gastown
Multi-agent orchestrator for Claude Code. Use when user mentions gastown, gas town, gt commands, bd commands, convoys, polecats, crew, rigs, slinging work, multi-agent coordination, beads, hooks, molecules, workflows, the witness, the mayor, the refinery, the deacon, dogs, escalation, or wants to run multiple AI agents on projects simultaneously. Handles installation, workspace setup, work tracking, agent lifecycle, crash recovery, and all gt/bd CLI operations.
93
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that excels across all dimensions. It uses third person voice correctly, provides comprehensive trigger terms covering the tool's unique vocabulary, clearly states both capabilities and usage conditions, and has highly distinctive terminology that minimizes conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'installation, workspace setup, work tracking, agent lifecycle, crash recovery, and all gt/bd CLI operations.' These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Multi-agent orchestrator... Handles installation, workspace setup...') and when ('Use when user mentions gastown, gt commands... or wants to run multiple AI agents on projects simultaneously'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including tool names (gastown, gas town), command prefixes (gt commands, bd commands), domain concepts (convoys, polecats, crew, rigs, multi-agent coordination), and component names (the witness, the mayor, the refinery, the deacon). | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with unique terminology (gastown, convoys, polecats, the witness, the mayor) that is unlikely to conflict with other skills. The specific tool names and concepts create a clear niche. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-structured skill with excellent actionability and workflow clarity. The System Readiness Checklist and verification steps are particularly valuable for preventing partial deployments. The main weakness is verbosity - the persona, creative freedom, and interaction style sections could be significantly condensed without losing functionality.
Suggestions
Condense the 'Creative Freedom' section - the examples are helpful but could be reduced to 2-3 representative patterns instead of 6+
Merge the 'Persona' and 'Interaction Style' sections into a single, tighter section since they overlap conceptually
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but verbose in places - the persona section, creative freedom examples, and multiple interaction style examples could be condensed. However, it avoids explaining basic concepts Claude knows and most content serves a purpose. | 2 / 3 |
Actionability | Excellent actionability with concrete commands throughout, executable bash examples, specific JSON schemas for AskUserQuestion tool calls, and clear command tables. The System Readiness Checklist provides copy-paste verification steps. | 3 / 3 |
Workflow Clarity | Outstanding workflow clarity with explicit validation checkpoints (System Readiness Checklist), clear sequencing (After Installation → After Rig Creation → Before Slinging Work → Full Flow Verification), and error severity guides with specific remediation actions. | 3 / 3 |
Progressive Disclosure | Well-structured with clear navigation to reference files (tutorial.md, setup.md, commands.md, concepts.md, troubleshooting.md). Includes grep commands for navigating large files and a clear reference table explaining when to load each file. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (705 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- numman-ali/n-skills
- Commit
8de01ac
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.