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.

Quality

26%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./plugins/antigravity-awesome-skills-claude/skills/agent-orchestrator/SKILL.md

Quality

Content

35%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill has a solid structural concept — a meta-orchestrator with auto-discovery, matching, and multi-skill coordination — and provides concrete CLI commands for its core workflow. However, it suffers from significant verbosity with generic boilerplate sections (Best Practices, Common Pitfalls, Limitations) that add no value, lacks validation/error-handling in its workflows, and inlines too much reference material that should be in separate files. The content would benefit greatly from aggressive trimming and adding error recovery steps.

Suggestions

Remove the generic boilerplate sections (Best Practices, Common Pitfalls, Limitations, When to Use/Do Not Use) — they contain no skill-specific information and waste tokens.

Add validation checkpoints to the mandatory workflow: what to do if scan_registry.py fails, if match_skills.py returns errors, or if orchestrate.py produces an invalid plan.

Move the Matching Algorithm details, Orchestration Patterns, and Project Management sections into separate reference files and link to them from the main SKILL.md.

Remove the static 'Skills Atuais Do Ecossistema' table — it contradicts the auto-discovery principle and will become stale; the scan_registry.py --status command already provides this dynamically.

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' and 'Common Pitfalls' section with generic filler content ('Provide clear, specific context about your project'), and the 'When to Use / Do Not Use' sections are tautological. The matching algorithm details, orchestration patterns, and project management sections could be drastically condensed.	1 / 3
Actionability	The skill provides concrete bash commands for scanning, matching, and orchestrating, which is good. However, there's no way to verify these scripts actually exist (no bundle provided), the JSON examples for projects.json are helpful but incomplete, and the orchestration patterns describe concepts rather than providing executable examples. The 'Best Practices' and 'Common Pitfalls' sections are entirely generic and non-actionable.	2 / 3
Workflow Clarity	The mandatory 3-step workflow (scan → match → orchestrate) is clearly sequenced with a decision table for branching, which is good. However, there are no validation checkpoints — what happens if scan_registry.py fails? What if match_skills.py returns malformed JSON? There's no error handling or feedback loop for any of the steps, and the orchestration step lacks verification that the plan executed correctly.	2 / 3
Progressive Disclosure	The content references 'References/Orchestration-Patterns.md' for detailed orchestration patterns, which is appropriate progressive disclosure. However, the main SKILL.md itself is monolithic — the matching algorithm details, project management, and orchestration patterns could all be split into separate reference files. The 'Related Skills' section mentions skills without linking to their locations. No bundle files were provided to verify references exist.	2 / 3
	Total	7 / 12 Passed

Description

17%Scale 1-3

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 internal terminology ('meta-skill', 'orquestra agentes', 'registry management') without providing concrete, user-facing actions or natural trigger terms. It lacks a 'Use when...' clause entirely, making it difficult for Claude to know when to select this skill. The description would benefit significantly from plain-language explanations and explicit trigger conditions.

Suggestions

Add an explicit 'Use when...' clause describing scenarios that trigger this skill, e.g., 'Use when the user needs to coordinate multiple skills, find the right skill for a task, or run multi-step workflows across different capabilities.'

Replace jargon with natural trigger terms users would actually say, such as 'find the right tool', 'combine skills', 'run a multi-step task', or 'which skill should I use'.

List concrete actions in plain language instead of abstract terms, e.g., 'Scans available skills and selects the best match for a given task, chains multiple skills together for complex workflows, and maintains a registry of all available 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. It describes domain and some actions but not comprehensively.	2 / 3
Completeness	Describes what it does at a high level but has no 'Use when...' clause or equivalent explicit trigger guidance. The 'when' is entirely missing, which per the rubric caps completeness at 2, and the 'what' is also vague enough to warrant a 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 skill.	1 / 3
Distinctiveness Conflict Risk	The concept of a 'meta-skill' orchestrator is somewhat distinctive, but terms like 'coordenacao de workflows' and 'registry management' are generic enough to potentially overlap with other orchestration or management skills.	2 / 3
	Total	6 / 12 Passed

Validation

90%

Warnings & errors only

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: popey/claude-code-skills
Path: plugins/antigravity-awesome-skills-claude/skills/agent-orchestrator/SKILL.md
Commit: a5a6601

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.