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

62%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/agent-orchestrator/SKILL.md

Quality

Content

65%

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 scripts, decision tables, and concrete scoring rules, but is padded with generic boilerplate sections and duplicates orchestration-pattern content that already lives in a reference file. Workflow sequencing is clear yet lacks explicit validation checkpoints.

Suggestions

Remove the generic 'When to Use'/'Best Practices'/'Common Pitfalls' boilerplate (e.g. 'When you need specialized assistance with this domain') that adds no domain-specific value.

Add explicit validation/error-recovery checkpoints to the workflow (e.g. verify scan output JSON, handle 'incomplete' skill status, retry on orchestration failure) to earn full workflow clarity.

Stop duplicating the three orchestration patterns inline and instead summarize briefly with a correctly-cased link to references/orchestration-patterns.md.

Dimension	Reasoning	Score
Conciseness	Largely efficient with command blocks and tables, but padded with boilerplate ('When you need specialized assistance with this domain', generic Best Practices/Common Pitfalls/Limitations, and repeated 'How It Works' prose). Not level 3 (extra tokens that add no unique value), above level 1 (core content is not a wall of basic concept explanation).	2 / 3
Actionability	Provides fully executable commands with exact arguments ('python agent-orchestrator/scripts/match_skills.py "<solicitacao>"'), scoring-criteria tables, and copy-paste JSON examples — concrete and instruction-ready.	3 / 3
Workflow Clarity	A clear 3-step sequenced workflow with a decision table on 'matched:' counts, but no explicit validation/error-recovery checkpoints for batch or orchestration operations; sequence present, checkpoints only implicit. Not level 3 (no validate->fix->retry feedback loop), above level 1 (steps are clearly ordered).	2 / 3
Progressive Disclosure	References real bundle files (scripts/ and references/orchestration-patterns.md) one level deep, but the reference is mis-signaled ('References/Orchestration-Patterns.Md' casing/path mismatch) and the orchestration patterns are largely duplicated inline rather than split out. Not level 3 (signaling inconsistent and content duplicated), above level 1 (real structure and references exist).	2 / 3
	Total	9 / 12 Passed

Description

60%

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 names several concrete capabilities but lacks any explicit 'Use when...' trigger guidance, relying on technical jargon rather than natural user phrasing. It states 'what' well but leaves 'when' only implied, capping completeness and trigger quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when coordinating multiple skills, discovering available skills, or routing a request across the skill ecosystem.'

Replace jargon ('orquestra', 'registry management') with natural user-facing terms users would actually say ('coordinate skills', 'find the right skill', 'run several skills together').

Narrow 'todos os agentes do ecossistema' to a more specific scope to reduce overlap with general multi-agent skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Scan automatico de skills', 'match por capacidades', 'coordenacao de workflows multi-skill', 'registry management' — rather than vague language.	3 / 3
Completeness	Clearly states what the skill does but has no 'Use when...' or equivalent explicit trigger guidance, so per the rubric 'when' is only implied and completeness is capped at 2.	2 / 3
Trigger Term Quality	Terms like 'orquestra', 'scan de skills', 'registry management' are technical jargon a user would rarely say naturally; missing common conversational variations. Not level 3 (no natural trigger phrasing), above level 1 (some relevant domain keywords present).	2 / 3
Distinctiveness Conflict Risk	The 'meta-skill que orquestra todos os agentes do ecossistema' framing is a distinct niche, but 'todos os agentes' is broad and could overlap with other orchestration/multi-agent skills; not clearly level-3 niche, above level-1 generic.	2 / 3
	Total	9 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: sickn33/antigravity-awesome-skills
Path: skills/agent-orchestrator/SKILL.md
Commit: 07da495

Reviewed: 2 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.