notque/vexjoy-agent / skills/process/workflow
workflow
VerifiedStructured work: multi-phase tasks, feature builds, planning, objective loops, hill climbing.
references/auto-pipeline/references/pipeline-catalog.json
View on GitHub{
"version": "1.0",
"generated": "2026-08-15T15:25:52Z",
"generated_by": "scripts/generate-pipeline-catalog.py",
"pipelines": [
{
"name": "agent-upgrade",
"description": "5-phase agent/skill improvement: AUDIT, DIFF, PLAN, IMPLEMENT, RE-EVALUATE.",
"phase_count": 5,
"phases": [
"AUDIT",
"DIFF",
"PLAN",
"IMPLEMENT",
"RE-EVALUATE"
],
"chain": "AUDIT → DIFF → PLAN → IMPLEMENT → RE-EVALUATE",
"task_type": "meta",
"triggers": [
"upgrade agent",
"improve agent",
"agent upgrade",
"fix agent quality",
"align agent to template"
]
},
{
"name": "article-evaluation-pipeline",
"description": "Wabi-sabi-aware 4-phase article evaluation for voice authenticity.",
"phase_count": 4,
"phases": [
"FETCH",
"VALIDATE",
"ANALYZE",
"REPORT"
],
"chain": "FETCH → VALIDATE → ANALYZE → REPORT",
"task_type": "content",
"triggers": [
"evaluate article",
"check article voice",
"is this authentic",
"review my article",
"voice evaluation",
"article evaluation",
"check my voice"
]
},
{
"name": "chain-composer",
"description": "Compose valid pipeline chains from the step menu per subdomain.",
"phase_count": 4,
"phases": [
"LOAD",
"COMPOSE",
"VALIDATE",
"PRODUCE"
],
"chain": "LOAD → COMPOSE → VALIDATE → PRODUCE",
"task_type": "meta",
"triggers": [
"compose chains",
"build pipeline chains",
"chain composition",
"pipeline spec",
"compose pipeline"
]
},
{
"name": "comprehensive-review",
"description": "Four-wave code review pipeline for large or high-risk changes.",
"phase_count": 4,
"phases": [
"CRITICAL",
"HIGH",
"MEDIUM",
"LOW"
],
"chain": "CRITICAL → HIGH → MEDIUM → LOW",
"task_type": "review",
"triggers": [
"comprehensive review",
"full code review",
"review everything",
"review and fix",
"thorough review",
"multi-agent review",
"complete code review",
"20-agent review",
"25-agent review",
"per-package review",
"3-wave review",
"4-wave review",
"adversarial review",
"full code review",
"review all packages"
]
},
{
"name": "de-ai-pipeline",
"description": "Scan-fix-verify loop for removing AI writing patterns from docs.",
"phase_count": 4,
"phases": [
"SCAN",
"FIX",
"VERIFY",
"REPORT"
],
"chain": "SCAN → FIX → VERIFY → REPORT",
"task_type": "content",
"triggers": [
"de-ai docs",
"clean ai patterns",
"fix ai writing",
"scan and fix docs",
"remove ai tells",
"de-ai pipeline"
]
},
{
"name": "do-perspectives",
"description": "Inline multi-perspective analysis with 10 analytical lenses.",
"phase_count": 5,
"phases": [
"VALIDATE INPUTS",
"MULTI-PERSPECTIVE ANALYSIS",
"SYNTHESIZE",
"APPLY",
"VERIFY AND REPORT"
],
"chain": "VALIDATE INPUTS → MULTI-PERSPECTIVE ANALYSIS → SYNTHESIZE → APPLY → VERIFY AND REPORT",
"task_type": "content",
"triggers": [
"multi-perspective analysis",
"do-perspectives",
"analyze from multiple angles"
]
},
{
"name": "doc-pipeline",
"description": "Structured 5-phase documentation pipeline with research.",
"phase_count": 5,
"phases": [
"RESEARCH",
"OUTLINE",
"GENERATE",
"VERIFY",
"OUTPUT"
],
"chain": "RESEARCH → OUTLINE → GENERATE → VERIFY → OUTPUT",
"task_type": "documentation",
"triggers": [
"document this",
"create readme",
"write documentation",
"document codebase",
"generate docs",
"technical documentation",
"create documentation",
"write docs",
"generate README",
"document the API"
]
},
{
"name": "domain-research",
"description": "Discover and classify subdomains for pipeline generation.",
"phase_count": 4,
"phases": [
"DISCOVER",
"CLASSIFY",
"MAP",
"PRODUCE"
],
"chain": "DISCOVER → CLASSIFY → MAP → PRODUCE",
"task_type": "meta",
"triggers": [
"research domain",
"discover subdomains",
"domain decomposition",
"what pipelines",
"domain research"
]
},
{
"name": "explore-pipeline",
"description": "Systematic codebase exploration with parallel subagents.",
"phase_count": 8,
"phases": [
"SCAN",
"MAP",
"ANALYZE",
"COMPILE",
"ASSESS",
"SYNTHESIZE",
"REFINE",
"REPORT"
],
"chain": "SCAN → MAP → ANALYZE → COMPILE → ASSESS → SYNTHESIZE → REFINE → REPORT",
"task_type": "meta",
"triggers": [
"understand codebase",
