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

59%

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

63%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 a well-structured, largely executable operations manual for the orchestrator's scan/match/orchestrate workflow, with concrete commands and useful decision tables. Its main weaknesses are generic boilerplate sections, duplicated/broken command blocks, weak signaling of the two reference files, and absent failure-handling checkpoints. Tightening the tail and fixing reference navigation would move it from good to excellent.

Suggestions

Replace the broken 'Comandos Do Registry' bash block (which embeds markdown headers inside the code fence and repeats scan_registry.py/--status commands already shown) with a single clean command table, and remove the duplicated Passo Rapido section.

Delete or rewrite the generic 'Best Practices', 'Common Pitfalls', and 'Related Skills' sections with orchestrator-specific content — e.g., what to do when matched: 0 but the user expected a skill, or how to pass context between pipeline stages — instead of template filler.

Add a clearly labeled 'References' section linking both bundle files with correct paths (references/orchestration-patterns.md and the currently orphaned references/capability-taxonomy.md), and add failure-handling checkpoints to the workflow (e.g., re-run scan with --force if the registry is stale, verify skill status is 'active' before orchestrating).

Dimension	Reasoning	Score
Conciseness	The core sections (workflow, matching algorithm, orchestration patterns) are dense and table-driven, but the tail sections ('Best Practices', 'Common Pitfalls', 'Related Skills', 'Limitations') are generic template filler ('Provide clear, specific context about your project and requirements'), and the registry commands are duplicated (scan_registry.py and --status each appear twice). This fits 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than 2, since the bulk is not padded prose.	3 / 5
Actionability	The body provides copy-paste-ready commands with arguments (scan_registry.py, match_skills.py "<solicitacao>", orchestrate.py --skills ... --query ...), result-interpretation tables, and a concrete JSON example for projects. It stops short of 5 because the 'Comandos Do Registry' bash block embeds markdown headers inside the code fence, duplicates earlier commands, and there is no worked end-to-end example of a full orchestrated run.	4 / 5
Workflow Clarity	'Workflow Obrigatorio' gives a clear Passo 1-3 sequence with a decision table ('matched: 0/1/2+' -> acao) acting as a checkpoint, plus a documented shortcut. It is not 5 because validation is implicit — there is no guidance for handling scan or match failures, stale registry entries, or verifying orchestration plans before execution — but the sequence and decision logic are unambiguous, placing it above 3.	4 / 5
Progressive Disclosure	The body cites 'Detalhes Em References/Orchestration-Patterns.Md' — the file references/orchestration-patterns.md exists but the reference uses mismatched casing and is a single buried line rather than a clearly signaled navigation section. Meanwhile references/capability-taxonomy.md exists in the bundle but is never referenced from SKILL.md at all. This matches 'references present but not clearly signaled'; the good section structure and appropriately inlined scripts keep it above 2.	3 / 5
	Total	14 / 20 Passed

Description

55%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 gives a decent inventory of what the skill does but reads like a feature list with jargon-heavy terms and completely lacks a 'when to use' clause. It would rarely be triggered correctly by natural user phrasing. Adding explicit trigger guidance and natural-language synonyms would substantially improve it.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when the user asks to combine, find, or coordinate multiple skills, or when unsure which skill applies'), since the missing trigger clause caps completeness at 3.

Include natural trigger phrases and synonyms users would actually say — 'find the right skill', 'use multiple skills together', 'which skill should I use' — alongside the current technical terms like 'registry management'.

State the concrete mechanism (e.g., 'Scans SKILL.md files, ranks them by relevance to the request, and executes a coordinated plan') in verb form to sharpen specificity and reduce overlap with generic orchestration skills.

Dimension	Reasoning	Score
Specificity	The description lists four named actions ('Scan automatico de skills, match por capacidades, coordenacao de workflows multi-skill e registry management'), matching the 'several specific actions with minor gaps' anchor. It falls short of 5 because the actions are nominalized phrases ('registry management') rather than the fully concrete, comprehensive action list of the top anchor, and above 3 because it goes beyond 1-2 actions.	4 / 5
Completeness	The 'what' is clearly stated (scan, match, orchestrate, registry management) but there is no 'Use when...' clause or equivalent trigger guidance anywhere in the description, which caps completeness at 3 per the judging guidelines. It is not 2 because the 'what' is concrete, not vague.	3 / 5
Trigger Term Quality	Terms like 'orquestra', 'skills', 'workflows' are relevant but the description leans on technical jargon ('registry management', 'match por capacidades') and misses the natural phrases a user would say, such as 'use multiple skills together' or 'find the right skill'. This matches the 'some relevant keywords but missing common variations or synonyms' anchor rather than 4's good coverage.	3 / 5
Distinctiveness Conflict Risk	The meta-skill/orchestration niche is somewhat specific, but 'orquestra todos os agentes do ecossistema' is broad and would overlap with any other agent-coordination or workflow skill. This fits the 'somewhat specific but could still overlap with similar skills' anchor; it is not 4 because the trigger terms do not carve out a clearly distinct niche.	3 / 5
	Total	13 / 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: 7b534bc

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.