all # Include in-progress and blocked issues\n/next --area mcp # Filter by vision direction area\n```\n\n## Workflow\n\n### Step 1: Ensure Labels Exist\n\nCreate all lifecycle labels idempotently:\n\n```bash\ngh label create \"priority:critical\" --color \"B60205\" --description \"Blocking other work\" --force\ngh label create \"priority:high\" --color \"D93F0B\" --description \"Important, should be next\" --force\ngh label create \"priority:medium\" --color \"FBCA04\" --description \"Standard priority\" --force\ngh label create \"priority:low\" --color \"0E8A16\" --description \"Nice to have\" --force\ngh label create \"in-progress\" --color \"6F42C1\" --description \"Actively being worked on\" --force\ngh label create \"ready-for-review\" --color \"0075CA\" --description \"PR submitted\" --force\ngh label create \"blocked\" --color \"9E9E9E\" --description \"Blocked by something\" --force\n```\n\n### Step 2: Fetch Data (parallel)\n\n**A — All open issues:**\n```bash\ngh issue list --state open --limit 100 --json number,title,labels,assignees,body\n```\n\n**B — VISION.md direction areas:**\nRead `VISION.md` and extract the \"Direction (Current)\" section. Identify the 5 direction areas:\n- AI Tool Integration\n- Package Management\n- MCP Integration\n- CLI & UX\n- Docs & Quality\n\n**C — In-progress and blocked issues:**\n```bash\ngh issue list --label \"in-progress\" --state open --json number,title,labels,assignees\ngh issue list --label \"blocked\" --state open --json number,title,labels,assignees\n```\n\n### Step 3: Categorize Each Issue\n\nFor each open issue:\n\n1. **Priority** — from `priority:*` labels:\n - `priority:critical` -> Critical\n - `priority:high` -> High\n - `priority:medium` -> Medium\n - `priority:low` -> Low\n - No priority label -> Medium (default)\n\n2. **Vision area** — keyword match the issue title and body against direction areas:\n - AI Tool Integration: ai tool, IDE, cursor, claude, windsurf, copilot, kiro, roo, cline, codex, translator, detection\n - Package Management: package, manifest, template, version, dependency, bundle, component\n - MCP Integration: MCP, server config, credential, sync\n - CLI & UX: CLI, command, TUI, Typer, Rich, output, error, UX\n - Docs & Quality: doc, test, CI, coverage, lint, quality, README\n - Other: anything that doesn't match\n\n3. **Status:**\n - `in-progress` label -> In Progress\n - `blocked` label -> Blocked\n - `ready-for-review` label -> Ready for Review\n - None -> Ready\n\n4. **Dependencies** — scan issue body for \"depends on #N\" / \"blocked by #N\"\n\n### Step 4: Filter\n\n- Default: exclude issues with `in-progress`, `blocked`, or `ready-for-review` labels\n- With `--all`: include everything\n- With `--area <area>`: only show issues matching that vision area\n\n### Step 5: Display Queue\n\nSort by priority tier (critical -> high -> medium -> low), then by issue number.\n\n```\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n 📋 Work Queue\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\n📋 AI Tool Integration\n 🟡 #83 — Add Zed AI tool support\n 🟢 #91 — Improve cursor rule translation\n\n📋 Package Management\n 🟡 #95 — Add version constraint support\n 🟢 #110 — Template system for packages\n\n📋 MCP Integration\n 🟡 #88 — Credential sync improvements\n\n📋 CLI & UX\n 🟡 #102 — Better error messages for install failures\n\n📋 Docs & Quality\n 🟢 #115 — Increase test coverage\n\n────────────────────────────────────────────\n\n 🔴 Critical: 0 🟠 High: 0 🟡 Medium: 4 🟢 Low: 3\n 📊 Total: 7 issues ready to work\n\n────────────────────────────────────────────\n```\n\n### Step 6: Recommend Next Item\n\n```\n ⭐ Recommended: #83 — Add Zed AI tool support\n Rationale: Highest priority in AI Tool Integration,\n no dependencies, aligns with IDE-agnostic principle.\n\n────────────────────────────────────────────\n 👉 Next: /start-work 83\n────────────────────────────────────────────\n```\n\n## Guidelines\n\n- Always show `#N — title` for issue references\n- Default view should be actionable — only show issues you can start right now\n- If there are 0 issues ready, say so and suggest `/triage --reassess` or `/new-issue`\n- Priority indicators: 🔴 Critical, 🟠 High, 🟡 Medium, 🟢 Low", "variables": [], "notes": "Prioritized work queue sorted by priority labels and VISION.md alignment Tools: Bash, Read, Grep, Glob, Task.", "metadata": { "source": { "provider": "github-claude-commands", "repository": "https://github.com/troylar/devsync", "path": ".claude/commands/next.md", "ref": "3061f0afae4b305a873ed488ee28f588fb98abec", "url": "https://github.com/troylar/devsync/blob/3061f0afae4b305a873ed488ee28f588fb98abec/.claude/commands/next.md", "key": "troylar/devsync/.claude/commands/next.md" } } }

next

About

/next Skill

Usage

Workflow

Step 1: Ensure Labels Exist

Step 2: Fetch Data (parallel)

Step 3: Categorize Each Issue

Step 4: Filter

Step 5: Display Queue

Step 6: Recommend Next Item

Guidelines

Install next and it becomes one more candidate the router can pick - when it fits.

What it costs to adopt - in engineering time.

One base URL

No vendor lock-in

Failover built in

Use it

Manifest

Reviews