OctavianTocan

Use when changing, extending, testing, or reviewing the Bun-backed Paw CLI package and its generated agent skills.

Use when writing or reviewing Pawrrtal Effect TypeScript code in backend-ts: API contracts, HttpApi handlers, services, repos, layers, tagged errors, Effect tests, streams, SQL, auth middleware, or vendor-source API checks.

Use when running the Bun-backed Paw CLI: local health, active context, shell completions, output modes, profiles, and verification of the supported command surface.

Turn a bad or long Pawrrtal work session into durable project learning. Use when the user says $retro, asks to learn from a session, says too much went wrong, or asks to create/update skills or rules from recent failures.

Use when touching Pawrrtal channels, providers, tools, plugins, subagents, context providers, turn orchestration, or code that decides where an integration should live. Enforces the split between generic kernel code, manifest plugins, trusted runtime adapters, provider adapters, channel adapters, and agent runtime primitives.

Operate Pawrrtal as a live service: prove the running commit, local origins, Cloudflared public URL, database schema, Telegram channel, and shutdown state. Use when checking whether Pawrrtal is live, deployed, reachable, healthy, broken in Telegram, safe to restart, or safe to take down.

Apply Pawrrtal-specific taste rules for clean modern UX, CLI output, Telegram rendering, and agent/tool presentation. Use when changing UI copy, visual polish, CLI labels, Telegram flow output, tool names, folder/file listings, thinking/tool rendering, or when generalizing user feedback into repo conventions.

Use when planning creative, ambiguous, or multi-step work: new features, components, behavior changes, refactors, or any task whose requirements need clarifying before implementation.

Create small, atomic, Conventional Commits. Use when the user asks to commit, split work into commits, draft commit messages, or stage related changes — never for drive-by mega-commits.

Use when designing Effect HTTP API surfaces (HttpApi, HttpApiClient, branded params, typed errors), Effect Config / AppConfig, module boundaries (Domain/Errors/Api/Service/Repo), sub-modules, Postgres persistence, or reviewing backend layout in apps/api or packages/api-core. Prefer repos/effect-smol and docs/agent-patterns/ for Effect idioms. NOT for visual UI.

Use when changing generated workflows, OpenAPI artifacts, project-structure blocks, or repo-local skills.

Decides when to create or update nested AGENTS.md, README.md, and CLAUDE.md files in the agentic-inbox monorepo. Use when adding packages/apps/tools, restructuring subtrees, writing agent docs, or when nested subtree docs may be stale or missing.

Use when adding, modifying, generating, checking, or debugging repo-local skill fragments embedded in source code with //<skill-gen> markers.

Use when creating, modifying, generating, checking, or debugging CI workflow fragments embedded in source code with //<gen-github-workflow> markers.

Use when adding, modifying, generating, checking, or debugging repo-local skill fragments embedded in source code with //<skill-gen> markers.

Use when setting up, debugging, or operating Cloudflare cloudflared tunnels, public hostnames, WebSocket apps, Zero Trust Access gates, DNS routes, and localhost-only origins on VPS or server hosts.

Use when setting up, debugging, or operating Cloudflare cloudflared tunnels, public hostnames, WebSocket apps, Zero Trust Access gates, DNS routes, and localhost-only origins on VPS or server hosts.

Use the Bitwarden Secrets Manager CLI bws safely. Trigger when working with Bitwarden, Secrets Manager, bws, BWS_ACCESS_TOKEN, secret get/list/create/edit/delete, project list, bws run, or secret-backed environment variables.

Use the Bitwarden Secrets Manager CLI bws safely. Trigger when working with Bitwarden, Secrets Manager, bws, BWS_ACCESS_TOKEN, secret get/list/create/edit/delete, project list, bws run, or secret-backed environment variables.

Stealth Chromium browser automation that bypasses bot detection. Use this skill whenever the user wants to scrape, screenshot, PDF, or automate a site that blocks normal headless browsers — Cloudflare Turnstile, reCAPTCHA v3, FingerprintJS, ShieldSquare, BrowserScan, "Access Denied" responses, suspicious 403/429s on plain `curl`, or any site where Playwright/Puppeteer get caught. Also use when the user mentions CloakBrowser, stealth Chromium, anti-bot bypass, "headless detection", "real Chrome fingerprint", or wants a one-off "what does this page actually render" check. Prefer this skill over raw `curl`/`fetch` for any site behind a CDN or bot-detection layer.

Send or verify Telegram notifications from Codex or Claude Code using Bitwarden Secrets Manager. Use when the user asks to notify, message, ping, send a Telegram update, verify completion notifications, or inspect the automatic completion-summary hook.

Socratic teaching loop for any Claude Code session — quiz yourself on what actually happened, confirm mastery item by item, and don't finish until everything's locked in. Use when the user says "/teach", "teach me this session", "quiz me on what we did", "help me understand what just happened", "make sure I understand", or wants to lock in understanding of a session, file, or topic before moving on.

Create new AI agent skills with proper structure, YAML frontmatter, and cookbook-based organization. Uses a grill-me style interview to understand requirements before building — walks the design tree one question at a time, resolving each branch. Use when the user wants to create a skill, make a new skill, scaffold a skill, or mentions "new skill", "create skill", "make skill", "skill template". Triggers on skill creation requests.

Use when the user mentions Notion, links to Notion, asks about Notion pages, or wants to create/read/search/update/delete/move/sync anything in Notion.

Persistent memory system for AI coding agents. Use when you need to save facts about the user, store interaction preferences, log session events, or search previously saved memories. Triggers on remembering, saving context, recalling past decisions, or when the user says "remember this". Also use proactively when the user shares personal info, project context, or preferences worth persisting across sessions.

Use Infisical CLI cleanly for secrets, env injection, machine identity auth, self-hosted domains, and repo-specific secret workflows. Trigger when the user mentions Infisical, infisical CLI, universal-auth, machine identity, secret injection, replacing .env files, or using secrets for Pawrrtal/dev services.

Request reviewers on a GitHub PR and/or mark it ready for review. Use when the user says 'tag <name> on the PR', 'add <name> as a reviewer', 'request review from <name>', 'mark this PR ready for review', 'add the ready-for-review label', or 'this PR is ready'. Friendly names like 'Alex' or 'Sam' are resolved to GitHub logins live via gh.