orchestrator

Skill do Tech Lead/Orquestrador do pipeline de desenvolvimento. Deve ser usada no inicio de toda task e entre etapas relevantes do pipeline. Coordena qual skill executar, em que ordem, adapta o fluxo ao contexto, garante que nenhuma etapa critica seja pulada e mantem visao geral do progresso. Trigger em: "nova task", "iniciar", "pipeline de desenvolvimento", "orquestrar", "coordenar", "planejar execucao", "proximo step do pipeline", "workflow".

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

77%Weight 40%Scale 1-3

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

The body is genuinely actionable with executable commands, real code, and well-sequenced workflows backed by explicit validation gates. Its main weaknesses are conciseness — heavy verbatim duplication and recurring restatements — and progressive disclosure, since it is a long monolithic file with no bundled detail files to offload the deeper material.

Suggestions

Remove the duplicated "Constituicao (se existir)" section and the repeated policies/constitution.md bullet, and consolidate the coordination duties that recur across Entradas/Saidas/Responsabilidades/Evidencia into a single canonical list.

Split the inline pipeline-base roster, image-generator invocation protocol, and programs catalog into referenced files (e.g. references/pipeline-base.md, references/programs.md) so SKILL.md stays a lean overview with one-level-deep pointers.

Move or qualify the time-sensitive version markers ("Auto-orchestration (v1.8.0)", "v2.2.0") into a dated changelog/deprecated section so they do not penalize conciseness or become stale.

Dimension	Reasoning	Score
Conciseness	The 440-line body is padded with verbatim duplication — the "Constituicao (se existir)" block repeats (lines 34-39 and 41-46), the policies/constitution.md bullet appears twice, and the same coordination duties recur across Entradas, Saidas, Responsabilidades and Evidencia. It is not a 1 because the content is accurate and mostly on-task, but not a 3 because the repetition and generic restatements waste tokens.	2 / 3
Actionability	Highly concrete and executable: real commands ("node scripts/route-task.mjs --json", "node scripts/auto-loop.mjs --worktree --parallel 5"), copy-paste TypeScript Agent dispatch with model routing, a mode A/B decision table, and an ambiguity-score formula. It is not a 2 because guidance is specific and copy-paste ready rather than pseudocode.	3 / 3
Workflow Clarity	Multi-step processes are explicitly sequenced with validation gates — Modo A/B pipelines, vertical slicing with "Apos aprovacao do plano, despachar", the pre-execution gate thresholds (score < 0.4 / 0.4-0.7 / > 0.7), and the rejection feedback loop. It is not a 2 because checkpoints and error-recovery branches are explicit, not implicit.	3 / 3
Progressive Disclosure	No bundle files ship (references/scripts/assets absent) and the SKILL.md is a long inline monolith; content that could live separately (full pipeline-base roster, image-generator sub-protocol, programs catalog) is in-body. External one-level paths (policies/programs/scripts/templates) are well-signaled, lifting it above a 1, but it is not a lean overview pointing to detail files, so not a 3.	2 / 3
	Total	10 / 12 Passed

Description

92%Weight 40%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.

The description is strong: third-person, concrete about its coordinating actions, and explicitly answers both what and when with a dedicated trigger clause. Its only soft spot is distinctiveness, since several trigger terms are broad enough to compete with adjacent planning/router skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete coordinating actions — "Coordena qual skill executar, em que ordem, adapta o fluxo ao contexto, garante que nenhuma etapa critica seja pulada e mantem visao geral do progresso" — rather than vague language. It is not a 2 because the actions are specific and several, matching the multiple-concrete-actions anchor.	3 / 3
Completeness	It states what ("Skill do Tech Lead/Orquestrador do pipeline de desenvolvimento") and when ("Deve ser usada no inicio de toda task e entre etapas relevantes do pipeline" plus the explicit Trigger clause), answering both what and when. It is not a 2 because the when is explicit, not merely implied.	3 / 3
Trigger Term Quality	An explicit "Trigger em:" clause gives natural terms a user would say — "nova task", "iniciar", "orquestrar", "coordenar", "planejar execucao", "workflow" — giving good coverage. It is not a 2 because the terms span common variations rather than a single narrow keyword.	3 / 3
Distinctiveness Conflict Risk	The orchestrator/tech-lead niche is fairly distinct, yet broad triggers like "coordenar" and "planejar execucao" could overlap with sibling planning skills (e.g. program-router). It is not a 3 because the trigger surface is not narrowly conflict-free; not a 1 because the role is more specific than generic file/data helpers.	2 / 3
	Total	11 / 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
referenced_paths_exist	Referenced path issues: 4 missing	Warning

	Total	15 / 16 Passed

Repository: felvieira/claude-skills-fv
Path: skills/09-orchestrator/SKILL.md
Commit: 030ef22

Reviewed: 6 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.