Generate structured PRD (Product Requirements Document) planning documents optimized for AI-assisted development. Creates discrete, single-conversation tasks with reasoning level estimates to optimize token usage and model selection. Use when users want to plan implementation work, break down features into tasks, create implementation roadmaps, or structure development work for AI pair programming. Triggers on phrases like "create a PRD", "plan this feature", "break down this task", "implementation plan", "create threads for", or "help me plan".

Task queue - add requests or process pending work

Manage tasks in Johnny.Decimal systems using the jdtodo.txt format — parsing, creating, completing, cancelling, and modifying tasks stored in todo.txt files at the 00.02 Tasks location. Use this skill when the user wants to manage their tasks, add a todo, complete a task, check what's due, review their task list, or says things like "show my tasks," "what's due today," "add a task," "mark that done," "what should I work on," "complete this task," "cancel that task," "show overdue tasks," "what's on my plate," "review my someday list," "show blocked tasks," or "what tasks are due this week." Also trigger when the user says "manage my todos," "update my task list," "process my tasks," or references todo.txt or jdtodo.txt.

DEFAULT PIPELINE for all tasks requiring execution. You (Claude) are the strategic orchestrator. Codex agents are your implementation army - hyper-focused coding specialists. Trigger on ANY task involving code, file modifications, codebase research, multi-step work, or implementation. This is NOT optional - Codex agents are the default for all execution work. Only skip if the user explicitly asks you to do something yourself.

Android WorkManager for guaranteed background execution - use for deferred tasks, periodic syncs, file uploads, notifications, and task chains. Covers CoroutineWorker, constraints, chaining, testing, and troubleshooting. Use when implementing background work that needs reliable execution across app restarts and doze mode.

Use the Fizzy CLI for project management — boards, cards, columns, comments, steps, tags, notifications, pins, webhooks, account. Triggers on any Fizzy task/card/board action or fizzy.do URL.

Filter and curate a KubeCon schedule from ICS calendar exports. Parses the raw schedule, applies heuristic filters to surface deep dives and high-signal talks, then iteratively refines recommendations based on user feedback. Outputs a curated markdown list and a filtered ICS file. Use this skill whenever the user mentions KubeCon schedule, KubeCon talks, filtering conference sessions, or wants help deciding which KubeCon sessions to attend — even if they just say "help me pick talks" or "there are too many sessions."

Extract and analyze Granola meeting notes. USE WHEN user asks to "extract granola meetings", "analyze my meetings", or "what meetings did I have". OUTPUT structured markdown with people, companies, TODOs, and insights to ~/.granola-archivist/output/

Guides intelligent planning strategies with automatic phase detection and complexity assessment. Auto-activates when users mention epic breakdown, feature decomposition, scope estimation, dependency analysis, risk identification, or ask "how do I plan this complex task", "break down this feature", "what's the scope", "estimate effort", "identify dependencies", or "planning strategy". Provides interactive planning mode with 6 planning phases (complexity assessment, scope definition, dependency analysis, risk identification, task breakdown, effort estimation). Works with sequential-thinking for complex decomposition, docs-seeker for research, pm-workflow-guide for command suggestions, and linear-subagent-guide for Linear integration.

Manage tasks, projects, and areas using the tdn CLI. Use when the user wants to create, update, query, or organize their tasks. This skill helps Claude work as a productivity assistant for life and work tasks.

Manage task documentation by syncing between local task directories and GitHub issues

Bootstrap project state, then execute a given task or pick the next priority. Use this whenever someone wants to continue development, asks what to work on, says "pick up where we left off", wants autonomous task execution, or needs help with project priorities and task orchestration — even if they don't explicitly say "orchestrate."

Interactive planning and execution for complex tasks. IMMEDIATELY invoke when user asks to use planner.

Comprehensive code quality review focusing on DRY (Don't Repeat Yourself), KISS (Keep It Simple, Stupid), and Clean Code (Easy to Read) principles. Use when reviewing code changes, analyzing code quality, or assessing code maintainability for any feature, bug fix, or refactoring task.

Communications-domain literature review with Claude-style knowledge-base-first retrieval. Use when the task is about communications, wireless, networking, satellite/NTN, Wi-Fi, cellular, transport protocols, congestion control, routing, scheduling, MAC/PHY, rate adaptation, channel estimation, beamforming, or communication-system research and the user wants papers, related work, a survey, or a landscape summary.

Create, read, update, share, and export Google Docs. Use when the user asks to create documents, write content to Google Docs, share docs, export to PDF/DOCX, or convert markdown files to Google Docs.

