CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

72

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

The body is highly actionable with strong workflow validation, but it is padded with persona/creative flourishes and has a real progressive-disclosure problem: content that should live only in reference files is duplicated inline while 8 bundle files are orphaned and undocumented.

Suggestions

Remove the inline System Readiness Checklist, Commands summary, Creative Freedom, and Examples sections from the body and point to their existing reference files instead — this eliminates duplication and orphans simultaneously.

Add the 8 unreferenced reference files (errors.md, first-contact.md, interaction-style.md, creative-freedom.md, examples.md, commands-(you-run-these).md, system-readiness-checklist.md) to the Reference Files table with "When to Load" guidance so the full bundle is discoverable.

Trim the Persona and Creative Freedom example-output blocks to a short directive; the character table and GUPP principle already convey the in-world voice without multiple illustrative dialogue samples.

DimensionReasoningScore

Conciseness

Operational guidance is mostly efficient, but the Persona, Creative Freedom, and illustrative example-output sections (large ASCII diagrams, character-voice samples) are decorative padding that could be tightened without losing clarity.

2 / 3

Actionability

Concrete, copy-paste-ready commands throughout: "gt sling <bead> <rig>", "bd create --title \"...\"", "gt mail send <rig>/witness -s ... -m ...", plus exact grep navigation recipes — fully executable guidance.

3 / 3

Workflow Clarity

Clear sequenced workflows with explicit validation checkpoints: the System Readiness Checklist BLOCKERS, the 6-step Full Flow Verification, and "Never Assume - Verify Everything" provide feedback loops ("If ANY step fails → investigate and fix") for destructive/batch operations.

3 / 3

Progressive Disclosure

The 5-file reference table with "When to Load" guidance is well signaled, but 8 of 13 bundle files (errors.md, first-contact.md, interaction-style.md, creative-freedom.md, examples.md, commands-(you-run-these).md, system-readiness-checklist.md) are unreferenced, and the body duplicates content that exists as separate reference files (e.g. System Readiness Checklist verbatim in system-readiness-checklist.md).

2 / 3

Total

10

/

12

Passed

Description

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.

The description is exemplary: third-person voice, explicit "Use when" triggers, multiple concrete actions, and a distinctive vocabulary set that minimizes conflict risk. It hits the top anchor on every dimension.

DimensionReasoningScore

Specificity

"Handles installation, workspace setup, work tracking, agent lifecycle, crash recovery, and all gt/bd CLI operations" lists multiple concrete, specific actions rather than vague language.

3 / 3

Completeness

Explicitly answers both what ("Multi-agent orchestrator for Claude Code... Handles installation...") and when ("Use when user mentions gastown... or wants to run multiple AI agents on projects simultaneously"), with an explicit "Use when" trigger clause.

3 / 3

Trigger Term Quality

Broad coverage of natural terms a user would say: "gastown, gas town, gt commands, bd commands, convoys, polecats, crew, rigs, slinging work, ... beads, hooks, molecules, workflows" plus common variations.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive gastown-specific vocabulary (gt/bd commands, polecats, beads, the witness, the mayor, the refinery) creates a clear niche unlikely to trigger for other skills.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (705 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
jeremylongshore/claude-code-plugins-plus-skills
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.