brainbrew-devkit

Use when setting up, verifying, or repairing BrainBrew DevKit in Codex, including hooks, global skills, MCP config, runner files, and plugin-native assets.

Use when configuring or troubleshooting BrainBrew MCP access in Codex, including .mcp.json, codex mcp commands, and available BrainBrew MCP tools.

Use when the user wants to run or follow a BrainBrew workflow in Codex, including develop, review, docs, devops, research, support, data, moderation, marketing, or skill-dev recipes.

Set up workflow templates and manage chain flows. Trigger when user says: "set up a workflow", "create a development workflow", "I need a CI/CD pipeline", "set up devops", "bump develop", "bump devops", "add agent to chain", "show chain flow", "edit chain config", "create custom workflow", "add a team node", "run agents in parallel", "create agent team", "validate chain", "check chain config", "verify chain".

Build and manage VitePress documentation site. Trigger when user says: "build docs", "deploy docs", "preview docs", "update docs", "docs dev server", "run docs locally", "check docs build".

Search and install skills from multiple sources (Vercel Skills, GitHub, Anthropic official). Use when user says "find skill", "search skill", "install skill", or when agent-improver needs to find skills for an agent.

Create and improve agents. Trigger when user says: "create an agent for X", "build me an agent", "I need an agent that does Y", "make a code review agent", "create a testing agent", "improve my agent", "list agents", "show me agents", "what agents do I have".

Create skills. Trigger when user says: "create a skill for X", "build me a skill", "I need a skill that does Y", "make a deployment skill", "list skills", "show my skills".

Trigger AI Discovery chain for exploring and optimizing prompts, skills, and agents through multi-agent debate

Iteratively reviews and fixes Claude Code skill quality issues until they meet standards. Runs automated fix-review cycles using the skill-reviewer agent. Use to fix skill quality issues, improve skill descriptions, run automated skill review loops, or iteratively refine a skill. Triggers on 'fix my skill', 'improve skill quality', 'skill improvement loop'. NOT for one-time reviews—use /skill-reviewer directly.

Analyze structured datasets (CSV, databases, numerical data). Triggers on 'analyze data', 'compute statistics', 'find patterns in data'. NOT for qualitative research — use research/analysis.

Clean and transform raw data for analysis. Triggers on 'clean data', 'fix data quality', 'normalize data', 'preprocess data'. NOT for data collection — use data-collection.

Collect data from sources (APIs, databases, files). Triggers on 'collect data', 'pull data', 'extract data', 'ingest data'. NOT for qualitative research or web research — use research/source-gathering.

Generate data-driven reports with metrics, charts, and recommendations. Triggers on 'create report', 'generate dashboard report', 'write data report'. NOT for narrative research reports — use research/report-writing.

Create data visualizations (charts, plots, dashboards). Triggers on 'visualize data', 'create chart', 'plot data', 'build dashboard'. NOT for written reports — use reporting.

Review code changes for bugs, security vulnerabilities, performance issues, and correctness. Triggers on "review this code", "check my changes", "code review", "review the diff". NOT for requesting external reviews — use requesting-code-review instead.

Implement code from an existing plan using the agent chain. Use when user says "start coding", "implement the plan", "execute the plan", "build this", or references a plan file to begin implementation. Requires a plan path as argument.

Write user-facing copy including UI text, error messages, notifications, and help content. Triggers on "write the copy for", "improve this error message", "write UI text", "help text for this feature". NOT for technical documentation — use documentation.

Quick diagnosis and fix for straightforward bugs and errors. Triggers on "fix this bug", "why is this broken", "this error keeps happening", "quick fix". NOT for complex multi-layer issues — use systematic-debugging instead.

Coordinate multi-file documentation updates across a codebase. Triggers on "update all docs", "sync docs with code", "documentation sweep", "audit documentation", "docs are out of date". NOT for single-file doc updates — use documentation.

Generate and update technical documentation for code, APIs, and projects. Triggers on "document this", "add docs", "write a README", "add JSDoc", "generate API docs". NOT for multi-file doc coordination — use doc-orchestration.

