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", "orquestrar", "coordenar", "planejar execucao", "proximo passo", "workflow".
80
Quality
76%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/09-orchestrator/SKILL.mdQuality
Discovery
82%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 effectively communicates its orchestration role and provides explicit trigger guidance with a good list of natural keywords. However, the actual capabilities described are somewhat abstract (coordination, adaptation, oversight) rather than concrete actions, and some trigger terms are generic enough to potentially cause conflicts with other skills.
Suggestions
Add more concrete, specific actions the orchestrator performs (e.g., 'creates execution plans', 'validates prerequisites', 'generates progress reports') rather than abstract coordination language.
Consider narrowing generic triggers like 'nova task' and 'iniciar' to more distinctive phrases that clearly indicate orchestration needs, such as 'orquestrar nova task' or 'iniciar pipeline'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Tech Lead/Orchestrator) and describes some actions like 'coordena qual skill executar', 'adapta o fluxo ao contexto', 'garante que nenhuma etapa critica seja pulada', but these are somewhat abstract coordination activities rather than concrete, measurable actions. | 2 / 3 |
Completeness | Clearly answers both what (coordinates skill execution, adapts flow to context, ensures no critical steps are skipped, maintains progress overview) AND when (at the start of every task and between relevant pipeline stages), with explicit trigger terms listed. | 3 / 3 |
Trigger Term Quality | Provides good coverage of natural trigger terms users would say: 'nova task', 'iniciar', 'pipeline', 'orquestrar', 'coordenar', 'planejar execucao', 'proximo passo', 'workflow'. These are practical terms a user would naturally use when starting or coordinating work. | 3 / 3 |
Distinctiveness Conflict Risk | While it establishes itself as an orchestrator/coordinator role, terms like 'nova task', 'iniciar', and 'proximo passo' are quite generic and could potentially conflict with other skills that handle task initiation or step progression. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This orchestrator skill demonstrates strong workflow clarity and progressive disclosure, with well-defined pipeline sequences and clear references to supporting documentation. The main weaknesses are moderate verbosity in governance sections and lack of concrete executable examples - the guidance is procedural but not copy-paste actionable. Overall, it serves its coordination purpose well but could be tightened.
Suggestions
Add a concrete, complete example of a task classification and pipeline selection (e.g., 'User request: Add dark mode toggle' -> classification -> selected pipeline -> handoff output)
Consolidate the governance section - consider replacing the policy file list with a single reference to a policies index or GLOBAL.md
Provide a filled-out example of the Image Generator invocation template rather than just the placeholder format
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundancy - the governance section listing multiple policy files could be more compact, and some sections repeat concepts (like handoff references appearing multiple times). However, it avoids explaining basic concepts Claude would know. | 2 / 3 |
Actionability | Provides concrete pipeline sequences and decision rules, but lacks executable code examples. The 'Como acionar' section shows a template format but it's not a complete, copy-paste ready example. Most guidance is procedural rather than executable. | 2 / 3 |
Workflow Clarity | Excellent workflow structure with clear pipeline sequences, explicit adaptation rules for different task types (bugfix, hotfix, landing page, etc.), rejection handling workflow, and validation checkpoints (QA, Security, Reviewer gates). The protocol sections clearly sequence multi-step processes. | 3 / 3 |
Progressive Disclosure | Well-structured with clear references to external files (GLOBAL.md, policies/, templates/, docs/skill-guides/orchestrator-playbook.md). References are one level deep and clearly signaled. Content is appropriately split between overview here and detailed playbook elsewhere. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- felvieira/claude-skills-fv
- Commit
524725e
- Reviewed
Table of Contents
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.