cross-machine-coordination

Enables squad agents on different machines to share work via git-based task queuing

Quality

63%

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

Fix and improve this skill with Tessl

tessl review fix ./.squad/skills/cross-machine-coordination/SKILL.md

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 content is highly actionable with clear, validated workflows, but it is over-long for a single SKILL.md due to a redundant repeated example and tangential sections, and it does not split detailed material into reference files.

Suggestions

Remove the near-duplicate GPU voice-clone example (it already appears in Usage) and trim or drop the Migration and Future Enhancements sections to tighten the token budget.

Move the detailed File Formats, Security Model, and full Examples into separate reference files under references/ and link to them from a concise overview, so SKILL.md stays a lean entry point.

Dimension	Reasoning	Score
Conciseness	The body is concrete and avoids lecturing on basics, but it is padded: the GPU voice-clone task YAML appears near-verbatim in both Usage and Examples, and the Migration and Future Enhancements sections add length without guiding execution.	2 / 3
Actionability	It provides copy-paste-ready bash commands (gh issue create, git add/commit/push), concrete YAML/JSON schemas, and explicit file paths; the only pseudocode is explicitly labeled 'Pseudo-code (Ralph implementation)', which justifies the flexibility.	3 / 3
Workflow Clarity	Multi-step processes are numbered (pull, validate, execute, write result, commit), the Validation Pipeline is explicit, and error handling defines feedback loops for failures, timeouts, and network retries.	3 / 3
Progressive Disclosure	Sections are well-organized, but the file is monolithic at ~440 lines with file-format specs, the security model, and full examples all inline; no bundle files exist and the single external pointer (research/.../README.md) is a bare path rather than a clearly signaled reference.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 conveys a clear what and a distinct niche, but lacks any explicit when-to-use trigger and relies on internal jargon over natural user language, leaving every dimension at the mid level.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when coordinating work across laptop, DevBox, or Azure VMs, or when the user asks to run tasks on a remote machine.'

Replace jargon with user-facing terms and add common variations: 'coordinate tasks across machines', 'queue remote work', 'share results between machines'.

List multiple concrete actions (e.g. 'assign GPU workloads, queue scripts, return results') instead of the single broad phrase 'share work'.

Dimension	Reasoning	Score
Specificity	It names the domain ('squad agents on different machines') and mechanism ('git-based task queuing') plus one broad action ('share work'), but does not list multiple specific concrete actions like the score-3 anchor requires.	2 / 3
Completeness	It clearly states what the skill does but provides no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Some natural terms appear ('share work', 'different machines'), but it leans on internal jargon ('squad agents', 'git-based task queuing') and omits common variations a user might say ('coordinate', 'across machines', 'remote tasks').	2 / 3
Distinctiveness Conflict Risk	The cross-machine git-queuing niche is fairly specific, but the generic 'share work' framing and absence of explicit triggers leave some overlap risk with general coordination or git-task skills.	2 / 3
	Total	8 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 7 missing	Warning

	Total	14 / 16 Passed

Repository: bradygaster/squad
Path: .squad/skills/cross-machine-coordination/SKILL.md
Commit: e23dd92

Reviewed: 1 day 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.