agent-orchestrator
Meta-skill que orquestra todos os agentes do ecossistema. Scan automatico de skills, match por capacidades, coordenacao de workflows multi-skill e registry management.
32
26%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/antigravity-awesome-skills-claude/skills/agent-orchestrator/SKILL.mdQuality
Discovery
17%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 relies heavily on technical jargon and buzzwords ('meta-skill', 'orquestra', 'ecossistema', 'registry management') without clearly explaining what concrete actions it performs or when it should be triggered. It lacks a 'Use when...' clause entirely, and the language is not aligned with how users would naturally request this functionality. The description reads more like an internal architecture note than a skill selection guide.
Suggestions
Add an explicit 'Use when...' clause describing the situations that should trigger this skill, e.g., 'Use when the user needs to coordinate multiple skills, find available capabilities, or run multi-step workflows across different tools.'
Replace jargon with natural trigger terms users would actually say, such as 'find the right skill', 'combine multiple tools', 'run a multi-step task', or 'list available capabilities'.
Describe concrete actions in plain language instead of abstract terms, e.g., 'Discovers available skills, selects the best skill for a task, chains multiple skills together for complex workflows, and maintains a registry of skill capabilities.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names some actions like 'scan automatico de skills', 'match por capacidades', 'coordenacao de workflows multi-skill', and 'registry management', but these are somewhat abstract and jargon-heavy rather than concrete user-facing actions. | 2 / 3 |
Completeness | Describes a vague 'what' (orchestrates agents, scans skills) but completely lacks any 'when' clause or explicit trigger guidance. The absence of a 'Use when...' clause caps this at 2, and the weak 'what' brings it to 1. | 1 / 3 |
Trigger Term Quality | Uses technical jargon like 'orquestra agentes', 'registry management', 'workflows multi-skill' that users would not naturally say. No natural trigger terms a user would use when needing this capability. | 1 / 3 |
Distinctiveness Conflict Risk | The concept of a meta-skill orchestrator is somewhat distinctive, but terms like 'coordenacao de workflows' and 'management' are generic enough to potentially overlap with other workflow or management skills. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a reasonable framework for agent orchestration with concrete commands and a clear mandatory workflow, but suffers from significant verbosity and generic boilerplate that wastes tokens. The lack of validation/error-handling steps in the workflow and the absence of bundle files to verify referenced scripts and paths weaken its reliability. The content would benefit greatly from aggressive trimming of filler sections and addition of error recovery steps.
Suggestions
Remove the entirely generic 'Best Practices', 'Common Pitfalls', 'Limitations', 'When to Use', and 'Do Not Use' sections — they add no skill-specific value and waste tokens.
Add error handling and validation checkpoints to the mandatory workflow (e.g., what to do if scan_registry.py fails, if match returns unexpected format, or if orchestrate.py produces an invalid plan).
Move the detailed matching algorithm table, registry metadata schema, and project management instructions into separate reference files and link to them from the main SKILL.md.
Provide the referenced bundle files (scripts, Orchestration-Patterns.md) or remove references to files that don't exist to avoid confusion.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose with significant padding. It explains concepts Claude already knows (what a registry is, what matching means), includes a boilerplate 'Best Practices' / 'Common Pitfalls' / 'Limitations' section that is entirely generic filler, and the 'When to Use' / 'Do Not Use' sections are tautological. The matching algorithm table, orchestration patterns, and project management sections could be dramatically condensed. Much content reads like documentation for humans rather than efficient instructions for Claude. | 1 / 3 |
Actionability | The skill provides concrete bash commands for scanning, matching, and orchestrating, which is good. However, the commands reference scripts (scan_registry.py, match_skills.py, orchestrate.py) whose existence and behavior cannot be verified since no bundle files are provided. The project management section gives JSON examples but the operations are described vaguely ('Atualizar o array skills'). The orchestration patterns describe concepts but don't give executable steps for Claude to follow when actually coordinating multi-skill workflows. | 2 / 3 |
Workflow Clarity | The mandatory 3-step workflow (scan → match → orchestrate) is clearly sequenced with a decision table for branching. However, there are no validation checkpoints or error handling steps — what happens if scan_registry.py fails? What if match_skills.py returns malformed JSON? What if orchestrate.py produces an invalid plan? For a meta-orchestration skill that coordinates destructive or complex multi-skill operations, the absence of feedback loops and error recovery caps this at 2. | 2 / 3 |
Progressive Disclosure | There is one reference to 'References/Orchestration-Patterns.md' for detailed orchestration patterns, which is good progressive disclosure. However, no bundle files are provided to verify this reference exists. The main SKILL.md is monolithic at ~200+ lines with inline content (matching algorithm details, project management, full registry schema) that could be split into separate reference files. The generic boilerplate sections at the end add to the bloat. | 2 / 3 |
Total | 7 / 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
- sickn33/antigravity-awesome-skills
- Commit
22710e9
- 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.