"explore repo",
"how does this work",
"codebase exploration",
"understand this code",
"map architecture",
"analyze quality",
"assess consistency",
"evaluate patterns",
"explore codebase",
"understand this repo",
"map the codebase",
"what is in this repo"
]
},
{
"name": "github-profile-rules",
"description": "Extract coding conventions from a GitHub user's public profile.",
"phase_count": 8,
"phases": [
"ADR",
"FETCH",
"RESEARCH",
"SAMPLE",
"COMPILE",
"GENERATE",
"VALIDATE",
"OUTPUT"
],
"chain": "ADR → FETCH → RESEARCH → SAMPLE → COMPILE → GENERATE → VALIDATE → OUTPUT",
"task_type": "meta",
"triggers": [
"github rules",
"profile analysis",
"coding style extraction",
"github conventions"
]
},
{
"name": "hook-development-pipeline",
"description": "5-phase hook creation pipeline with performance gates.",
"phase_count": 5,
"phases": [
"SPEC",
"IMPLEMENT",
"TEST",
"REGISTER",
"DOCUMENT"
],
"chain": "SPEC → IMPLEMENT → TEST → REGISTER → DOCUMENT",
"task_type": "infrastructure",
"triggers": [
"create hook pipeline",
"new hook formal",
"hook with gates"
]
},
{
"name": "mcp-pipeline-builder",
"description": "Convert any repository into a registered MCP server.",
"phase_count": 6,
"phases": [
"ANALYZE",
"DESIGN",
"GENERATE",
"VALIDATE",
"EVALUATE",
"REGISTER"
],
"chain": "ANALYZE → DESIGN → GENERATE → VALIDATE → EVALUATE → REGISTER",
"task_type": "meta",
"triggers": [
"mcp pipeline",
"repo to mcp",
"create mcp from repo",
"generate mcp",
"mcp builder",
"mcp from repo"
]
},
{
"name": "pipeline-retro",
"description": "Trace pipeline test failures to generator root causes.",
"phase_count": 5,
"phases": [
"INGEST",
"TRACE",
"PROPOSE",
"REGENERATE",
"REPORT"
],
"chain": "INGEST → TRACE → PROPOSE → REGENERATE → REPORT",
"task_type": "meta",
"triggers": [
"pipeline retro",
"trace failures",
"generator improvement",
"three-layer fix",
"fix generator"
]
},
{
"name": "pipeline-scaffolder",
"description": "Scaffold pipeline components from a Pipeline Spec JSON.",
"phase_count": 5,
"phases": [
"LOAD",
"BIND OR WRITE THE DOMAIN REFERENCE",
"SCAFFOLD SKILLS",
"INTEGRATE",
"REPORT"
],
"chain": "LOAD → BIND OR WRITE THE DOMAIN REFERENCE → SCAFFOLD SKILLS → INTEGRATE → REPORT",
"task_type": "meta",
"triggers": [
"scaffold pipeline",
"create pipeline components",
"generate pipeline from spec"
]
},
{
"name": "pipeline-test-runner",
"description": "Test generated pipeline skills against real targets.",
"phase_count": 4,
"phases": [
"DISCOVER TARGETS",
"EXECUTE",
"VALIDATE OUTPUTS",
"REPORT"
],
"chain": "DISCOVER TARGETS → EXECUTE → VALIDATE OUTPUTS → REPORT",
"task_type": "meta",
"triggers": [
"test generated pipelines",
"run pipeline tests",
"validate scaffolded skills",
"pipeline test runner"
]
},
{
"name": "research-pipeline",
"description": "Formal 5-phase research pipeline with artifact saving and source quality gates. Min 3 parallel agents.",
"phase_count": 5,
"phases": [
"SCOPE",
"GATHER",
"SYNTHESIZE",
"VALIDATE",
"DELIVER"
],
"chain": "SCOPE → GATHER → SYNTHESIZE → VALIDATE → DELIVER",
"task_type": "meta",
"triggers": [
"research pipeline",
"formal research",
"research with artifacts",
"structured research",
"research topic",
"research this",
"investigate thoroughly",
"deep research",
"systematic research",
"multi-source research"
]
},
{
"name": "research-to-article",
"description": "Multi-agent research pipeline for voice content generation.",
"phase_count": 6,
"phases": [
"GATHER",
"COMPILE",
"GROUND",
"GENERATE",
"VALIDATE",
"OUTPUT"
],
"chain": "GATHER → COMPILE → GROUND → GENERATE → VALIDATE → OUTPUT",
"task_type": "content",
"triggers": [
"research then write",
"article with research",
"write about",
"research and article",
"full article pipeline",
"comprehensive article"
]
},
{
"name": "skill-creation-pipeline",
"description": "5-phase skill creation pipeline with quality gates.",
"phase_count": 5,
"phases": [
"DISCOVER",
"DESIGN",
"SCAFFOLD",
"VALIDATE",
"INTEGRATE"
],
"chain": "DISCOVER → DESIGN → SCAFFOLD → VALIDATE → INTEGRATE",
"task_type": "meta",
"triggers": [
"create skill pipeline",
"new skill formal",
"skill with gates",
"create skill formally",
"new skill with gates",
"skill creation pipeline",
