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.

Quality

81%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

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 provides a clear 'what' (multi-agent orchestrator with specific capabilities), an explicit and comprehensive 'when' clause with extensive trigger terms, and uses highly distinctive domain-specific vocabulary that minimizes conflict risk. The only minor concern is that the sheer volume of trigger terms could feel slightly overwhelming, but each serves a legitimate purpose for skill selection.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: installation, workspace setup, work tracking, agent lifecycle, crash recovery, and gt/bd CLI operations. These are clear, actionable capabilities.	3 / 3
Completeness	Clearly answers both 'what' (multi-agent orchestrator handling installation, workspace setup, work tracking, agent lifecycle, crash recovery, CLI operations) and 'when' (explicit 'Use when' clause with extensive trigger terms and scenarios).	3 / 3
Trigger Term Quality	Extensive coverage of trigger terms including the tool name ('gastown', 'gas town'), CLI commands ('gt commands', 'bd commands'), domain-specific terminology ('convoys', 'polecats', 'crew', 'rigs', 'beads', 'hooks', 'molecules'), role names ('the witness', 'the mayor', 'the refinery', 'the deacon'), and natural language phrases ('multi-agent coordination', 'run multiple AI agents'). Very thorough keyword coverage.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with unique domain-specific terminology (gastown, convoys, polecats, gt/bd commands) that is unlikely to conflict with any other skill. The niche is very clearly defined.	3 / 3
	Total	12 / 12 Passed

Implementation

62%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is highly actionable with excellent workflow clarity, featuring concrete commands, validation checklists, and clear error recovery paths. However, it is severely bloated — the persona instructions, creative freedom examples, interaction style guidance, and lengthy ASCII art demonstrations consume enormous token budget for content that could be drastically condensed or moved to reference files. The skill tries to be both an operational manual and a personality guide, and the personality/style content dominates at the expense of token efficiency.

Suggestions

Move the Creative Freedom section (with all its examples), Persona section, and Interaction Style section to a separate reference file like references/style-guide.md — these consume ~150 lines that aren't operational.

Condense the Examples section dramatically: keep one example per mode (Learning/Setup/Operating) and cut them to 3-4 lines each instead of full ASCII art demonstrations.

Remove the Capability Checklist table at the end — it duplicates the Reference Files table and adds no actionable information.

Reduce repetition of 'CALL THE TOOL' / 'DO NOT just write text' instructions to a single clear statement rather than restating it 5+ times across sections.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at 400+ lines. Extensive sections on persona, creative freedom, interaction style with lengthy examples, ASCII art demonstrations, and multiple JSON examples for AskUserQuestion all consume significant tokens. The capability checklist table at the end, the repeated emphasis on 'CALL THE TOOL' (stated 5+ times), and the elaborate examples section with full ASCII diagrams are all padding. Much of this content (persona instructions, creative flourishes examples, character voice examples) could be dramatically condensed.	1 / 3
Actionability	Provides concrete, executable commands throughout (gt sling, gt doctor, bd create, etc.), specific bash commands for navigating reference files with grep, complete JSON schemas for AskUserQuestion tool calls, and a detailed system readiness checklist with exact verification commands. The command reference table and troubleshooting steps are copy-paste ready.	3 / 3
Workflow Clarity	Multi-step workflows are clearly sequenced with explicit validation checkpoints. The System Readiness Checklist provides numbered steps with BLOCKER designations, the Full Flow Verification is a 6-step sequence with clear pass/fail criteria, and the setup flow includes diagnostic verification. Error severity is categorized with specific remediation actions. Feedback loops are present (fix → re-validate → proceed).	3 / 3
Progressive Disclosure	References to external files (tutorial.md, setup.md, commands.md, concepts.md, troubleshooting.md) are well-signaled with a clear table and grep navigation instructions. However, no bundle files were provided to verify these exist, and the SKILL.md itself is monolithic — the persona section, creative freedom section, interaction style section, and extensive examples could all be in separate reference files rather than inline, making the main file bloated.	2 / 3
	Total	9 / 12 Passed

Validation

90%

Warnings & errors only

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: a518c67

Reviewed: 12 days ago

Table of Contents

Discovery Implementation Validation

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.