CtrlK
BlogDocsLog inGet started
Tessl Logo

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'.

67

Quality

81%

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

SKILL.md
Quality
Evals
Security

Quality

Content

78%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 highly actionable with executable commands, complete JSON examples, and a clearly sequenced handoff workflow with validation and feedback loops. Its weakness is repetition: the squad-vs-task-agent disambiguation is restated across multiple sections and could be consolidated to improve token efficiency.

Suggestions

Consolidate the repeated 'squad vs ad-hoc task agents' disambiguation into one authoritative section; the Context block, Disambiguation intro, and Anti-patterns restate the same point and can be tightened.

Move the full manifest schema and squad.config.ts example into a separate reference file (e.g., references/manifest.md) to keep SKILL.md an overview and lift progressive disclosure to a clear 5.

Trim the duplicated Anti-Patterns section at the end, which overlaps heavily with the in-section Anti-patterns under Disambiguation.

DimensionReasoningScore

Conciseness

The body is mostly efficient and action-oriented, but several passages restate the same disambiguation point multiple times (the Context block, the Disambiguation section, and the Anti-patterns all repeat 'don't treat task agents as squads'), which is padding that could be tightened. It does not over-explain concepts Claude already knows, keeping it above 2.

3 / 5

Actionability

Provides copy-paste-ready commands and concrete examples throughout — `squad registry add`, `squad discover`, `squad delegate`, `gh issue create` with exact title/label/body fields, plus complete manifest JSON and config snippets — covering the common cases with executable guidance.

5 / 5

Workflow Clarity

The Work Handoff Protocol is a clearly sequenced 4-step process (Check manifest → Create issue → Track → Poll) with an explicit validation checkpoint ('Verify the target squad accepts the work type') and a feedback loop (Poll via `gh issue view`, update originating issue, close when merged), matching the top anchor.

5 / 5

Progressive Disclosure

Content is well-organized into Context, Disambiguation, Patterns, Examples, and Anti-Patterns, with a clearly signaled one-level reference to the companion `cross-squad-communication` skill. It stays below 5 because no bundle files exist and some reference-style detail (e.g., full manifest schema) is inlined rather than split into a separate file, leaving minor organization gaps.

4 / 5

Total

17

/

20

Passed

Description

85%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 strong: it states concrete capabilities, supplies explicit 'when' triggers, and proactively disambiguates the product sense of 'squad' from casual usage. Its main limitation is relying on a single somewhat-specialized keyword rather than a fuller spread of natural synonyms.

DimensionReasoningScore

Specificity

Names three concrete actions — 'discovery, delegation, and disambiguation' — tied to a specific domain (multiple Squad instances), which lists several specific actions with only minor coverage gaps (e.g., manifest publishing/tracking not surfaced). It sits below 5 because it stops at three actions and does not enumerate the fuller capability set.

4 / 5

Completeness

Explicitly answers both 'what' (coordinating work across multiple Squad instances — discovery, delegation, disambiguation) and 'when' (when the user says 'squad' the product vs casual English), with concrete trigger phrases populated in the triggers list.

5 / 5

Trigger Term Quality

Captures natural user phrases like 'spawn N squads', 'ask the other squad', and 'delegate to a squad' in the triggers list, with good keyword coverage of the squad vocabulary; below 5 because it leans on the somewhat specialized term 'squad' rather than spanning common synonyms and variations a broader audience would say.

4 / 5

Distinctiveness Conflict Risk

The disambiguation framing ('squad' the product vs casual 'group of agents') carves a clear niche that reduces overlap with generic team/sub-agent skills; below 5 because the term 'squad' is shared with everyday usage, leaving residual overlap risk that the skill itself has to disambiguate.

4 / 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.

Validation15 / 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
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.