agentsclimarketplace

Workflow

Skill notque/vexjoy-agent/skills/workflow

VexJoy AI Agent with Intelligent Routing - /do routes plain-English requests to the right specialist agent and gates the work with reviews, tests, and a learning loop.

Install
npx -y skills add notque/vexjoy-agent --skill workflow

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its author says it does

Copied from the file, not written here

Structured multi-phase workflows: review, debug, refactor (tidy, clean up, untangle messy code without behaviour change), deploy, create, research.

SKILL.md

8.6 KB, ~1.8k tokens by cl100k_base, as published. Nobody here has run it

Workflow

Umbrella skill for all structured multi-phase workflows. Load the appropriate workflow reference based on the task.

Terminology: "workflow" is the canonical term for these flows. "pipeline" is the retained legacy alias — kept for back-compat. Routing keys, meta.name exports, and pipeline-index.json keep their existing "pipeline" identifiers unchanged; do not rename them. Use "workflow" in new prose.

Available Workflows

CategoryWorkflowReference
Code ReviewComprehensive multi-wave reviewreferences/comprehensive-review.md
Code ReviewSystematic code reviewskills/review/systematic-code-review/SKILL.md
DebuggingEvidence-based debugging pipelinereferences/systematic-debugging.md
RefactoringSafe refactoring with test gatesreferences/systematic-refactoring.md
FeaturesEnd-to-end feature lifecycleskills/process/feature-lifecycle/references/pipeline.md
PR WorkflowPR creation pipelineskills/process/pr-workflow/references/pipeline.md
ResearchFormal research with source gatesreferences/research-pipeline.md
ResearchResearch to article pipelinereferences/research-to-article.md
ContentVoice content generationreferences/voice-writer.md
ContentArticle evaluationreferences/article-evaluation-pipeline.md
ContentDe-AI content pipelinereferences/de-ai-pipeline.md
ContentDocumentation pipelinereferences/doc-pipeline.md
ExplorationCodebase explorationreferences/explore-pipeline.md
ExplorationMulti-perspective analysisreferences/do-perspectives.md
CreationSkill creation pipelinereferences/skill-creation-pipeline.md
CreationHook development pipelinereferences/hook-development-pipeline.md
CreationMCP server pipelinereferences/mcp-pipeline-builder.md
CreationPipeline scaffoldingreferences/pipeline-scaffolder.md
CreationDomain research for pipelinesreferences/domain-research.md
CreationChain compositionreferences/chain-composer.md
CreationAuto-pipeline generationreferences/auto-pipeline.md
UpgradeAgent/skill upgradereferences/agent-upgrade.md
UpgradeSystem upgradereferences/system-upgrade.md
UpgradeToolkit improvementreferences/toolkit-improvement.md
TestingPipeline test runnerreferences/pipeline-test-runner.md
TestingPipeline retroreferences/pipeline-retro.md
GitHubProfile rules extractionreferences/github-profile-rules.md
OrchestrationTask orchestrationreferences/workflow-orchestrator.md
PatternsComposable-pattern + failure-mode + cost-gate catalogreferences/workflow-patterns.md
PatternsTournament (pairwise-comparison) templatereferences/tournament-workflow.md
PatternsQuarantine (untrusted-source triage isolation)references/quarantine-pattern.md
OrchestrationDAG-based multi-skill composition patternsreferences/dag-composition-patterns.md
OrchestrationSkill compatibility matrix for chainingreferences/dag-compatibility-matrix.md
OrchestrationCommon DAG skill patternsreferences/dag-skill-patterns.md
OrchestrationDAG orchestration worked examples (standard sequential/parallel compositions)references/dag-orchestration-examples.md
OrchestrationError recovery, circular-dependency detection, adaptive/nested composition, performance metricsreferences/dag-orchestration-advanced.md

How to Use (MANDATORY)

You MUST load the named target before executing any workflow phase. The table above is a routing index — the actual methodology, phases, gates, and instructions are in its references or standalone skills.

  1. Identify the workflow category from the user's task using the table above
  2. Load the matching target. references/... paths resolve under ${CLAUDE_SKILL_DIR}; skills/.../SKILL.md paths are standalone public skills rooted at the repository.
  3. Follow the phases and gates defined in that reference exactly — do not improvise phases
  4. Report using the output format specified in the loaded reference

If the task spans multiple workflows (e.g., research then write), load each reference in sequence and follow them in order.

