Run Claude Code on a remote host over SSH — a persistent expect-driven login session, headless claude -p with the stdin fix, the interactive TUI inside a remote tmux driven by send-keys/capture-pane (one keystroke at a time, capture-verified; relayed user messages go through verbatim), and multi-turn continuity via --session-id/--resume or stream-json; hosts and credentials are placeholders resolved at runtime from the user or the vault, never hardcoded.
For product and technical management work: turn PRDs, roadmaps, RFCs, architecture reviews, and retros into decision documents. Built around the core query "pm-feature-business-case-deck", with product strategy lead judgment, buyer-ready proof, and this outcome: approve the feature, architecture, roadmap, or incident follow-up.
Multi-agent adversarial verification: two independent reviewers with the same rubric must both pass before output ships, with a fix-and-re-review convergence loop and human escalation cap. Use when gating publishing, production deploys, compliance or brand-sensitive content, or hallucination-prone claims before they ship.
Research-before-coding workflow: search npm/PyPI, MCP servers, skills, and GitHub for existing tools before writing custom code, then adopt, extend, or build. Launches the researcher agent for non-trivial needs. Use when starting a feature, adding a dependency or integration, or about to write a utility that may already exist.
Expert guidance for proactive threat hunting in Google SecOps. Use when proactively hunting for threats, retroactively analyzing indicators of compromise (IoCs), performing prevalence searches across enterprise events, hunting for MITRE ATT&CK techniques, or detecting behavioral and statistical outliers using UDM queries. Don't use for incoming alert triage (use secops-triage), active incident response and timeline deep-dives on a known breach (use secops-investigate), or detection rule authoring (use secops-detection-engineering).
Expert guidance for deep security incident and entity investigations in Google SecOps. Use when investigating cases, analyzing entities (hosts, IPs, domains, hashes, users), extracting and searching UDM events, performing asset and user timeline analysis, and detecting lateral movement across enterprise networks. Don't use for detection rule authoring or YARA-L tuning (use secops-detection-engineering), proactive hypothesis-driven hunting (use secops-hunt), initial alert triage (use secops-triage), or basic case status updates (use secops-cases).
Expert guidance for security alert triage in Google SecOps. Use when investigating and triaging security alerts, determining false positives vs. true positives, assessing entity risk, adjusting alert severity or priority, and closing or escalating alerts and cases. Don't use for deep multi-hop incident investigations across host timelines (use secops-investigate), proactive threat hunting or retroactive IoC sweeps (use secops-hunt), or authoring new detection rules (use secops-detection-engineering).
Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.
Scan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions. Use when auditing a .claude/ directory — CLAUDE.md, settings.json, MCP servers, hooks, or agent definitions.
Inspect or modify Letta Code's own memory, model, context window, system prompt, compaction, permissions, toolsets, mods, skills, channels, schedules, agent secrets, and local runtime settings. Use when the user asks how this agent or conversation is configured, asks about account usage, remaining credits, or model quota, asks you to change how you behave or how the harness runs you, or renames you.
Use when ready to commit, push, and create a PR with CI verification. Triggers include "commit and pr", "push pr", "create pr", "ship it", or when implementation is complete and needs CI validation. Watches CI and auto-fixes failures. Part of the Shep autonomous SDLC platform — https://shep.bot
Use when the user wants rapid implementation iteration without tests, builds, or commits. Triggers include "fast loop", "fast iteration", "just code", "no tests", "iterate quickly", or when the user says they have a dev server running and want to check results manually. Part of the Shep autonomous SDLC platform — https://shep.bot
Use after a PR has been merged to clean up. Switches to main, pulls latest, and deletes the local feature branch. Triggers include "merged", "pr merged", "cleanup branch", or after confirming a PR was merged. Part of the Shep autonomous SDLC platform — https://shep.bot
Use when starting any new feature, functionality, or enhancement. Triggers include "new feature", "start developing", "add functionality", "implement X", or explicit /shep-kit:new-feature invocation. Creates spec branch and scaffolds specification directory. Part of the Shep autonomous SDLC platform — https://shep.bot
Use after /shep-kit:research to create implementation plan and task breakdown. Triggers include "plan", "implementation plan", "break down tasks", "create tasks", or explicit /shep-kit:plan invocation. Part of the Shep autonomous SDLC platform — https://shep.bot
Use after /shep-kit:new-feature to analyze technical approach, evaluate libraries, document decisions. Triggers include "research", "technical analysis", "evaluate options", "which library", or explicit /shep-kit:research invocation. Part of the Shep autonomous SDLC platform — https://shep.bot
Use when a large body of work (a version milestone, an epic, a roadmap, a set of PRDs/design docs) needs to be broken into parallel workstreams and executed with the shep CLI. Triggers include "break this down", "split into workstreams", "plan V6", "what should we build first", "run these in parallel", "dependency graph", "merge order", "worktree split", or any request to turn planning docs into running shep features. Produces a workstream plan first, then drives shep feat new / shep feat start wave by wave. Part of the Shep autonomous SDLC platform — https://shep.bot
Use when creating, modifying, or reviewing web UI components. Triggers include "new component", "add component", "create UI", "build a widget", "update component", working with files in src/presentation/web/components/, or when the user asks to build any React component for the web UI. Part of the Shep autonomous SDLC platform — https://shep.bot
Implement, configure, and secure Sign In With Google (SiwG) using Google Identity Services (GIS / https://accounts.google.com/gsi/client) across web architectures. Use when creating Google sign-in buttons, implementing Google One Tap with FedCM, integrating GIS in React/Next.js/Angular/HTML, verifying ID tokens on backend runtimes (Python/Node.js/Go/Java), enforcing Google Workspace domain restrictions (hd), securing client-side ID tokens via WebCrypto nonces or encrypted IndexedDB, embedding in cross-origin iframes via the Intermediate Iframe API (https://accounts.google.com/gsi/intermediate), configuring Content Security Policy (CSP), COOP, and Permissions Policy (identity-credentials-get) headers, or handling sign-out and revocation. Don't use for legacy Google Sign-In (gapi.auth2), Google Cloud IAM service accounts, or Android/iOS native Credential Manager.
OpenDesign's operating review: growth, burn, and the concrete path to sustainability without losing the open ethos. Built as a decision-grade corporate strategy deck for leadership team.
Install skills from external ecosystems into this agent's agentstate/skills/ — resolve Claude Code plugin marketplaces, the Codex plugin repo, skills.sh registry names, GitHub repos, or local folders to their skill directories, review every file, and normalize SKILL.md frontmatter to the Penguin format.
Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation.