cross-squad-communication

Protocol for sending queries, delegating tasks, and sharing context between independent Squad instances across different repositories

Quality

72%

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/skills/cross-squad-communication/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 body is highly actionable with executable examples and clearly sequenced workflows backed by a robust liveness/feedback protocol, but it is verbose with repeated guidance and monolithic rather than split across reference files.

Suggestions

Deduplicate the `--agent squad` rationale and the sync-vs-async guidance so each is stated once and referenced elsewhere, tightening conciseness.

Move the Liveness Protocol and the YAML request/response file formats into reference files under references/ and link to them one level deep, improving progressive disclosure for a 390-line skill.

Consolidate the three overlapping sync/async summaries (decision tree, 'When to use' table, and coordinator bulleted list) into a single canonical decision point.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but it repeats itself — the `--agent squad` rule and the sync-vs-async guidance each appear in the decision tree, table, coordinator list, and anti-patterns — so it could be tightened; not a 1 because the detail is genuinely operational rather than padded fluff.	2 / 3
Actionability	It provides fully executable PowerShell invocations, concrete YAML request/response file formats, and a copy-paste `gh issue create` command, matching the anchor for specific, copy-paste-ready examples.	3 / 3
Workflow Clarity	Each pattern is a clearly numbered sequence (e.g. Pattern 0 steps 1–3, Pattern 2 steps 1–5), and the Liveness Protocol adds explicit validation checkpoints with stall detection thresholds and recovery actions, satisfying the clear-sequence-with-feedback-loops anchor.	3 / 3
Progressive Disclosure	The skill is well-sectioned but runs ~390 lines as a single monolithic file with no bundle files in references/scripts/assets, and content that could be split (the Liveness Protocol, YAML file formats, the dependency-scan appendix) is inline; not a 3 because the simple-skill allowance does not apply at this length.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 specific and occupies a clear, distinctive niche, but it omits any explicit 'Use when...' trigger guidance, leaving the 'when to use' question only implied and capping completeness and trigger-term quality at 2.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when a squad agent needs information from, or must delegate work to, another squad-enabled repository.'

Soften the technical jargon ('independent Squad instances') toward terms users would actually say, such as 'another squad' or 'a different repo's squad', to improve trigger-term quality.

Mirror the body's concrete request types (knowledge query, PR review, task delegation, dependency analysis) in the description so the 'what' matches the skill's actual scope.

Dimension	Reasoning	Score
Specificity	The description names multiple concrete actions — 'sending queries, delegating tasks, and sharing context' — matching the anchor for listing several specific concrete actions rather than vague language.	3 / 3
Completeness	It clearly answers 'what' (a protocol for sending queries, delegating tasks, sharing context) but provides no 'when' guidance — there is no 'Use when...' clause or equivalent explicit trigger, which caps completeness at 2 per the rubric guidelines.	2 / 3
Trigger Term Quality	It contains relevant terms (queries, delegating tasks, sharing context, repositories) but leans on technical jargon like 'independent Squad instances' and omits common natural variations a user would actually say; not a 3 because no 'Use when...' phrasing is present.	2 / 3
Distinctiveness Conflict Risk	The niche is clearly scoped to communication between independent Squad instances across different repositories, making it unlikely to trigger for unrelated skills; this matches the clear-niche anchor.	3 / 3
	Total	10 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: bradygaster/squad
Path: .squad/skills/cross-squad-communication/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.