CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cross-squad

Coordinating work across multiple Squad instances — discovery, delegation, and disambiguation when the user says 'squad' (the product) vs casual English 'group of agents'.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

The canonical home for this skill is cross-squad in github/gh-aw

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 highly actionable, well-structured body whose commands, tables, and protocol steps are copy-paste ready. Its weaknesses are redundancy in the disambiguation messaging and inlining of manifest/config material that could be split into reference files.

Suggestions

State the disambiguation rule once (in the Disambiguation section) and have the Context callout point to it, cutting the duplicated framing and the cost-of-asking rhetoric.

Move the manifest JSON schema and squad.config.ts example into a references/ file (e.g., MANIFEST.md) linked from the Discovery section to slim the main body.

Add an explicit failure-recovery step to the Work Handoff Protocol (e.g., what to do when 'gh issue create' fails or the target squad's manifest cannot be read).

DimensionReasoningScore

Conciseness

The body is mostly efficient — tables, code blocks, and checklists carry the weight with no generic-concept explanations — but the core disambiguation rule is stated three times (Context callout, Default behaviour table, Anti-patterns) and rhetorical padding like 'The cost of asking is one ask_user. The cost of getting it wrong is the user has to redo the work' could be trimmed. This matches anchor 3: mostly efficient but could be tightened.

3 / 5

Actionability

Guidance is fully executable: copy-ready commands ('squad registry add platform-squad ../friend-platform', 'squad delegate platform-squad "Add Prometheus metrics endpoint..."'), a complete ask_user prompt block, manifest JSON, a squad.config.ts example, and a concrete issue-creation spec with title/label/body contents. This matches anchor 5: copy-paste ready commands covering the common cases.

5 / 5

Workflow Clarity

The Work Handoff Protocol is a clear numbered sequence (check manifest → create issue → track → poll) with an upfront validation checkpoint ('Verify the target squad accepts the work type') and a polling feedback loop. Minor gaps remain — no explicit error-recovery path if delegation or polling fails — matching anchor 4 rather than 5.

4 / 5

Progressive Disclosure

Good structure with well-organized sections, and protocol detail is correctly delegated via a clearly signaled one-level reference to cross-squad-communication/SKILL.md ('This skill answers who — the companion answers how'). The manifest schema and config examples are inlined where they could live in reference files, keeping it at anchor 4 rather than 5.

4 / 5

Total

16

/

20

Passed

Description

78%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.

A specific, well-targeted description with explicit what and when clauses and strong distinctiveness from generic orchestration skills. Its main gap is that it omits the concrete trigger phrases (spawn, fan out, team) that would fully connect user phrasing to the skill.

Suggestions

Add concrete trigger phrases to the when-clause, e.g., 'Use when the user says spawn squads, fan out to squads, delegate to a squad, or asks for another squad.'

Mention registry/upstream management and the issue-based work handoff to close the coverage gaps in the 'what' clause.

DimensionReasoningScore

Specificity

The description names the domain ('Coordinating work across multiple Squad instances') and three concrete actions ('discovery, delegation, and disambiguation'), with minor gaps such as registry management and the work-handoff protocol. It lists several specific actions but is not comprehensive, matching the anchor 4 example rather than 5.

4 / 5

Completeness

Both 'what' (coordinating work across Squad instances — discovery, delegation, disambiguation) and 'when' ('when the user says squad (the product) vs casual English group of agents') are explicitly stated. The when-clause states a condition rather than concrete trigger phrases, matching anchor 4 rather than 5.

4 / 5

Trigger Term Quality

Natural terms like 'squad', 'delegation', and 'group of agents' are present, and the product-vs-casual-English framing doubles as trigger guidance. A few natural phrases users would say ('spawn squads', 'fan out', 'team') are missing, so it fits anchor 4 rather than 5.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche (cross-Squad-instance coordination) with distinct triggers, and the explicit disambiguation from 'group of agents' actively minimizes conflict with generic multi-agent skills. This matches anchor 5: clear niche, minimal conflict risk.

5 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

bradygaster/squad

Path

.squad-templates/skills/cross-squad/SKILL.md

Reviewed

Table of Contents

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.