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".
53
61%
Does it follow best practices?
Impact
—
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 defines its purpose, provides extensive and distinctive trigger terms, and explicitly addresses both what the skill does and when to use it. The domain-specific vocabulary (gastown ecosystem terminology) makes it highly distinguishable from other skills. The only minor concern is that the heavy use of themed jargon (polecats, rigs, the deacon, dogs) might be confusing without context, but for skill selection purposes these serve as excellent unique triggers.
| 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, beads, hooks, molecules) and natural phrases ('slinging work', 'multi-agent coordination', 'fire up the engine', 'gt sling'). These are highly specific to this tool's vocabulary. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with unique domain-specific terminology (gastown, polecats, convoys, the witness, the mayor, the refinery, the deacon) that is extremely unlikely to conflict with any other skill. The niche is very clearly defined. | 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 content is a skeleton that describes Gas Town at a high level but provides almost no actionable guidance. The instructions read like a table of contents rather than executable steps—there are no actual CLI commands with arguments, no code examples, no validation checkpoints, and no concrete workflows. The referenced bundle files (errors.md, examples.md) are not provided, leaving the skill hollow.
Suggestions
Add concrete, executable command examples for each step (e.g., `go install github.com/...`, `gt rig add --path ./myproject --name myrig`, `bd create --title 'Fix auth bug' --rig myrig`)
Include validation checkpoints in the workflow, such as verifying installation with `gt doctor` output examples and checking bead status before proceeding to sling
Add at least one complete end-to-end example showing the full workflow from rig setup through bead creation, slinging, monitoring, and merge completion with expected terminal output
Remove obvious prerequisites like 'Terminal access for running commands' and trim the overview to focus on what Claude needs to know that it wouldn't already infer from the commands themselves
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The overview paragraph explains what Gas Town is at a high level, which is somewhat unnecessary padding. The prerequisites section includes obvious items like 'Terminal access for running commands.' However, it's not egregiously verbose—mostly reasonable length but could be tightened. | 2 / 3 |
Actionability | The instructions are entirely abstract—numbered steps like 'Install Gas Town CLI tools' and 'Create your workshop directory at ~/gt' provide no actual commands, code, or executable guidance. There are no concrete examples of gt or bd commands with arguments, flags, or expected output. | 1 / 3 |
Workflow Clarity | While steps are listed in sequence, they lack any concrete commands, validation checkpoints, or error recovery loops. For a multi-agent orchestration system involving destructive/batch operations (merging, agent lifecycle), there are no validation steps or feedback loops, which should cap this at 1 given the complete absence of specifics. | 1 / 3 |
Progressive Disclosure | References to errors.md and examples.md are well-signaled and one level deep, which is good structure. However, no bundle files were provided, so these references point to nothing verifiable. The 'Resources' section lists vague items ('Official Gastown documentation') with no actual links or paths. The main content itself is too thin 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
6e9558f
- 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.