gastown
Manage 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. Trigger with phrases like "gas town", "gt sling", "fire up the engine".
67
61%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/community/gastown/skills/gastown/SKILL.mdQuality
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 clearly identifies its domain (multi-agent orchestration for Claude Code via the 'gastown' tool), lists concrete capabilities, and provides extensive trigger terms. The 'Use when...' clause is comprehensive with both tool-specific jargon and natural language variations. The highly distinctive terminology makes it virtually impossible to confuse with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: installation, workspace setup, work tracking, agent lifecycle, crash recovery, and gt/bd CLI operations. Also names the domain clearly as multi-agent orchestrator for Claude Code. | 3 / 3 |
Completeness | Clearly answers both 'what' (manage multi-agent orchestrator, handles installation, workspace setup, work tracking, agent lifecycle, crash recovery, CLI operations) and 'when' (explicit 'Use when...' clause with extensive trigger terms and example phrases). | 3 / 3 |
Trigger Term Quality | Extensive coverage of natural trigger terms including tool-specific jargon (gastown, gas town, gt commands, bd commands, convoys, polecats, crew, rigs, molecules, hooks, beads) and conceptual terms (multi-agent coordination, workflows, escalation). Includes example phrases like 'gt sling' and 'fire up the engine'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with very specific domain terminology (gastown, polecats, convoys, rigs, the witness, the mayor, the refinery, the deacon) that is unlikely to conflict with any other skill. The niche is clearly multi-agent orchestration via the 'gas town' tool. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill body reads like a table of contents rather than actionable guidance. It names many Gas Town concepts (beads, polecats, rigs, convoys, Refinery) but never provides concrete commands, code examples, or executable instructions for any of them. The workflow is a list of abstract steps without validation or error recovery, and the referenced bundle files (errors.md, examples.md) are not provided, leaving the skill hollow.
Suggestions
Add concrete, copy-paste-ready command examples for key operations (e.g., `gt rig add <repo-url>`, `bd create --title 'Fix auth bug'`, `gt sling --bead <id>`) directly in the Instructions section.
Include validation checkpoints in the workflow, such as verifying installation with `gt doctor` output expectations and checking bead status before slinging work.
Remove or flesh out the empty 'Resources' section—the current bullet points with no links or content add no value.
Provide at least one end-to-end inline example showing a complete workflow from rig setup to bead completion, rather than deferring all examples to a missing bundle file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The overview paragraph explains what Gas Town is at a high level, which is somewhat unnecessary padding. The prerequisites list includes obvious items like 'Terminal access for running commands.' However, it's not egregiously verbose—mostly just slightly padded. | 2 / 3 |
Actionability | The instructions are entirely abstract—numbered steps like 'Install Gas Town CLI tools' and 'Create work items as beads' provide no concrete commands, code, or executable guidance. There are no actual command examples, flags, or expected outputs anywhere in the body. | 1 / 3 |
Workflow Clarity | While steps are listed in sequence, they are vague descriptions rather than concrete instructions. There are no validation checkpoints, no feedback loops for error recovery, and no indication of what to do if any step fails. For a multi-step orchestration system involving agent lifecycle and merging, this is critically insufficient. | 1 / 3 |
Progressive Disclosure | References to errors.md and examples.md are appropriately one level deep and clearly signaled. However, no bundle files were provided, so these references may be broken. The 'Resources' section is empty with only vague bullet points. The body itself lacks enough substantive content to serve as a useful overview. | 2 / 3 |
Total | 6 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
3a2d27d
- 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.