agent-orchestration
Multi-agent orchestration and state management.
31
14%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agent/skills/agent-orchestration/SKILL.mdQuality
Discovery
7%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is extremely weak, using abstract technical jargon without concrete actions or usage triggers. It fails to help Claude understand when to select this skill and what specific capabilities it provides. The description would be nearly useless for skill selection among multiple options.
Suggestions
Add specific concrete actions the skill performs (e.g., 'Coordinates multiple AI agents, manages task queues, tracks agent states, handles inter-agent communication').
Include a 'Use when...' clause with natural trigger terms users might say (e.g., 'Use when coordinating multiple agents, managing workflows, or when the user mentions agent coordination, task distribution, or parallel processing').
Replace abstract jargon with user-facing language that describes observable outcomes or use cases.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, abstract language ('orchestration', 'state management') without listing any concrete actions. It does not specify what actions the skill performs. | 1 / 3 |
Completeness | Only vaguely addresses 'what' with abstract terms, and completely missing any 'when' guidance or explicit trigger conditions. | 1 / 3 |
Trigger Term Quality | Contains technical jargon ('multi-agent orchestration', 'state management') that users are unlikely to naturally say. Missing common variations or natural language triggers. | 1 / 3 |
Distinctiveness Conflict Risk | The terms 'multi-agent' and 'orchestration' provide some specificity to a domain, but 'state management' is generic enough to potentially overlap with many other skills. | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads like a conceptual overview or documentation summary rather than actionable guidance. It describes multi-agent patterns at a high level but provides zero executable code, concrete examples, or step-by-step workflows. Claude cannot act on vague instructions like 'Assign roles dynamically' without specific implementation details.
Suggestions
Add executable code examples showing how to implement stateful graph logic (e.g., a concrete state machine or workflow implementation)
Provide specific, copy-paste ready patterns for the Reflexion loop with actual validation logic and retry mechanisms
Include concrete examples of multi-agent delegation with actual prompts or function signatures for each role (Planner, Coder, Reviewer, Executioner)
Remove conceptual explanations Claude already knows (what graphs are, what plugins do) and replace with specific implementation patterns
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is relatively brief but includes conceptual explanations (what graphs are, what roles mean) that Claude already understands. The emoji headers and attribution footer add unnecessary tokens. | 2 / 3 |
Actionability | The skill is entirely abstract and descriptive with no concrete code, commands, or executable examples. Phrases like 'View complex tasks as a Graph' and 'Assign roles dynamically' describe concepts without showing how to implement them. | 1 / 3 |
Workflow Clarity | Despite being about orchestration and workflows, there are no actual step sequences, validation checkpoints, or concrete processes. The 'Reflexion Pattern' mentions evaluation but provides no actionable implementation. | 1 / 3 |
Progressive Disclosure | The content is organized into logical sections with clear headers, but there are no references to detailed documentation, examples, or supporting files. Everything is inline but shallow. | 2 / 3 |
Total | 6 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- Dokhacgiakhoa/antigravity-ide
- Commit
332e58b
- 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.