Feature Spec
Write structured product requirements documents (PRDs) with problem statements, user stories, requirements, and success metrics. Use when speccing a new feature, writing a PRD, defining acceptance criteria, prioritizing requirements, or documenting product decisions.
idea
Quick-capture an idea into Synapse with zero friction. Use when the user says /idea followed by any text. One round-trip, no follow-up questions.
google-workspace-capabilities
Reference for what Claude Code can and cannot do with Google Workspace programmatically. Consult when assessing whether Google-related tasks are agentic, hybrid, or manual.
find-bugs
Find bugs, security vulnerabilities, and code quality issues in local branch changes. Use when asked to review changes, find bugs, perform a security review, or audit code on the current branch.
supabase-capabilities
Reference for what Claude Code can and cannot do with Supabase programmatically. Consult when assessing whether Supabase-related tasks are agentic, hybrid, or manual.
create-pr
Creates pull requests with structured titles, descriptions, and issue references. Use when creating a PR, opening a PR, submitting changes for review, or pushing and creating a PR.
security-review
Security code review for vulnerabilities. Use when asked to "security review", "find vulnerabilities", "check for security issues", "audit security", "OWASP review", or to review code for injection, XSS, authentication, authorization, or cryptography issues. Provides a systematic review with confidence-based reporting.
bug-triage
Triage bug tickets from Jira or pasted text. Classifies, scores, searches the codebase for related code, identifies missing information, and produces a prioritized triage report. Use when asked to "triage bugs", "triage tickets", "review Jira issues", "prioritize bugs", or "assess bug reports".
skill-scanner
Scan agent skills for security issues. Use when asked to "scan a skill", "audit a skill", "review skill security", "check skill for injection", "validate SKILL.md", or assess whether an agent skill is safe to install. Checks for prompt injection, malicious scripts, excessive permissions, secret exposure, and supply chain risks.
deep-thought
Interactive brainstorming session — expand, connect, and research ideas using Synapse. Use when the user wants to explore an idea in depth, find connections between ideas, or brainstorm new directions.
Vercel capabilities
Reference for what Claude Code can and cannot do with Vercel programmatically. Consult when assessing whether Vercel-related tasks are agentic, hybrid, or manual.
cloudflare-capabilities
Reference for what Claude Code can and cannot do with Cloudflare programmatically. Consult when assessing whether Cloudflare-related tasks are agentic, hybrid, or manual.
council
Convene a mentor council — quick roundtable, named council, facilitator-led, or chamber mode. Manages councils, EQ presets, and meeting history. Use when user says "/council".
github-capabilities
Reference for what Claude Code can and cannot do with GitHub programmatically. Consult when assessing whether GitHub-related tasks are agentic, hybrid, or manual.
Code Review
Perform code reviews following Sentry engineering practices. Use when reviewing pull requests, examining code changes, or providing feedback on code quality. Covers security, performance, testing, and design review.
commit
Creates commits with proper conventional commit format and issue references. Use when committing code changes, creating a git commit, or saving changes.
roadmap-management
Plan and prioritize product roadmaps using frameworks like RICE, MoSCoW, and ICE. Use when creating a roadmap, reprioritizing features, mapping dependencies, choosing between Now/Next/Later or quarterly formats, or presenting roadmap tradeoffs to stakeholders.