Agent Claude Code
System design, architecture decisions, and technical planning. Use when evaluating trade-offs, designing a feature or module, making refactoring or library choices, or before any task touching 3+ files that needs a plan first.
Agent Claude Code
Expert code review for correctness, conventions, performance, and maintainability. Use after a build phase, on a PR, or when asked for a second opinion on code quality.
Agent Claude Code
Marketing strategy, positioning, copywriting, SEO, CRO, and content creation. Works as a peer to the PM — not a subordinate. Gives the product/market direction while the PM gives the technical direction. Use PROACTIVELY when: working on landing pages, pricing pages, social media posts, email sequences, SEO…
Agent Claude Code
DevOps, SRE, and FinOps specialist for infrastructure, CI/CD, deployment, monitoring, and cost optimization. Use for CI/CD pipelines, Dockerfiles, infrastructure-as-code, monitoring/alerting, cloud-cost work, deployment troubleshooting, or environment configuration.
Agent Claude Code
Operations monitor and first responder. Reads diagnostics, scheduled-task outputs, and monitoring data, triages issues, recommends severity, and assists with remote fixes. Use to process a diagnostic, triage an alert, or investigate a production issue.
Agent Claude Code
QA specialist for test strategy, edge cases, regression testing, and coverage. Use to validate coverage after a build, find missing tests during review, add regression tests for a bug, or design a test strategy for a new module.
Agent Claude Code
Application security auditor and red team specialist. Use when reviewing auth/authorization, billing/payment, data handling, internet-exposed endpoints, cryptographic operations, or any security-sensitive code.
Agent Claude Code
Product Manager for autonomous sprint orchestration. Plans sprints, makes product decisions, executes sprint cycles, and updates project state. Use PROACTIVELY when: planning what to build next, prioritizing backlog items, making product decisions, or orchestrating sprint execution. Also use when the user says "plan…
Agent Claude Code
Tech Lead and QA reviewer for autonomous sprint orchestration. Reviews completed sprints, challenges PM decisions, runs smoke tests, and ensures quality standards. Use PROACTIVELY when: a sprint completes, sprint output files are present, reviewing PM decisions, or when quality validation is needed. Also use when the…
Hook Claude Code
Runs when the agent finishes a response, executing setup.py with --tb. From rbah31/claude-code-workflow.
Hook Claude Code
Runs after a tool call finishes for Write and Edit tool calls, running an inline shell check (2 commands). From rbah31/claude-code-workflow.
Hook Claude Code
Runs before the agent uses a tool for Write, Edit and Bash tool calls, executing block_wiki_write.py and protect-uncommitted-hook.py via python3 with --force and --hard (4 commands). From rbah31/claude-code-workflow.
Hook Claude Code
Runs when the agent sends a notification, running an inline shell check. From rbah31/claude-code-workflow.
Settings file Claude Code
Agent settings declaring 4 hook events (Stop, PostToolUse, PreToolUse, Notification) and 4 allowed tools.
Skill Claude CodeCodex
Ship and capture lessons workflow. Creates the PR, updates lessons learned, updates documentation, generates the sprint retrospective, and updates the backlog. Use at the end of a sprint cycle, or when the user says "ship", "capture", "lessons", "retro", "retrospective", "wrap up", or "done with this sprint". Also use…
Skill Claude CodeCodex
Generate changelogs, release notes, and feature announcements from sprint artifacts. Use when a sprint is complete and needs to be communicated to users. Also use when the user says "changelog", "release notes", "what's new", "announce this", "communicate this feature", "write the update", or after a capture-lessons…
Skill Claude CodeCodex
Fetch, query, and analyze project data. Use this skill when the user wants to investigate metrics, understand user behavior, debug a data issue, or answer a question that requires looking at real data. Triggers on "what happened", "why did X drop", "show me the numbers", "query", "metrics", "funnel", "cohort", "data"…
Skill Claude CodeCodex
Fix phase workflow. Fixes issues identified during code review, based on the triaged review output. Use after a review phase is complete and the human has triaged the findings, or when the user says "fix", "fix the issues", "address review feedback", or "apply fixes". Also use when the user says "fix these" after…
Skill Claude CodeCodex
Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.
Skill Claude CodeCodex
Orchestrates a complete sprint cycle autonomously. Each phase runs as a separate claude -p session for context isolation. Use when the sprint-directive.md is ready and the sprint should execute end-to-end. Also use when the user says "run a full sprint", "execute the sprint", "build everything", "autonomous sprint"…
Skill Claude CodeCodex
Synchronize product state with marketing strategy. Use after sprints ship, when user feedback arrives, or when the marketing-context needs updating. Also use when the user says "sync marketing", "update positioning", "what should we communicate", "user feedback review", "marketing brief", or "prepare marketing for…
Skill Claude CodeCodex
Quick monitoring briefing. Reads all reports in monitoring/ and tasks/backlog.md, produces a 5-10 line status summary. Designed for remote use via Telegram/Channels. Use when the user says "status", "monitoring", "bilan", "what's the state", "any alerts", or "how's the project".
Skill Claude CodeCodex
Drive the running product and verify it works end-to-end. Use this skill after a deploy, before a release, or when the user says "verify", "smoke test", "does it work", "test the flow", "check staging", "end-to-end test", or "drive the product". Also use when the user wants to verify a specific user journey (signup…
Skill Claude CodeCodex
Security red team that produces executable attack scripts and a static code audit. Use this skill for any security sprint, pre-release hardening, or when code touches authentication, billing, data storage, API endpoints, or secrets. Also use when the user says "red team", "pentest", "attack surface", "security audit"…