Scope-aware implementation workflow with TDD and continuous quality checks. Use when asked to "implement this", "build this feature", "execute the plan", or after /arc:ideate has created a feature spec. For small work it creates a lightweight inline plan; for larger work it creates or loads a full implementation plan and executes task-by-task with build agents.

Comprehensive SessionEnd hook that syncs and synthesizes all daily completions, notes, todos, and conversation data into unified daily notes and knowledge bases.

Unified worklog system. Synthesizes session work into daily markdown files with clean bullet points. Supports weekly rollups for Slack #progress sharing. Replaces fragmented checkpoint/session-state/weekly-notes systems.

Anti-detect browser automation CLI & Skills for AI agents. Use when the user needs to interact with websites with bot detection, CAPTCHAs, or anti-bot blocks, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task that requires bypassing fingerprint checks.

Find the next highest-priority action to work on. Scans local TODO files, source code TODO comments, GitHub issues, and unpushed local commits. Checks for blockers, staleness, and priority signals to recommend what to do next. Use when asked "what should I work on next", "next task", "find work", or "what's left to do".

Comprehensive guidelines for designing, writing, and implementing effective notification systems across email, push, SMS, in-app, and chat channels.

Manage Gmail email sync, triage, and analysis workflows. Use when user wants to sync emails, triage inbox, check email analysis results, view email statistics, manage the email processing pipeline, find newsletters, check pending emails, or understand email workflow status. Triggers on phrases like "sync my emails", "triage inbox", "email status", "check newsletters", "email analysis", "what emails do I have", "pending emails", "unsubscribe from newsletters".

Build forms using @mantine/form in the mantine-9 repository. Use this skill when: (1) setting up a form with useForm, (2) adding validation rules or async validation, (3) working with nested object or array fields, (4) sharing form state across components with createFormContext, (5) using uncontrolled mode for performance, (6) using the standalone useField hook, or (7) any task involving useForm, getInputProps, onSubmit, insertListItem, or form validation.

Thin orchestrator for Task Decomposition Protocol v2. Supports two modes - /plan (decompose spec into tasks) and /execute (run tasks via subagents). Delegates all state management to the tasker CLI.

Refine, parallelize, and verify a draft task specification into a fully planned implementation-ready task

Set up a cross-platform Ralph Wiggum loop for continuous autonomous Claude execution. Use when the user wants to run Claude in a loop, implement the Ralph technique, or needs continuous autonomous operation. This skill only sets up the PS1 scripts - use pm7y-ralph-planner to create TASKS.md files.

Use when executing multi-task plans where each task can be implemented independently by a subagent. Triggers when a plan has 3+ independent tasks, when speed of execution is important, when tasks have clear acceptance criteria suitable for delegation, or when two-stage review gates (spec compliance and code quality) are needed for iterative fix cycles.

This skill should be used when the user has a large, complex task requiring: (1) multi-file or multi-step implementation, (2) major refactoring or architecture changes, (3) new feature spanning multiple components. This skill should NOT be used for simple fixes, single-file edits, or quick questions. Activates strict verification with planning, success criteria, and evidence collection.

Use after writing-plans to decompose monolithic plan into individual task files and identify tasks that can run in parallel (up to 2 subagents simultaneously)

Mandatory skill that ensures all work follows RAE guidelines. Activates automatically before any code task.

Autonomous development orchestrator that combines ephemeral Ralph workers with Beads granular task tracking. Use when executing multiple beads autonomously, running parallel development tasks, or when you need persistent work tracking across sessions.

Use when orchestrating parallel phases in plan execution - creates isolated worktrees for concurrent task execution, installs dependencies, spawns parallel subagents, verifies completion, stacks branches linearly, and cleans up (mandatory for ALL parallel phases including N=1)

Collaborate with Codex (GPT-5.2) via named sessions. Trigger: user asks to work with Codex, use Codex, ask Codex, involve Codex, etc. CRITICAL: Use subcodex CLI via Bash, NOT the Task subagent tool.

Default path for all single-workflow work: new one-off workflows, existing- workflow edits, verification repairs, and workflow-local data tables. Use build-workflow directly — do not load planning or create-tasks first. Load planning only when multiple coordinated workflows or shared cross-task data tables require a dependency-aware task graph.

Control the user's real Safari browser on macOS using AppleScript and screencapture. This skill should be used when the user asks to interact with Safari, browse websites, read web pages, automate browser tasks, take screenshots of web content, or when any task would benefit from seeing or interacting with what's in their browser. Triggers on keywords like "safari", "browser", "web page", "open tab", "screenshot the page", "read this site", "browse", "click on", "fill in the form".

Use when you need to create an execution plan from a feature spec - handles worktree context, dispatches subagent for task decomposition, validates quality, analyzes dependencies, groups into phases, and commits the plan

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.

This skill provides guidance for using the gh-pr-review GitHub CLI extension to view and manage inline PR review comments from the terminal. Use this skill when working with pull request reviews, viewing inline code review threads, replying to comments, starting/submitting reviews, resolving threads, or when needing structured JSON output for PR review workflows. Triggers on requests like "show PR review comments", "reply to this thread", "start a review", "resolve threads", "view unresolved comments", or any PR code review task.

Use to share state across sessions and agents using the rosemary CLI knowledge graph — session continuity (start/end), a durable task dispatcher (`/rosemary tasks`) that replaces ephemeral TodoWrite/local jsonl, and a knowledge tier (`/rosemary recall`). Auto-triggers when `.agents/` exists at conversation start, or when the user says "start session", "let's continue", "dispatch the next task", "wrap up", "end session".

Manage macOS Calendar events and Reminders using the ekctl CLI tool

Create ShinkaEvolve task scaffolds from a target directory and task description, producing `evaluate.py` and `initial.<ext>` (multi-language). Use when asked to set up new ShinkaEvolve tasks, evaluation harnesses, or baseline programs for ShinkaEvolve.

Alignment conversation starting from a user's rough idea. Co-decides with the user whether the idea should be acted on directly in the current session, or fixed into a formal Task by producing four documents in `.task/` for independent dispatch. Handles lightweight 'do it now while we talk', heavyweight 'define precisely, run later', and 'just help me think about this' — all on the same skill. Use when the user describes a task or intent they want to align on. Trigger phrases include 'help me plan this', 'let's think this through', 'I want to explore X', 'I have an idea', '/task-alignment'. Also use proactively when a user jumps into a complex task without defining scope or success criteria — pause, align, and help them pick the right vessel (this session vs. a task).

Access real-time context and life history from Bee, a wearable AI that captures and transcribes the owner's conversations. ALWAYS start with 'bee now' for the last 10 hours of conversations with full utterances - the highest-value context for relevant help. Use this skill when: (1) you need to know what's happening RIGHT NOW - recent conversations, current context, what was just discussed; (2) the user asks about something that just happened or someone they just talked to; (3) you need life context - who the owner is, relationships, work, preferences, places they go, photos; (4) searching past conversations/daily summaries/facts, recalling where the owner was, reviewing insights, or managing facts and todos; (5) syncing or monitoring Bee data.

Apply Spatie's Laravel and PHP coding standards for any task that creates, edits, reviews, refactors, or formats Laravel/PHP code or Blade templates; use for controllers, Eloquent models, routes, config, validation, migrations, tests, and related files to align with Laravel conventions and PSR-12.

Enrich contact, company, and influencer data using x402-protected APIs. Superior to generic web search for structured business data. USE FOR: - Enriching person profiles by email, LinkedIn URL, or name - Enriching companies by domain - Finding contact details (email, phone) with confidence scores - Resolving person identity and enriching consumer profiles (Minerva) - Searching for people or companies by criteria - Verifying email deliverability before outreach - Enriching influencer/creator profiles across social platforms TRIGGERS: - "enrich", "lookup", "find info about", "research" - "who is [person]", "company profile for", "tell me about" - "find contact for", "get LinkedIn for", "get email for" - "employee at", "works at", "company details" - "verify email", "check email", "is this email valid" - "influencer", "creator", "influencer contact", "influencer marketing"

Generate 1-3 personalized email variants for a single prospect. The composition bar adapts to the use case — cold_outbound demands a signal → pain → positioning chain; follow-ups / recaps / renewals lean on prior context and next-step framing. Supports cold_outbound, discovery_follow_up, demo_recap, re_engagement, renewal, expansion, objection_handling. Returns subject lines and mobile-readable bodies with a rationale chain. Use for sales prospecting, lead generation, account-based selling, buyer-intent-driven outreach, B2B prospecting. Triggers on phrases like "write a cold email", "personalize an email", "draft outreach", "follow up on this prospect", "email this prospect", "outbound to X", "send a chaser".

This skill should be used when the user asks to "verify a fix", "reproduce failure", "diagnose issue", "check BEFORE/AFTER state", "VF task", "reality check", "check test quality", "mock-only tests", or needs guidance on verifying fixes by reproducing failures before and after implementation, or detecting mock-heavy test anti-patterns.

GitLab automation hub. Routes requests to specialized skills. ALWAYS use this skill when: (1) any GitLab operation, (2) unsure which skill to use, (3) multi-step GitLab workflows. Start here for any gitlab task.

