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

54%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/09-orchestrator/SKILL.md

Quality

Content

27%

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

This orchestrator skill attempts to be comprehensive but suffers from severe verbosity, content duplication (the Constituicao section appears twice), and poor progressive disclosure — it inlines detailed implementation guidance (parallelization patterns, model routing, image generation) that should live in referenced files. While the pipeline modes and task-type adaptation tables provide useful structure, the sheer volume of content undermines its effectiveness as a quick-reference orchestration guide.

Suggestions

Remove the duplicated 'Constituicao (se existir)' section and trim the file to under 150 lines by moving parallelization details, model routing tables, and image generator protocol to their respective referenced files (policies/vertical-slices.md, policies/model-routing-real.md, skills/17-image-generator/SKILL.md).

Add explicit validation checkpoints to the workflow: after pipeline classification, after each skill handoff, and before final delivery — with concrete pass/fail criteria and retry instructions.

Replace the lengthy inline anti-pattern examples and code blocks with concise references: e.g., 'Parallelization: see templates/parallel-slice-prompt.md' instead of embedding the full Agent() call patterns.

Convert the pre-execution gate into a concrete decision tree or flowchart with unambiguous thresholds rather than the current mix of signal lists and scoring formulas.

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose (~400+ lines) with significant redundancy: the 'Constituicao' section is duplicated verbatim, there are lengthy explanations of concepts Claude already understands (pipeline orchestration, vertical slicing philosophy), and extensive inline content that should be in referenced files. The anti-pattern examples, model routing tables, and parallelization details bloat the file far beyond what's needed for an orchestration overview.	1 / 3
Actionability	The skill provides some concrete guidance — pipeline sequences for different task types, code examples for Agent dispatch, and specific file paths to reference. However, much of the content is descriptive rather than instructive (listing responsibilities, explaining when to use modes), and the actual orchestration logic relies heavily on external files (policies/, templates/, programs/) without providing the executable decision tree inline.	2 / 3
Workflow Clarity	The two pipeline modes (A and B) are clearly defined with sequences, and the adaptation table maps task types to pipeline variants. However, validation checkpoints are mostly implicit ('verificar criterios de saida'), the pre-execution gate scoring formula lacks concrete thresholds for sub-components, and there's no explicit feedback loop for when pipeline adaptation fails. The workflow is present but lacks the tight validate-fix-retry loops expected for an orchestration skill.	2 / 3
Progressive Disclosure	Despite referencing many external files (policies/, templates/, programs/, docs/), the SKILL.md itself is a monolithic wall of text that inlines extensive content that should live in referenced files — the full parallelization guide, model routing table, image generator protocol, vertical slicing details, and anti-rationalization table are all inline. The file tries to be both overview and comprehensive reference, defeating progressive disclosure.	1 / 3
	Total	6 / 12 Passed

Description

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 does a solid job of explaining both what the skill does and when to use it, with explicit trigger terms. Its main weaknesses are that the capabilities described are somewhat abstract (orchestration, coordination) rather than listing concrete deliverables, and the broad 'Tech Lead' framing could create overlap with other development-related skills. The use of third person voice is appropriate.

Suggestions

Make the specific actions more concrete — instead of 'coordena qual skill executar', list examples of the pipeline stages or specific outputs (e.g., 'generates execution plans', 'produces pipeline status reports').

Sharpen distinctiveness by clarifying what this skill does NOT do (e.g., 'does not perform code review or implementation directly') to reduce conflict risk with other development skills.

Dimension	Reasoning	Score
Specificity	The description names the domain (Tech Lead/Orchestrator of development pipeline) and lists some actions like '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.' However, these actions are somewhat abstract and process-oriented rather than concrete, specific operations.	2 / 3
Completeness	The description clearly answers both 'what' (coordinates which skill to execute, in what order, adapts flow to context, ensures no critical step is skipped, maintains progress overview) and 'when' (at the start of every task, between relevant pipeline stages, with explicit trigger terms listed).	3 / 3
Trigger Term Quality	The description includes a good set of natural trigger terms: 'nova task', 'iniciar', 'pipeline de desenvolvimento', 'orquestrar', 'coordenar', 'planejar execucao', 'proximo step do pipeline', 'workflow'. These cover multiple natural variations a user might say when needing orchestration.	3 / 3
Distinctiveness Conflict Risk	While the orchestrator/pipeline coordination role is somewhat distinct, terms like 'planejar execucao', 'coordenar', and 'workflow' could overlap with project management or planning skills. The concept of 'Tech Lead' is broad and could conflict with code review or architecture skills.	2 / 3
	Total	10 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: felvieira/claude-skills-fv
Commit: 9e5d744

Reviewed: 12 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.