By WenyuChiou
6 skills for context-safe multi-agent collaboration: task-splitter, context-budget, output-reconciler, debate, shared-memory, and acceptance-gate. Composes with codex-delegate + gemini-delegate via bounded .ai task packets, .coord context policy, and result.json contracts.
Use when a multi-agent round needs a pre-merge gate, pre-commit check, verification before push, or a PASS/FAIL decision after reconciliation.
Use when multi-agent work risks context overflow, memory growth, noisy logs, oversized handoffs, cross-session continuation, or parallel Codex and Gemini execution.
Use when a consequential decision needs adversarial review, opposing agent arguments, a second opinion via debate, or explicit trade-off analysis before implementation.
Use when multiple agents have completed a round and the user asks to reconcile outputs, compare Codex and Gemini, synthesize run results, identify conflicts, or decide what should be retried.
Use when a task needs single-agent self-correction across multiple iterations — write plan, execute, critique own output, revise plan, re-execute, until convergence or budget exhausted. Different from `agent-debate` (which is 2 agents arguing pro vs con); this is 1 agent looping over its own work.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
English ・ 繁體中文

6 Claude Code skills for context-safe multi-agent collaboration — task splitter, context budget, output reconciler, adversarial debate, shared memory, acceptance gate. Designed to compose with
codex-delegateandgemini-delegate-skill.
📚 Part of the agentic AI learning roadmap — a 7-stage curated path for building agentic AI, multilingual (zh-TW · zh-CN · English). Multi-agent orchestration is covered in Stage 7.
A focused marketplace for the orchestration layer above delegation. Existing delegate skills solve "Claude → Codex / Gemini handoff." This catalog solves what comes next: how to split a goal across agents, how to reconcile their outputs, how to remember decisions across sessions, and how to gate merges.
Sister marketplace: ai-research-skills
(13 skills for the research workflow).
Three high-leverage scenarios where these skills clearly pay off:
grep × N checks, and the YAML presets have caught real drift the human audit missed.Token measurements and incident logs are in docs/measured-benefits.md for the curious — but the practical takeaway is just the three scenarios above.
📋 When should I actually invoke which skill / preset? See
docs/when-to-invoke.md— has the trigger rules, YES / NO / judgment-call scenarios, decision flowchart, and a copy-paste CLAUDE.md template you can drop into your own project to codify the rules.
Prerequisite: Claude Code (https://claude.ai/code). Recommended (but
not required): codex-delegate and gemini-delegate already
installed via ai-research-skills, plus their CLI binaries on PATH.
claude plugin marketplace add WenyuChiou/agent-collab-skills
claude plugin install agent-collab-workspace@agent-collab-skills
This installs all 7 skills as one bundle. Verify:
claude plugin list
ls ~/.claude/skills/ # should include agent-task-splitter, etc.
Or use the helper script:
bash scripts/install-all.sh # macOS / Linux / git-bash
pwsh scripts/install-all.ps1 # Windows PowerShell
CLAUDE.md?No. Claude Code's built-in skill matching reads each SKILL.md's description field and auto-routes user prompts. Plugin install is the only setup step — saying "split this across Claude, Codex, and Gemini" triggers agent-task-splitter without any extra configuration.
You may optionally add explicit routing rules to your ~/.claude/CLAUDE.md if you:
agent-acceptance-gate before merging any multi-agent round")Otherwise leave CLAUDE.md alone — the skills are designed to work via description-based discovery.
npx claudepluginhub wenyuchiou/agent-collab-skills --plugin agent-collab-workspaceHand token-heavy mechanical work (batch edits, scaffolding, refactors, test generation, plotting scripts) from Claude to Codex CLI.
Hand long-context reading, bilingual rewrites, second-opinion review, and Traditional Chinese / CJK output from Claude to Gemini CLI.
11 research-hub skills: literature triage matrix, context compression, project orientation, design dialog, multi-AI routing, NotebookLM brief verification, paper-memory builder, paper summarizer, Zotero curator, the gap-to-topic decision dossier, and the research-hub orchestrator. Auto-discovered from skills/<name>/SKILL.md.
Full Zotero CRUD: search, add, update, delete items with notes, tags, collections, and PDF attachments. Dual local/Web API routing.
Manuscript revision, claim-evidence audit, banned-word / humanize pass, figure-text consistency, journal-format check, reviewer response.
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Permanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
UI/UX design intelligence. 67 styles, 161 palettes, 57 font pairings, 25 charts, 15 stacks (React, Next.js, Vue, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Nuxt, Jetpack Compose). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.
This skill should be used when users need to generate ideas, explore creative solutions, or systematically brainstorm approaches to problems. Use when users request help with ideation, content planning, product features, marketing campaigns, strategic planning, creative writing, or any task requiring structured idea generation. The skill provides 30+ research-validated prompt patterns across 14 categories with exact templates, success metrics, and domain-specific applications.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.