CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-squad-swift

Use when building or modifying a Swift app that uses the AgentSquad Swift framework — on-device multi-agent orchestration for iOS 16+ / macOS 14+: orchestrator, agents (Agent, GroundedAgent), classifier routing, LLM clients (OpenAI-compatible), tools (native + MCP), tool UIs/widgets, on-device storage, tracing, and realtime voice — built-in types and custom implementations.

68

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

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 well-organized, framework-specific guide that assumes competence, stays disciplined about not duplicating API reference material, and points outward to source and docs for depth. Its main limitation is that the dense voice/audio gotcha section and reliance on a single code example keep it just short of exemplary on conciseness and actionability.

Suggestions

Tighten the voice/audio gotcha block (AEC, barge-in, session policy) into a short table or a one-level-deep reference file to cut tokens from the longest section.

Add one or two more runnable Swift snippets — e.g. constructing an Orchestrator+Agent and a GroundedAgent — so the most common wiring is copy-paste ready rather than described.

Consider extracting the per-seam custom-implementation table and the modules table into a bundled reference file, leaving SKILL.md as a tighter overview with clearly signaled links.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's Swift competence (no basic-concept padding), explicitly framing itself as 'a map — not an API reference' and deferring signatures to source; the voice/audio gotcha block is the one area that runs long, keeping it just below fully lean.

4 / 5

Actionability

It gives concrete, executable guidance — a SwiftPM package URL, exact import modules, one runnable `route(...)` stream snippet, specific type names, and exact source/doc paths — with only minor gaps (a single code example, rest is descriptive pointers).

4 / 5

Workflow Clarity

The 'When to use what' decision branch and 'How a turn works' sequence ('classify? → run agent → stream → persist') give a clear, ordered flow; there are no destructive or batch operations that would require validation checkpoints, so no cap applies.

4 / 5

Progressive Disclosure

Well-structured into labeled sections with a 'Go deeper' block and a custom-implementation table that clearly signal external source/doc paths one level deep; no bundle files exist, and the inlined overview content is appropriately map-level, with only minor organization gaps.

4 / 5

Total

16

/

20

Passed

Description

87%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 strong, well-scoped description that clearly states both what the skill covers and when to invoke it, with comprehensive enumeration of the framework's component surface and a distinct, low-conflict trigger. The only soft spot is slightly generic verbs ('building or modifying').

DimensionReasoningScore

Specificity

The description enumerates many concrete capability areas ('orchestrator, agents (Agent, GroundedAgent), classifier routing, LLM clients (OpenAI-compatible), tools (native + MCP), tool UIs/widget, on-device storage, tracing, and realtime voice') but the verbs ('building or modifying') are somewhat generic, leaving minor coverage gaps versus a fully comprehensive action list.

4 / 5

Completeness

It explicitly answers both 'what' (on-device multi-agent orchestration with the listed components) and 'when' ('Use when building or modifying a Swift app that uses the AgentSquad Swift framework') with concrete trigger phrases.

5 / 5

Trigger Term Quality

It includes natural terms a user would say ('building or modifying a Swift app', 'AgentSquad Swift framework', 'multi-agent orchestration', 'iOS 16+', 'realtime voice') with good coverage, though a few common synonyms or phrasings are absent.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche (AgentSquad Swift framework, iOS 16+/macOS 14+, on-device multi-agent orchestration) with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
2FastLabs/agent-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.