worktrail-go

Use when the user invokes worktrail-go, asks to pick up queued work, resume active specs, implement or fix a spec, route engineering work, or orient across repositories. Renders the orientation dashboard, classifies free-text requests, claims/resumes handoff briefs, and dispatches SDD work without requiring the user to know sdd-workflow. Grammar: worktrail-go [REPO] <noun> <verb>, nouns handoff / spec / pr / decision. Triggers: worktrail-go, worktrail-go help, worktrail-go spec fix, worktrail-go spec implement, worktrail-go spec route F, worktrail-go handoff new, worktrail-go handoff auto, worktrail-go decision answer, worktrail-go BRIEF-ID, bare worktrail-go, multi-repo orientation.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%Weight 40%Scale 1-5

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

A well-structured, highly actionable dispatcher workflow with excellent sequencing, validation gates, and progressive disclosure into real reference files. Its main weakness is conciseness: the rationale and incident-citation prose, plus repeated restatements of the same ownership guarantee, make it noticeably longer than it needs to be.

Suggestions

Collapse the repeated dispatch-id / same-owner guarantee explanations (currently restated in the Invocation Context, Phase 2, Phase 6, Phase 7, and Dispatch Contract sections) into a single authoritative statement that later phases reference by name.

Move the live-incident citations and date-stamped 'confirmed live YYYY-MM-DD' asides into the relevant reference files or a dedicated 'incident log' note, so the main phase flow stays procedural rather than evidentiary.

Trim the rationale paragraphs that explain why each guard exists to one sentence, keeping the guard's actionable rule; the surrounding bash already shows the mechanic.

Dimension	Reasoning	Score
Conciseness	The body is dense and high-signal rather than padded with basics, but at ~1050 lines it repeats the same dispatch-id/claim-ownership guarantee across phases and surrounds each bash block with lengthy rationale and live-incident citations ('confirmed live 2026-08-24') that could be tightened.	3 / 5
Actionability	Concrete, executable bash blocks with real flags, a dispatch-mode decision table, and worked routing YAML examples cover the common cases; the minor gap is that several full procedures are delegated to references/*.md rather than being copy-paste complete in the body itself.	4 / 5
Workflow Clarity	Phases 0-8 are explicitly sequenced with validation checkpoints and feedback loops throughout: the Phase 5.5 collision/staleness guards, the intake triage gate, assert-terminal as a hard gate, and the CI watch loop with rerun/patch/escalate branches.	5 / 5
Progressive Disclosure	SKILL.md is an overview that points to 15 real, one-level-deep references/*.md files, each clearly signaled inline ('Full procedure: references/batch-consumption.md'); heavy procedures are appropriately split out and navigation is easy.	5 / 5
	Total	17 / 20 Passed

Description

95%Weight 40%Scale 1-5

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 strong: it gives a concrete action list, an explicit 'Use when...' trigger clause with natural phrasing, and a distinct command namespace that prevents misfiring. The only soft spot is a couple of slightly generic action verbs ('dispatches SDD work', 'route engineering work').

Dimension	Reasoning	Score
Specificity	Names the domain and lists several concrete actions ('Renders the orientation dashboard, classifies free-text requests, claims/resumes handoff briefs, and dispatches SDD work'), but 'dispatches SDD work' and 'route engineering work' are slightly generic, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both what ('Renders... classifies... claims/resumes... dispatches') and when ('Use when the user invokes worktrail-go, asks to pick up queued work, resume active specs...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage including synonyms and literal command forms ('pick up queued work', 'resume active specs', 'implement or fix a spec', 'worktrail-go handoff auto', 'worktrail-go BRIEF-ID', 'bare worktrail-go').	5 / 5
Distinctiveness Conflict Risk	A clear niche as the worktrail front-door dispatcher with distinct literal command triggers ('worktrail-go', its grammar, and named noun/verb forms), giving minimal conflict risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1051 lines); consider splitting into references/ and linking	Warning
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	13 / 16 Passed

Repository: behindthedash/worktrail
Path: skills/worktrail-go/SKILL.md
Commit: ca98247

Reviewed: ~4 hours 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.