"formal skill creation"
]
},
{
"name": "system-upgrade",
"description": "6-phase pipeline for adapting agents, skills, and hooks to changes.",
"phase_count": 6,
"phases": [
"CHANGELOG",
"AUDIT",
"PLAN",
"IMPLEMENT",
"VALIDATE",
"DEPLOY"
],
"chain": "CHANGELOG → AUDIT → PLAN → IMPLEMENT → VALIDATE → DEPLOY",
"task_type": "meta",
"triggers": [
"system upgrade",
"upgrade agents",
"claude update",
"upgrade skills",
"adapt workflow",
"system health"
]
},
{
"name": "systematic-debugging",
"description": "Evidence-based 5-phase debugging: OBSERVE, HYPOTHESIZE, TEST, FIX, RECORD.",
"phase_count": 5,
"phases": [
"OBSERVE",
"HYPOTHESIZE",
"TEST",
"FIX",
"RECORD"
],
"chain": "OBSERVE → HYPOTHESIZE → TEST → FIX → RECORD",
"task_type": "process",
"triggers": [
"debug",
"find root cause",
"reproduce bug",
"fix this bug",
"this is broken",
"not working",
"why is this broken",
"getting an error",
"unexpected behavior",
"investigate error"
]
},
{
"name": "systematic-refactoring",
"description": "Safe 5-phase refactoring with test characterization and learning.",
"phase_count": 5,
"phases": [
"CHARACTERIZE",
"PLAN",
"REFACTOR",
"VERIFY",
"RECORD"
],
"chain": "CHARACTERIZE → PLAN → REFACTOR → VERIFY → RECORD",
"task_type": "process",
"triggers": [
"refactor safely",
"rename symbol",
"extract function",
"refactor",
"simplify this",
"restructure code",
"reduce complexity",
"split this file",
"restructure",
"move to separate file"
]
},
{
"name": "toolkit-improvement",
"description": "Multi-angle toolkit evaluation, ADR creation, and fix pipeline.",
"phase_count": 0,
"phases": [],
"chain": "—",
"task_type": "meta",
"triggers": [
"improve the toolkit",
"evaluate the repo",
"find ways to improve",
"make the toolkit better",
"upgrade the toolkit",
"improve yourself",
"improve this system",
"repo health check",
"toolkit audit",
"audit the system",
"toolkit system health",
"health check",
"run a health check",
"check system health",
"audit everything",
"comprehensive improvement",
"full evaluation",
"toolkit evaluation",
"repo evaluation",
"evaluate everything",
"evaluate the system",
"deep evaluation",
"thorough evaluation",
"evaluate all components",
"find issues",
"find problems",
"find bugs",
"what needs fixing",
"what's broken",
"what can be better",
"how can we improve",
"show me what's wrong",
"diagnose the toolkit",
"scan for issues",
"self-improvement",
"meta improvement",
"improvement pipeline",
"continuous improvement",
"self-evaluate",
"introspect",
"self-audit",
"self-review",
"send agents to evaluate",
"multi-agent evaluation",
"30 agent review",
"wave evaluation",
"parallel evaluation",
"swarm evaluation",
"agent swarm",
"team evaluation",
"dispatch evaluation agents"
]
},
{
"name": "workflow-orchestrator",
"description": "Three-phase task orchestration: BRAINSTORM, WRITE-PLAN, EXECUTE-PLAN.",
"phase_count": 4,
"phases": [
"BRAINSTORM",
"WRITE-PLAN",
"VALIDATE-PLAN",
"EXECUTE-PLAN"
],
"chain": "BRAINSTORM → WRITE-PLAN → VALIDATE-PLAN → EXECUTE-PLAN",
"task_type": "meta",
"triggers": [
"orchestrate",
"complex task",
"plan and execute",
"break this down",
"multi-step implementation"
]
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| planning-and-task-breakdownaddyosmani/agent-skillsBreaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| screenpipethedotmack/claude-memSearch screen and audio history recorded by Screenpipe and optionally save selected context into claude-mem. Use when the user asks to recall desktop activity, a meeting, or something seen in another app through Screenpipe. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |
| contact-widgetnexu-io/open-designSelf-contained floating chat widget with welcome screen, social links, meeting button, and message input. Single HTML file, zero dependencies. | Stars: 108k | Updated | Claude CodeCodex | Verified | Install |
| meeting-notesnexu-io/open-designMeeting notes page — title bar with attendees, agenda checklist, decisions block, action items table with owners + dates, and a "next meeting" footer. Use when the brief mentions "meeting notes", "minutes", "1:1 notes", "all-hands recap", or "会议纪要". | Stars: 108k | Updated | Claude CodeCodex | Verified | Install |