Implement features following a plan and existing codebase patterns. Triggers on "implement this", "build this feature", "write the code for", "start coding". NOT for planning — use plan. NOT for fixing bugs — use debugging.

Write structured session notes, retrospectives, and lessons learned. Triggers on "write a retro", "document what happened", "journal this session", "lessons learned", "what went wrong". NOT for technical documentation — use documentation.

Discover, configure, and test MCP server integrations and tool connections. Triggers on "add MCP server", "configure MCP", "list MCP tools", "connect to MCP", "test MCP integration". NOT for general API integration — use implementation.

Track implementation progress, update plan status, identify blockers, and write status reports. Triggers on "update the plan status", "what's the progress", "mark phase as done", "project status", "track progress". NOT for creating plans — use plan.

Research technical topics, compare solutions, and produce structured reports. Triggers on "research this", "compare options for", "what's the best approach for", "evaluate frameworks", "find best practices". NOT for codebase exploration — use scouting.

Explore codebase structure, discover files, map patterns, and understand architecture. Triggers on "explore the codebase", "find where X is", "map the project structure", "what files are related to", "how is this organized". NOT for external research — use research.

Run tests, verify builds, and report results with evidence. Triggers on "run tests", "check if tests pass", "verify the build", "test this". NOT for writing new test files — use implementation. NOT for debugging failures — use debugging.

Review and create UI component specifications, check accessibility, and apply design patterns. Triggers on "design this component", "review the UI", "check accessibility", "improve the UX", "create a component spec". NOT for writing copy — use copywriting.

Triage and respond to monitoring alerts by assessing severity, diagnosing root cause, and deciding on action. Triggers on 'handle alert', 'investigate alert', 'service is down', 'error rate spike', 'incident response'. NOT for proactive monitoring (use monitoring) or executing rollbacks (use rollback).

Fix code issues identified by code-scanning, security-auditor, or linter output. Triggers on 'fix these issues', 'apply fixes', 'fix vulnerabilities', 'fix lint errors'. NOT for writing new features or refactoring -- only fix identified issues.

Scan code for quality issues, anti-patterns, complexity, and dependency problems. Triggers on 'scan code', 'check code quality', 'pre-commit check', 'analyze changes'. NOT for security-specific scanning (use security-auditor) or compliance (use compliance-review).

Review code and infrastructure for compliance with regulatory frameworks (GDPR, SOC2, HIPAA, PCI-DSS). Triggers on 'compliance check', 'GDPR review', 'SOC2 audit', 'PII scan', 'regulatory review'. NOT for general security scanning (use security-auditor) or code quality (use code-scanning).

Deploy applications to target environments with build, tag, deploy, and health verification steps. Triggers on 'deploy to', 'release to staging', 'push to production', 'deploy this'. NOT for rollbacks (use rollback) or monitoring after deploy (use monitoring).

Monitor application health, resource usage, and service availability. Triggers on 'check health', 'monitor services', 'check status', 'is the app up'. NOT for handling alerts (use alert-handling) or rolling back (use rollback).

Analyze application performance, identify bottlenecks, and compare against baselines. Triggers on 'check performance', 'analyze latency', 'profile app', 'bundle size check'. NOT for runtime monitoring (use monitoring) or fixing issues (use code-fixing).

Roll back a deployment to the previous stable version when failures or critical issues occur. Triggers on 'rollback', 'revert deployment', 'undo deploy', 'restore previous version'. NOT for code-level reverts or database migration rollbacks without explicit confirmation.

Scan code for security vulnerabilities against OWASP Top 10 and common insecure patterns. Triggers on 'security audit', 'check for vulnerabilities', 'scan for secrets', 'OWASP check'. NOT for compliance framework reviews (use compliance-review) or runtime alert handling (use alert-handling).

Run test suites, generate coverage reports, and verify code quality. Triggers on 'run tests', 'check coverage', 'test this', 'verify tests pass'. NOT for writing new tests (do that manually) or debugging failures (use code-fixing).

Scan codebase to find undocumented functions, classes, and APIs. Triggers on "find undocumented code", "scan for doc gaps", "what needs docs". This scans code for DOCUMENTATION gaps, NOT security or code quality issues (use devops/code-scanning for that).