Create, read, update, move, and manage kanban board feature files backed by markdown with YAML frontmatter. Use when working with kanban boards, task/feature tracking, `.devtool/features/` directories, feature files with status/priority frontmatter, or any project management tasks involving markdown-based kanban workflows.

Review and finalize (REVIEWER + DOCUMENTER phases) - runs adversarial code review, commits changes, completes task, and records reflection to capture pattern outcomes.

This skill should be used when code search is needed (whether explicitly requested or as part of completing a task), when indexing the codebase after changes, or when the user asks about ccc, cocoindex-code, or the codebase index. Trigger phrases include 'search the codebase', 'find code related to', 'update the index', 'ccc', 'cocoindex-code'.

Evening task selection ceremony for maker work (discovery: requirements-clarity). Evaluate at requirements-clarity when user mentions shutdown ritual, evening ceremony, select for book, end of day selection, or tomorrow's tasks.

Access Google Gmail, Calendar, Tasks, Drive APIs

Turn ideas into structured specs and execute them — conduct interviews to refine requirements, import existing plans, or run task lists via subagents. Use whenever starting a feature, planning implementation, or managing task execution.

Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.

Intelligence gathering phase - spawns parallel agents to analyze codebase, patterns, git history, and web research. Creates or updates task file with findings.

IMPORTANT: This skill contains a research methodology you MUST read before doing any web research. It defines a 4-phase protocol (dimension mapping → parallel subagent allocation → T1-T4 source credibility triage → completeness gate with saturation stopping criteria) that you do not have by default. Without reading this skill, you will skip dimension mapping, run searches sequentially instead of in parallel, miss the source tier system, and lack the completeness checkpoints. Read this skill FIRST whenever the user asks to research, investigate, compare, evaluate, explain, or look into any topic — or when they need current real-world information for any task (articles, presentations, reports, decisions). Also read it for 'what is X', 'what are the best practices for X', market/technology analysis, or any question requiring synthesis of multiple web sources.

Use simplicity-cli to autofill PDF forms from local files or URLs, monitor async task execution, and download filled PDFs. Use when a user asks to fill forms with AI, run form autofill from context/source documents, check task status, wait for completion, or debug CLI workflow/auth behavior.

Guide agents to use `package:ffigen` to automatically generate FFI bindings instead of writing them manually. Use this skill when a task involves writing new FFI bindings, extending C/Objective-C/Swift integrations, or replacing hand-crafted `dart:ffi` setups.

Search Haskell APIs using Hoogle. Use this skill when working with Haskell projects to look up function signatures, find functions by type, or discover library documentation. Activate proactively when you need to understand Haskell library APIs, find the right function for a task, or look up type signatures.

Write contextual commits that capture intent, decisions, and constraints alongside code changes. Use when committing code, finishing a task, or when the user asks to commit. Extends Conventional Commits with structured action lines in the commit body that preserve WHY code was written, not just WHAT changed.

Google Drive: Manage files, folders, and shared drives.

Google Drive: Manage files, folders, and shared drives.

A structured framework for dynamic and reflective problem-solving through sequential thoughts. Use when tackling complex, multi-step problems that require careful analysis, revision of assumptions, or exploration of alternative approaches. Ideal for algorithm optimization, architectural decisions, debugging complex issues, or any task where initial understanding may need to evolve.

\<task_skill_guides>

Persistent task memory for AI agents across sessions

Patterns for autonomous project execution with minimal human intervention. Use this skill when executing well-defined tasks autonomously, including validation strategies, stop conditions, and quality gates. Don't use when doing a single task interactively with the user, or when the project lacks a tasks document.

Essential reference for working in any Kotlin Multiplatform (KMP) project. Use whenever developing, building, or debugging a KMP app or library. Covers expect/actual patterns, source set hierarchy, file naming conventions, platform-specific Gradle task naming (compilation, linking, testing), and multiplatform dependency configuration.

Executes unattended batch processing of all pending tasks with autonomous decision-making. Use when running all tasks automatically, batch processing without supervision, completing entire feature backlog, or working on a specific task by ID. Triggers on 'run all tasks', 'complete all features', 'batch processing', 'unattended mode', 'auto-complete tasks', 'run feature'.

Execute a single task with Pathfinder/Builder/Inspector crew. Self-fetches work from Beads.

Stacking the Bricks reviewer — Amy Hoy & Alex Hillman persona for reviewing business decisions, pitches, emails, copy, and product strategy. Use when reviewing sales copy, marketing emails, business plans, product pitches, or any entrepreneurial decision. Triggers on: 'review this pitch', 'is this copy good', 'STB review', 'Amy Hoy', 'stacking the bricks', 'review my email', 'should I build this', 'sales safari', or any request for brutally honest business/marketing feedback.

