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

53%

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

57%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.

The body is highly actionable with concrete commands and decision tables, and has a clear mandatory workflow, but it is held back by duplicated/inlined reference content, a malformed reference link, and the absence of validation checkpoints in a batch/multi-skill workflow (capping workflow clarity at 3).

Suggestions

Add explicit validation/checkpoint steps to the mandatory workflow (e.g., verify scan output JSON is well-formed, confirm each matched skill's status is 'active' before orchestration, and define the retry/failure path) so workflow clarity is not capped at 3.

Move the inlined orchestration-pattern sections out of SKILL.md into references/orchestration-patterns.md and link to them with proper markdown links; also link to capability-taxonomy.md from the relevant section instead of leaving it unreferenced.

Tighten redundancy: collapse the repeated scan_registry.py command examples and remove the duplicated description in Overview/How It Works to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly information-dense and actionable, but it restates the description in the Overview/How It Works, repeats the scan_registry.py command several times, and inlines orchestration patterns that also live in references, fitting 'mostly efficient but could be tightened'.	3 / 5
Actionability	Provides concrete, copy-paste-ready commands for each step plus a decision table for matched 0/1/2+ and a scoring-criteria table, meeting 'mostly executable guidance with minor gaps' (the only gap being the assumed agent-orchestrator/ path prefix).	4 / 5
Workflow Clarity	The mandatory Passo 1-3 sequence and matched-count decision table give a clear order, but the main workflow lacks explicit validation/checkpoint steps for what are batch/multi-skill operations, which per the rubric caps workflow clarity at 3.	3 / 5
Progressive Disclosure	Reference files exist (orchestration-patterns.md, capability-taxonomy.md) and scripts are bundled, but the reference signal is malformed plain text ('Detalhes Em References/Orchestration-Patterns.Md'), capability-taxonomy.md is never linked from the body, and orchestration patterns are duplicated inline rather than split out, matching 'some structure but references not clearly signaled and content that should be separate is inline'.	3 / 5
	Total	13 / 20 Passed

Description

50%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.

The description clearly conveys what the skill does with several named actions but omits any explicit 'when to use' trigger guidance, which caps completeness. Trigger terms are present but technical and lacking natural synonyms, and the broad meta-scope carries moderate overlap risk.

Suggestions

Add an explicit 'Use when...' clause with concrete trigger phrases (e.g., 'Use when coordinating multiple skills, discovering available skills, or routing a request to the right agent').

Replace generic verbs with more concrete operations and add natural user-facing terms/synonyms so the description matches how users actually phrase requests.

Narrow the scope language from 'todos os agentes do ecossistema' to a clearer niche to reduce overlap/conflict risk with other orchestration skills.

Dimension	Reasoning	Score
Specificity	Names the orchestration domain and several actions ('Scan automatico de skills', 'match por capacidades', 'coordenacao de workflows multi-skill', 'registry management'), but the actions are high-level/conceptual rather than concrete operations, so it sits at the 'domain + 1-2 actions' anchor rather than the comprehensive-action level above.	3 / 5
Completeness	Clearly states 'what' the skill does but provides no 'Use when...' / 'when' clause, which per the rubric caps completeness at 3 ('clear what but when missing or weakly implied').	3 / 5
Trigger Term Quality	Contains some relevant keywords ('orquestra agentes', 'scan skills', 'match por capacidades', 'workflows multi-skill') but leans technical and lacks common synonyms or natural user phrasings, matching the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The meta-orchestrator niche is somewhat distinguishable, but 'orquestra todos os agentes do ecossistema' is broad and could overlap with many multi-skill/orchestration requests, fitting the 'somewhat specific but could still overlap' anchor.	3 / 5
	Total	12 / 20 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/agentic-awesome-skills
Path: skills/agent-orchestrator/SKILL.md
Commit: b1aebac

Reviewed: ~18 hours 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.