Workflow rule: Load the named target before executing a workflow phase. The table shows names only; the target contains the actual instructions, gates, artifact requirements, and quality criteria.

Reference Loading Table

SignalLoad These FilesWhy
Code Reviewcomprehensive-review.mdComprehensive multi-wave review
Code Reviewskills/review/systematic-code-review/SKILL.mdSystematic code review
Debuggingsystematic-debugging.mdEvidence-based debugging pipeline
Refactoringsystematic-refactoring.mdSafe refactoring with test gates
Featurespipeline.mdEnd-to-end feature lifecycle
PR Workflowpipeline.mdPR creation pipeline
Researchresearch-pipeline.mdFormal research with source gates
Researchresearch-to-article.mdResearch to article pipeline
Contentvoice-writer.mdVoice content generation
Contentarticle-evaluation-pipeline.mdArticle evaluation
Contentde-ai-pipeline.mdDe-AI content pipeline
Contentdoc-pipeline.mdDocumentation pipeline
Explorationexplore-pipeline.mdCodebase exploration
Explorationdo-perspectives.mdMulti-perspective analysis
Creationskill-creation-pipeline.mdSkill creation pipeline
Creationhook-development-pipeline.mdHook development pipeline
Creationmcp-pipeline-builder.mdMCP server pipeline
Creationpipeline-scaffolder.mdPipeline scaffolding
Creationdomain-research.mdDomain research for pipelines
Creationchain-composer.mdChain composition
Creationauto-pipeline.mdAuto-pipeline generation
Upgradeagent-upgrade.mdAgent/skill upgrade
Upgradesystem-upgrade.mdSystem upgrade
Upgradetoolkit-improvement.mdToolkit improvement
Testingpipeline-test-runner.mdPipeline test runner
Testingpipeline-retro.mdPipeline retro
GitHubgithub-profile-rules.mdProfile rules extraction
Orchestrationworkflow-orchestrator.mdTask orchestration
Patterns / cost gate / failure modesworkflow-patterns.mdWhich named pattern + when to escalate + when NOT to use
Tournamenttournament-workflow.mdPairwise-comparison ranking template
Quarantinequarantine-pattern.mdIsolate untrusted-source readers from privileged actions
DAG orchestration, multi-skill chaining, dependency resolutiondag-composition-patterns.md, dag-compatibility-matrix.mdProven multi-skill composition patterns and compatibility (from demoted skill-composer).
DAG skill patterns, skill chain troubleshootingdag-skill-patterns.md, dag-orchestration-examples.mdCommon patterns and worked examples (from demoted skill-composer).
Error recovery, circular-dependency detection, adaptive/nested skill composition, aggregate performance metricsdag-orchestration-advanced.mdAdvanced/failure-path worked examples split out of dag-orchestration-examples.md to stay under the 500-line reference limit (ADR-001).

What ships with it: 103 files

938.4 KB alongside SKILL.md, 14 of them executable

references/

63 more files not listed here. See all 103 in the repository.

Gives 0 of the 12 instructions most automation workflows skills give in ~1.8k tokens

Counted across 745 of the 1,008 authors here whose files we hold, read 2026-08-07

  • Write conventional commit messagesin 36 of 745, across 35 files
  • Delete branches after mergein 30 of 745, across 21 files
  • Make atomic commitsin 25 of 745, across 15 files
  • Write minimal code to pass testsin 22 of 745, across 10 files
  • Re-snapshot after navigation or DOM changesin 21 of 745, across 13 files
  • Use try-catch for error handlingin 20 of 745, across 8 files
  • Run tests before committingin 20 of 745, across 12 files
  • Write tests before implementationin 20 of 745, across 8 files
  • Configure branch protection rulesin 19 of 745, across 5 files
  • Explain the why in commit messagesin 19 of 745, across 9 files
  • Refactor code while tests remain greenin 19 of 745, across 6 files
  • Interact with elements using refsin 19 of 745, across 11 files

Said here and by no other author read

  • identify the workflow category from the task
  • load the matching reference target
  • follow the defined phases and gates exactly
  • do not improvise phases
  • report using the loaded reference format
  • load multiple references in sequence if needed

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 327,132. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.