cross-machine-coordination

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

Quality

58%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

62%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.

The body is a well-structured, validation-heavy specification with excellent workflow sequencing and explicit error handling, and the task-creation side is directly executable. Its weaknesses are the duplicated and padded example/migration sections, a core executor loop that exists only as pseudocode with no accompanying scripts, and a complete absence of progressive disclosure — everything lives inline in one long file with no reference bundle.

Suggestions

Move the full worked examples, file-format specs, and security model into reference files (e.g. references/formats.md, references/examples.md) and keep SKILL.md as a concise overview with clearly signaled links.

Replace or supplement the executor pseudo-code with an executable watcher script in scripts/ (the skill is marked 'ready for implementation' but ships no code), or explicitly justify why only pseudocode is appropriate.

Cut the duplicated Example 1 task YAML (it repeats the Usage section verbatim) and drop the 'Migration from Manual Handoff' and 'Future Enhancements' sections, which add tokens without operational value.

Dimension	Reasoning	Score
Conciseness	Most content is genuinely needed spec material (file formats, security model, config), but Example 1 restates the Usage-section task YAML nearly verbatim, and the 'Migration from Manual Handoff', 'Future Enhancements', and 'Questions?' sections add padding without operational value. Not a 2 because the bulk is substantive rather than explaining concepts Claude already knows.	3 / 5
Actionability	The task-source side is copy-paste ready (concrete git/gh commands, complete YAML task and result formats), but the executor side — the heart of the skill — is explicitly labeled '# Pseudo-code (Ralph implementation)' rather than executable code, and referenced scripts like scripts/voice-clone.py and scripts/debug-model.py do not exist in any bundle. This matches the 'pseudocode instead of executable code; missing key details' anchor despite the concrete task-creation guidance.	3 / 5
Workflow Clarity	Both roles have clearly numbered step sequences, the 5-step validation pipeline (schema, whitelist, resource limits, isolation, audit) is explicit, and dedicated error-handling sections cover task failures, timeouts, and network outages with retry feedback loops (re-push with status: pending, retry on next cycle). This matches the top anchor: explicit validation steps plus error-recovery loops for a batch/risky operation.	5 / 5
Progressive Disclosure	Section headers are clear and consistent, but the skill is a 434-line monolith with no bundle files at all: task/result format specs, the full worked examples, the security model, and the monitoring commands are all inlined where they belong in separate reference files. The single external pointer ('research/active/cross-machine-agents/README.md') is outside the skill and buried in a closing 'Questions?' section. Some structure exists, so this sits at the 'could be better organized; content that should be separate is inline' anchor rather than the minimal-structure one.	3 / 5
	Total	14 / 20 Passed

Description

53%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 states a clear, distinctive 'what' with a specific mechanism (git-based task queuing), but it completely lacks a 'when to use' clause and natural trigger phrases, and its action vocabulary is thin ('share work'). It is serviceable but below the quality of the reference good examples, which pair capabilities with explicit 'Use when...' guidance.

Suggestions

Add an explicit trigger clause, e.g. 'Use when agents on different machines need to exchange tasks or results, when the user mentions DevBox/Azure VM handoff, or cross-machine work sharing.'

Enumerate the concrete capabilities instead of the single generic 'share work': e.g. 'assign tasks to remote machines, execute queued workloads, and pass results back via git pushes.'

Include natural synonyms users would actually say ('coordinate agents across machines', 'remote task queue', 'hand off work to DevBox') to strengthen trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('squad agents on different machines') and the mechanism ('git-based task queuing') but offers only one generic action ('share work'). It matches the '1-2 concrete actions, not comprehensive' anchor rather than the several-specific-actions anchors, which would require listing capabilities like task assignment, result passing, or issue-based dispatch.	3 / 5
Completeness	The 'what' is clear ('share work via git-based task queuing') but there is no 'when' clause at all — no 'Use when...' or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not a 4 because the 'when' is entirely missing rather than just weakly stated.	3 / 5
Trigger Term Quality	Relevant keywords exist ('squad agents', 'machines', 'git', 'task queuing') but natural user phrasings and common variations ('coordinate work', 'assign tasks to DevBox', 'cross-machine') are absent. Not a 2 because several genuinely relevant domain keywords are present rather than only one or two generic ones.	3 / 5
Distinctiveness Conflict Risk	'Git-based task queuing' scoped to 'squad agents on different machines' carves a clear niche unlikely to trigger for general git or orchestration skills. Not a 5 because 'share work' and 'coordination' are broad enough to overlap slightly with generic agent-orchestration skills.	4 / 5
	Total	13 / 20 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-templates/skills/cross-machine-coordination/SKILL.md
Commit: 29e69f5

Reviewed: 5 days 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.