coco-research

206 mods across 1 repository, 636 stars between them.

create-rule

01

coco-research/coco

Skill Claude CodeCodex

Create Cursor rules for persistent AI guidance. Use when the user wants to create a rule, add coding standards, set up project conventions, configure file-specific patterns, create RULE.md files, or asks about .cursor/rules/ or AGENTS.md.

not rated 636 +126 today A 53 tokens

create-skill

02

coco-research/coco

Skill Claude CodeCodex

Guides users through creating effective Agent Skills for Cursor. Use when the user wants to create, write, or author a new skill, or asks about skill structure, best practices, or SKILL.md format.

not rated 636 +126 today A 46 tokens

create-subagent

03

coco-research/coco

Skill Claude Code

Create custom subagents for specialized AI tasks. Use when the user wants to create a new type of subagent, set up task-specific agents, configure code reviewers, debuggers, or domain-specific assistants with custom prompts.

not rated 636 +126 today A 49 tokens

migrate-to-skills

04

coco-research/coco

Skill Claude Code

Convert 'Applied intelligently' Cursor rules (.cursor/rules/.mdc) and slash commands (.cursor/commands/.md) to Agent Skills format (.cursor/skills/). Use when the user wants to migrate rules or commands to skills, convert .mdc rules to SKILL.md format, or consolidate commands into the skills directory.

not rated 636 +126 today A 73 tokens

coco-research/coco

Skill Claude CodeCodex

Modify Cursor/VSCode user settings in settings.json. Use when the user wants to change editor settings, preferences, configuration, themes, font size, tab size, format on save, auto save, keybindings, or any settings.json values.

not rated 636 +126 today A 54 tokens

ai-engineer

06

coco-research/coco

Agent Claude Code

Senior AI engineer for architecting, implementing, and optimizing end-to-end AI systems — from model selection and training pipelines to production deployment, monitoring, and ethical governance. Use proactively when designing AI architectures, selecting models, building training pipelines, optimizing inference…

not rated 636 +126 changed 1mo ago A 69 tokens

code-reviewer

07

coco-research/coco

Agent Claude Code

Senior code and architecture reviewer for comprehensive quality, security, performance, and architectural integrity analysis. Use proactively after writing or modifying code, before merging PRs, when reviewing structural changes, designing services, or evaluating API modifications. Covers security vulnerabilities…

not rated 636 +126 changed 1mo ago A 79 tokens

data-specialist

08

coco-research/coco

Agent Claude Code

Senior data specialist covering exploratory analysis, statistical modeling, machine learning, experimentation, SQL optimization, query design, and performance tuning across major database platforms. Use proactively when analyzing datasets, building predictive models, running A/B tests, writing or optimizing complex…

not rated 636 +126 changed 1mo ago A 67 tokens

database-architect

09

coco-research/coco

Agent Claude Code

Database architecture and design specialist. Use PROACTIVELY for database design decisions, data modeling, scalability planning, microservices data patterns, database technology selection, migration strategies, and performance optimization.

not rated 636 +126 changed 1mo ago A 42 tokens

mcp-specialist

10

coco-research/coco

Agent Claude Code

MCP (Model Context Protocol) specialist covering server/client development, configuration, troubleshooting, tool setup, architecture, transport layers, and protocol compliance against the MCP 2025-06-18 spec. Use proactively when building MCP servers, configuring MCP integrations in Cursor or Claude Code, designing…

not rated 636 +126 changed 1mo ago A 77 tokens

pm-advisor

11

coco-research/coco

Agent Claude Code

Product management advisor for feature planning, issue creation, prioritization, and data-driven product decisions. Use proactively when planning features, writing user stories, creating GitHub/Jira issues, prioritizing a backlog, defining acceptance criteria, structuring epics, or translating business needs into…

not rated 636 +126 changed 1mo ago A 63 tokens

coco-research/coco

Agent Claude Code

Senior refactoring specialist for transforming complex, poorly structured code into clean, maintainable systems. Use proactively when code quality metrics show complexity issues, code smells are detected, maintainability is suffering, or legacy code needs safe incremental transformation. Covers code smell detection…

not rated 636 +126 changed 1mo ago A 80 tokens

test-guardian

13

coco-research/coco

Agent Claude Code

Ensures tests actually test what they claim. Catches tautological assertions, mock leakage, tests that pass for wrong reasons, missing edge cases. Run after writing or modifying tests.

not rated 636 +126 changed 1mo ago A 40 tokens

typescript-pro

14

coco-research/coco

Agent Claude Code

Advanced TypeScript specialist for type-level programming, complex generics, end-to-end type safety, monorepo architecture, and large-scale migrations. Use when implementing advanced type patterns (conditional types, mapped types, template literals, branded types), architecting full-stack type safety (tRPC, GraphQL…

not rated 636 +126 changed 1mo ago A 108 tokens

ui-ux-designer

15

coco-research/coco

Agent Claude Code

Research-backed UI/UX design critic providing opinionated, evidence-based feedback on interfaces. Use proactively when reviewing UI code, designing layouts, choosing typography or color palettes, auditing accessibility, evaluating mobile UX, or fighting generic SaaS aesthetics. Cites Nielsen Norman Group studies and…

not rated 636 +126 changed 1mo ago A 64 tokens

INDEX

16

coco-research/coco

Command Claude Code

Auto-generated. Run python3 scripts/build-index.py to refresh.

not rated 636 +126 changed 7d ago A 0 tokens

agents-md-creation

17

coco-research/coco

Cursor rule Cursor

Use when starting an agent or assistant project, adding AI capabilities to an existing project, or wiring LLM training. Creates and maintains AGENTS.md with the required sections and links it to Agent Lightning training.

not rated 636 +126 changed 1mo ago A 0 tokens

code-quality

18

coco-research/coco

Cursor rule Cursor

Code documentation, error handling, and logging standards.

not rated 636 +126 today A 1,169 tokens

parallel-agents

22

coco-research/coco

Cursor rule Cursor

Use when a task has 2 or more independent subtasks, when work needs waves of parallel agents, or when changes need an independent verification pass. Auto-selects wave, shared-file or resume-chain orchestration and never skips verification.

not rated 636 +126 changed 1mo ago A 634 tokens

persistent-memory

23

coco-research/coco

Cursor rule Cursor

Use when starting a session or after a code change, bug fix, refactor, or decision: read /.claude/CLAUDE.md and ./CLAUDE.local.md first, then log the change and its rationale to ./CLAUDE.local.md in the same batch.

not rated 636 +126 changed 1mo ago A 942 tokens

prd-default-skill

24

coco-research/coco

Cursor rule Cursor

Use when the user asks to create, write, or revise a PRD, or any time a PRD task starts. Requires reading the prd-generator skill file before you write anything, then following its 5-step workflow and validation script.

not rated 636 +126 changed 1mo ago A 588 tokens

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: