CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

parallel-dispatcher

Divide trabalho independente e orienta sua execucao paralela. 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

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/40-parallel-dispatcher/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

70%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 orchestration playbook: concrete dispatch code, a decision tree, six documented anti-patterns with fixes, and a post-dispatch workflow with real validation and self-fix loops. Weaknesses are length that could be tightened (duplicated arbitration summary and reference pointers) and a reference graph that mostly points outside the shipped bundle, leaving navigation broken for all but one path.

Suggestions

Move the long-horizon compression and telemetry sections into their own reference files, keeping one-line pointers in SKILL.md, and collapse the closing 13-item reference list to items not already linked inline — this trims the two lowest-scoring areas (conciseness, organization).

Ship the referenced files in the bundle (policies/skills-vs-agents.md, templates/parallel-slice-prompt.md, scripts/mmd-canvas-builder.mjs, AGENTS.md table, hooks/scripts/agent-dispatch-validator.mjs) or remove/reword the pointers — currently only references/arbitration-disagreement.md resolves, so most navigation is broken.

Deduplicate the arbitration section: it restates the arbitrator role and fail-closed gate in summary form and cites references/arbitration-disagreement.md twice; a single short summary plus one pointer would preserve clarity at roughly half the tokens.

DimensionReasoningScore

Conciseness

The body is mostly dense operational content (decision tree, ❌/✅ anti-pattern pairs, code), but ~335 lines includes clear tightening opportunities: the arbitration section is summarized inline at length while its detail already lives in references/arbitration-disagreement.md (pointed to twice), the 13-item closing reference list largely repeats inline pointers, and the long-horizon compression and telemetry sections are peripheral to the core dispatch workflow. Fits 'mostly efficient but could be tightened'; not a 4 given the duplicated arbitration summary and repeated reference pointers.

3 / 5

Actionability

Concrete, near-executable guidance throughout: full Agent({...}) call shapes with subagent_type, model tier, and isolation flags, a tierForSlice routing helper, runnable commands ("node scripts/mmd-canvas-builder.mjs --session .auto", the jq telemetry audit), a slice-prompt template skeleton, and paired ❌/✏ anti-pattern examples. Not a 5 because prompts are '...' placeholders and buildSliceSelfContainedPrompt is a stub whose template file is not in the bundle; well above 3 since the dispatch patterns and commands are concrete and copy-adaptable.

4 / 5

Workflow Clarity

The multi-step process is clearly sequenced with explicit validation and feedback loops: a decision tree routes to one of three canonical paths, and the post-dispatch consolidation lists 7 numbered steps including 'Suite completa de testes no branch consolidado' and 'Self-fix CRITICAL/HIGH (loop até verde)' — a validate/fix/retry loop — plus acceptance-criteria checklists in the slice template and a fail-fast blocking hook. Matches the anchor requiring clear sequence, explicit validation, and error-recovery loops; nothing significant is missing to drop to 4.

5 / 5

Progressive Disclosure

Inline structure and signaling are good (one-level references called out with 'Ver ...' and the arbitration detail correctly split into references/arbitration-disagreement.md, which exists and matches its summary), but scored against the actual bundle only 1 of the ~13 referenced paths resolves — policies/*.md, templates/parallel-slice-prompt.md, AGENTS.md, scripts/mmd-canvas-builder.mjs, and hooks/scripts/* are absent, breaking navigation — and peripheral sections (long-horizon compression, telemetry) are inlined rather than split out. Fits 'some structure but could be better organized'; the clearly signaled but mostly dangling references keep it from 4.

3 / 5

Total

15

/

20

Passed

Description

77%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 concise, third-person description with an exceptionally strong, exhaustive trigger list that clearly signals when to invoke the skill. The main weakness is the thin 'what' clause: it states the domain and two abstract actions without naming any of the skill's concrete capabilities. Overall a strong description with one clear improvement opportunity.

DimensionReasoningScore

Specificity

"Divide trabalho independente e orienta sua execucao paralela" names the domain (parallel execution of independent work) with two actions, matching the 'domain + 1-2 concrete actions' anchor, but never enumerates the skill's concrete capabilities (dispatch paths, worktree isolation, model routing, arbitration). Not a 4 because it does not list several specific actions; not a 2 because two real actions are stated rather than purely generic handling.

3 / 5

Completeness

Both parts are present: a clear 'what' ("Divide trabalho independente e orienta sua execucao paralela") and an explicit 'when' ("Trigger em: ..." with concrete trigger phrases), so the missing-trigger cap of 3 does not apply. Not a 5 because the 'what' is a single thin compound clause — unlike the 5-anchor it lists no multiple concrete operations — while the 'when' itself is fully explicit, placing this between anchors 4 and 5.

4 / 5

Trigger Term Quality

Fourteen trigger phrases with comprehensive synonym coverage — "paralelize", "fan-out", "scatter-gather", "multi-agent parallel", "worktree paralelo" plus phrasing variants ("dispatch paralelo" / "dispatch em paralelo") and natural user questions like "quem decide quando os agentes discordam". Matches the comprehensive-synonyms anchor; not below 5 since no common variation of the request is obviously missing.

5 / 5

Distinctiveness Conflict Risk

Mostly distinct niche with specific triggers ("N slices", "scatter-gather", "arbitragem entre agentes") unlikely to fire for unrelated skills, but "comprehensive review", "5 workers", and "multi-agent parallel" have minor overlap risk with code-review or general multi-agent orchestration skills. Matches 'mostly distinct; minor overlap risk'; not a 5 given those broad terms, not a 3 since the core triggers are clearly niche.

4 / 5

Total

16

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

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.