Tessl • The management layer for AI agent skills

SkillPublic

parallel-dispatcher

Skill especializada em paralelizar trabalho via subagents corretamente — sem cair na armadilha skill-vs-agent. Use quando precisar despachar N slices verticais, N reviews, ou N tarefas independentes em paralelo, e quando reviewers/agentes paralelos discordam sobre o mesmo achado e a decisão de arbitrar/bloquear precisa de um critério formal. Trigger em: "paralelize", "N slices", "dispatch paralelo", "worktree paralelo", "5 workers", "dispatch em paralelo", "fan-out", "scatter-gather", "comprehensive review", "multi-agent parallel", "reviewers discordam", "achados divergentes", "arbitragem entre agentes", "quem decide quando os agentes discordam".

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

88%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.

A dense, highly actionable playbook with executable code, clear validated workflows, and good progressive disclosure anchored by a real bundle file. Weakest on conciseness due to a few tangential asides and on disclosure where some referenced files are absent from the bundle.

Suggestions

Trim the cost-justification paragraph in Anti-padrão 5 ('~$0.40 per slice × 5 = $2... 30 sessões/mês = $60') to a one-line rationale; the hook/API detail already justifies the habit.

Either include the referenced bundle files (policies/skills-vs-agents.md, templates/parallel-slice-prompt.md, policies/vertical-slices.md, etc.) or mark them as external/kit-level so navigation claims match the actual bundle.

Tighten the 'Teste de informação nova' MAST aside into a single concrete rule to reduce token weight without losing the fan-out criterion.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and code-forward assuming Claude's competence, but trimmable asides remain (the per-session cost-savings paragraph and the MAST 'informação nova' aside) that keep it just below lean.	4 / 5
Actionability	Copy-paste-ready executable TypeScript for all three canonical paths, a concrete helper function (tierForSlice), a prompt template structure, and ❌/✅ anti-patterns covering the common cases.	5 / 5
Workflow Clarity	The 7-step Pós-dispatch consolidation is clearly sequenced with explicit validation checkpoints ('Verificar status', 'Suite completa de testes') and a feedback loop ('Self-fix CRITICAL/HIGH — loop até verde'), plus a fail-closed arbitration gate.	5 / 5
Progressive Disclosure	Well-structured overview with one-level-deep references, and the arbitration detail is correctly offloaded to the real references/arbitration-disagreement.md bundle file; however several other referenced paths (policies/, templates/) do not exist in this bundle, slightly overstating navigation.	4 / 5
	Total	18 / 20 Passed

Description

91%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.

A strong, specific description that clearly states capability and triggers with comprehensive natural keywords. Main weakness is mild abstraction in the capability phrasing and minor overlap risk with related orchestration skills.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('despachar N slices verticais, N reviews, ou N tarefas independentes em paralelo', 'arbitrar/bloquear') with only minor abstraction gaps, fitting the 'several specific actions' anchor rather than the fully comprehensive 5.	4 / 5
Completeness	Explicitly answers both what ('paralelizar trabalho via subagents corretamente', arbitrar) and when ('Use quando... Trigger em:') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger list with synonyms and colloquial phrasings ('paralelize', 'fan-out', 'scatter-gather', '5 workers', 'reviewers discordam', 'quem decide quando os agentes discordam') that users would naturally say.	5 / 5
Distinctiveness Conflict Risk	Clear niche (parallel dispatch + inter-agent arbitration) with distinct triggers, but minor overlap risk with sibling orchestrator/swarm skills in the same kit keeps it just below 5.	4 / 5
	Total	18 / 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
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: felvieira/claude-skills-fv
Path: skills/40-parallel-dispatcher/SKILL.md
Revision: 90329e3

Reviewed: 24 days ago

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.

parallel-dispatcher

Table of Contents

Is this your skill?