cross-squad-communication

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

Quality

61%

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

63%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 thorough, actionable protocol guide with clear sequencing and feedback loops, but it is verbose and monolithic — everything lives in one long SKILL.md with no progressive disclosure into separate reference files. Trimming redundancy and splitting per-pattern details into referenced files would raise the weakest dimensions.

Suggestions

Split each numbered pattern into its own referenced file (e.g. PATTERN_0_SYNC_CLI.md, PATTERN_2_GIT_ASYNC.md) and keep SKILL.md as a concise overview with one-level-deep links, satisfying progressive disclosure.

Consolidate the repeated `--agent squad` rationale into the single "Universal rule" section and remove redundant restatements from each pattern to reduce token cost.

Trim the three full Pattern 0 invocation variants (Options A/B/C) to one canonical example plus a brief note on the alternatives, eliminating padding without losing actionability.

Dimension	Reasoning	Score
Conciseness	The ~390-line body is largely substantive domain-specific protocol detail Claude would not already know, but it pads sections with repeated `--agent squad` emphasis, a duplicate "coordinator decides" list, and three full Pattern 0 invocation variants that could be tightened.	3 / 5
Actionability	It provides concrete, copy-paste-ready PowerShell, `gh issue create`, and YAML examples across all four patterns with specific flags and file paths, with only minor illustrative-path gaps keeping it below fully executable everywhere.	4 / 5
Workflow Clarity	A decision tree plus per-pattern numbered protocols and a Discovery Protocol sequence steps through the work clearly, and Pattern 0 includes explicit liveness/stall feedback loops; only minor validation gaps remain for the async patterns.	4 / 5
Progressive Disclosure	The skill is a single 390-line monolith with no bundle files and no external references, so content that clearly belongs in separate files (per-pattern details, the dependency-scan appendix) is inlined rather than split one level deep.	3 / 5
	Total	14 / 20 Passed

Description

58%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 specific and distinct, clearly stating what the skill does across multiple concrete actions, but it lacks an explicit "Use when..." trigger clause and natural user-facing keywords, which caps both completeness and trigger-term quality. Adding a concrete trigger clause would lift the weakest dimensions.

Suggestions

Append an explicit trigger clause, e.g. "Use when coordinating queries, task delegation, or context sharing across squad-enabled repos, or when the user mentions cross-repo/cross-squad work."

Add natural-language synonyms and file/extension cues users would actually say (e.g. "cross-repo", "peer squad", "multi-repo coordination") to broaden trigger coverage.

Reconsider first-line wording to lead with the action rather than the abstract noun "Protocol for" to make the capability scan faster.

Dimension	Reasoning	Score
Specificity	The description names the domain and lists three concrete actions ("sending queries, delegating tasks, and sharing context") with only minor gaps in coverage, fitting between the 1-2-action anchor and full comprehensive coverage.	4 / 5
Completeness	It clearly answers the "what" but provides no explicit "when/Use when..." trigger guidance, so per the judging guidelines a missing trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Terms like "queries", "delegating tasks", and "Squad instances" are relevant but skew technical and miss the natural phrasings a user would say (no synonyms or common variations), matching the anchor for some relevant keywords with missing variations.	3 / 5
Distinctiveness Conflict Risk	"between independent Squad instances across different repositories" carves a distinct niche with minimal conflict risk, with only minor overlap against the companion cross-squad discovery skill.	4 / 5
	Total	14 / 20 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: a0d2563

Reviewed: about 15 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.