Develops and troubleshoots dbt incremental models. Use when working with incremental materialization for: (1) Creating new incremental models (choosing strategy, unique_key, partition) (2) Task mentions "incremental", "append", "merge", "upsert", or "late arriving data" (3) Troubleshooting incremental failures (merge errors, partition pruning, schema drift) (4) Optimizing incremental performance or deciding table vs incremental Guides through strategy selection, handles common incremental gotchas.

This skill should be used when finding, tracing, or understanding code in a repository with SymDex available. Trigger it for requests like "where is this defined?", "who calls this?", "what route handles this path?", "show me the file outline", "search this codebase by intent", or any task that would otherwise rely on broad Read/Grep/Glob exploration.

Use when interacting with Gmail via the agentio CLI - list, read, search, send, draft, reply, archive, mark, attachments, export.

Convert PRDs to beads for ralph-tui execution. Creates an epic with child beads for each user story. Use when you have a PRD and want to use ralph-tui with beads as the task source. Triggers on: create beads, convert prd to beads, beads for ralph, ralph beads.

Manage agentapi-proxy SlackBots for automated session creation from Slack events. Use when you need to: (1) Create SlackBot configurations, (2) Update SlackBot settings, (3) List existing SlackBots, (4) Delete SlackBots, (5) Configure channel filters and message templates. SlackBots use Socket Mode (WebSocket) to receive Slack events and automatically create sessions based on configured templates.

Send emails via CLI. Use when the user asks to send an email, compose a message, or needs email functionality. Supports AgentMail, Google Workspace, Proton Mail, and generic SMTP.

Google Classroom: Manage classes, rosters, and coursework.

Google Classroom: Manage classes, rosters, and coursework.

Generate compelling invitation emails for training programs, workshops, or events. Use when user asks to "write class invitation email", "create training invitation", "generate mass email for training", or mentions "course promotion email".

This skill should be used when the user asks to "add a background job", "process async", "schedule a task", "retry failed jobs", "add email sending", "run this later", "add a cron job", "unique jobs", "batch process", or mentions Oban, Oban Pro, workflows, job queues, cascades, grafting, recorded values, job args, or troubleshooting job failures.

This skill should be used when the user asks to "add a background job", "process async", "schedule a task", "retry failed jobs", "add email sending", "run this later", "add a cron job", "unique jobs", "batch process", or mentions Oban, Oban Pro, workflows, job queues, cascades, grafting, recorded values, job args, or troubleshooting job failures.

Handle email tasks (checking inbox, drafting replies, managing threads, adding events to calendar). Use when working with emails to prevent common mistakes like broken threading or missing recipients.

Create or continue PLAN.md for the current branch. Use when starting a new feature, bug fix, refactoring, or any task that benefits from upfront planning. Suggest this when user is on a feature branch (not main/master) without an existing PLAN.md.

Create a new worktrunk worktree (optionally in another repo) and switch this session's working directory into it. Use when launching a session that should work in its own worktree (e.g. `/wt-switch-create my-branch -- <task>`, or `/wt-switch-create my-branch ~/workspace/other-repo -- <task>`), or mid-session to move work into a fresh branch.

Configure Slack integration for Cyrus — create a Slack app from manifest, then guide the user to save credentials.

Searches journal for past work related to current task, finding relevant context, solutions, and decisions

Google People: Manage contacts and profiles.

Query project-specific knowledge for conventions, patterns, architecture decisions, gotchas, and domain context. Use when starting a new task, touching unfamiliar code, making architectural decisions, reviewing code patterns, or needing context about how things are done in this project.

Runs end-to-end B2B prospecting by chaining company discovery, contact search, email verification, and enrichment. Use when the user wants to build a prospect list, find and qualify leads, or run a full prospecting pipeline.

Use this skill when the task is clearly connected to the user's YouMind workspace, YouMind APIs, or the youmind CLI. It helps agents search, inspect, and call YouMind OpenAPI endpoints to work with boards, groups, YouMind files, picks, chats, and YouMind skills.

Activate when user mentions "clink codex" to provide guidance on delegating implementation tasks to clink codex as a junior developer. Use when assigning coding tasks, discussing task delegation, or working with clink codex for code implementation.

Auto-load Conductor project context when conductor/ directory exists. Use for any development task in a Conductor-managed project to ensure alignment with product goals, tech stack, and workflow methodology.

Access Google Workspace APIs (Gmail, Drive, Sheets, Docs) via oauth2l + curl.

Google Chat: Manage Chat spaces and messages.