Create and edit Obsidian Bases (.base files): Obsidian's native database layer for dynamic tables, card views, list views, filters, formulas, and summaries over vault notes. Triggers on: create a base, add a base file, obsidian bases, base view, filter notes, formula, database view, dynamic table, task tracker base, reading list base.

Run cold and warm outreach campaigns to find and engage potential customers or partners. Use when building a prospecting pipeline, writing cold emails or LinkedIn messages, identifying and qualifying leads, planning an outreach strategy, or scaling lead generation as a solopreneur. Covers lead identification, qualification frameworks, cold email writing, LinkedIn outreach, multi-touch sequences, and tracking. Trigger on "cold outreach", "prospecting", "find customers", "cold email", "LinkedIn outreach", "lead generation", "outreach strategy", "build a pipeline", "find clients".

Create implementation plan files with dependency analysis and parallel execution support. Breaks down complex features into multiple self-contained plans with proper dependency tracking. Use when user wants to create plans, break down features, or plan implementation.

Show overview of all plans and their current execution status from the file PROGRESS.md located in the plans/ folder. Displays progress bar, completed plans, in-progress plans, failed plans, and suggested next actions. Use when user asks about plan status, progress, what's done, what's left, or wants to see plan overview.

Analyzes a .NET 8 codebase and produces analysis findings for upgrading to .NET 10. Uses pm7y-ralph-planner to generate TASKS.md with validation requirements and learnings tracking for autonomous execution. Use when planning a .NET 10 upgrade.

When the user wants to optimize their App Store listing for seasonal events, holidays, or trending moments — including keyword opportunities, metadata updates, screenshot theming, and timing strategy. Use when the user mentions "seasonal", "holiday", "Christmas", "New Year", "Valentine's Day", "summer", "back to school", "seasonal keywords", "trending now", "limited time", or wants to capitalize on a calendar event. For general keyword research, see keyword-research. For full metadata rewrites, see metadata-optimization.

Use when delegating a task to Codex CLI with session persistence across turns.

This skill should be used when the user asks to "ship", "ship it", "commit and create PR with tasks", "commit push pr and register tasks", or wants to commit, push, create a pull request, AND register test plan items as tasks. This combines the commit-push-pr workflow with automatic task registration from PR checklists. Use this skill instead of commit-push-pr when the user wants test plan tracking. Usage: /ship

Create an automation that generates an async standup digest from Slack. Searches selected channels for messages since the previous workday, groups updates by project, highlights blockers and decisions, and posts a summary to a target channel.

Universal task dispatcher. Start, route, and execute any task through the development workflow (Steps 0-9). Invoke on every task — /task <description>, /task

Coordinate work across multiple agents using memory and Task tool for clean context and parallel execution

This skill should be used when the user asks to "save current task", "save progress", "create task from context", "task-save", "break down tasks", "decompose work", or wants to capture current work state as structured tasks with dependency ordering. Usage: /task-save [--cwd <path>] [query] --cwd: Cross-project handoff (records target directory in metadata for ClaudePanel.spoon).

Task decomposition expert for breaking technical specifications into atomic, implementable tasks with dependencies and priorities. Use when converting specs into actionable task lists for development teams.

Adaptive pre-planning exploration loop. Builds sufficient context before committing to a detailed plan. Use when: (1) brief is ambiguous or underspecified, (2) task touches unfamiliar code or libraries, (3) multiple valid approaches exist and the right one isn't obvious, (4) user says "thorough plan" or invokes /thorough-plan. NOT for trivial tasks where the path is obvious — triage will skip exploration in those cases.

This skill should be used when the user asks to "create a ticket", "add a task", "track an issue", "manage dependencies", "show blocked tickets", "list open tickets", "close a ticket", "add notes to a ticket", "link tickets", "query tickets", "what's ready to work on", "what's blocking", "break down an epic", or any task management operation using the `tk` CLI. Also triggers when the user mentions "tk", "ticket system", ".tickets", or asks about project task organization.

Use before any completion claim, success statement, or marking a task done. Triggers when about to say "Great!", "Perfect!", "Done", "All set", "Ready to commit", before creating a PR, before moving to the next task, or when code has changed since the last test run.

Use to spawn isolated worker processes for autonomous issue work. Uses Task tool with run_in_background for parallel execution and TaskOutput for monitoring. Pre-extracts context to minimize worker token usage.

INVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, and HITL interrupts.

This skill should be used when the user asks about "email", "mailers", "Action Mailer", "deliver_now", "deliver_later", "email templates", "attachments", "mail previews", "SMTP", "email configuration", "interceptors", or needs guidance on sending emails in Rails applications.

Merge task branch to base branch with linear history (works from task worktree)

Generate personalized cold email sequences (7-14 emails) with A/B test subject lines, follow-up timing recommendations, and integrated social proof. Creates multi-touch campaigns optimized for response rates. Use when users need outbound email campaigns, sales sequences, or lead generation emails.

Create clean conventional commits. Use when the user wants to commit changes, make a commit, save progress, or says "commit". Offers three message variants (short, descriptive, multi-line) with live preview, automatic task number detection from branch names, and conventional commit prefixes. Never adds Co-Authored-By lines.

Build and execute a content marketing strategy for a solopreneur business. Use when planning what content to create, deciding on content formats and channels, building a content calendar, measuring content performance, or systematizing content production. Covers audience research for content, content pillars, distribution strategy, repurposing workflows, and metrics. Trigger on "content strategy", "content marketing", "what content should I create", "content plan", "content calendar", "content ideas", "content distribution", "grow through content".

Advanced sub-skill for Dask focused on distributed system performance, memory management, and task graph optimization. Covers cluster tuning, efficient serialization, data skew mitigation, and dashboard-driven debugging.

This skill provides guidance on accessing session data efficiently in ultrawork. Covers JSON vs Markdown rules, token efficiency rationale, and common patterns. Required knowledge for all ultrawork agents (explorer, planner, worker, verifier, reviewer).

INVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, and HITL interrupts.

Joel's private egghead.io Slack integration — channel taxonomy, token config, passive monitoring, and message intelligence pipeline.

Manage your GitLab to-do list from the CLI, including listing pending or completed items and marking items done. Use when reviewing assigned or mentioned work from GitLab notifications, clearing to-dos, or scripting to-do triage. Triggers on todo, to-do, notification list, mark done, assigned items, mentioned items.

Unified Google Workspace integration for managing email, calendar, files, and communication across multiple accounts

Google Drive: Manage files, folders, and shared drives via the gws CLI. Use when the user asks to "upload file", "share file", "list drive files", "search drive", "download from drive", or any Google Drive operation.

Creates Jira tasks following Prowler's standard format. Trigger: When user asks to create a Jira task, ticket, or issue.

Decide which decisions to make autonomously and which to surface during a multi-decision task, so the user is interrupted only for genuine forks and never blindsided by a silent wrong turn. Trigger whenever the user says "meaningful-fork triage", "use confidence gating" / "confidence-gate this", "only surface the real forks", "don't hold my hand", or "minimize friction" — or kicks off a long multi-step task (authoring a doc, large refactor, multi-step implementation, bulk config edits) and signals they want fewer interruptions. Also trigger at the start of any delegated task where the user wants their attention spent only on consequential, uncertain choices. Do NOT trigger when the user wants to approve every step, for a single-decision task where there is nothing to triage, or when the user only wants existing questions restructured one-at-a-time (that is q-interactive, not triage).

Use this skill whenever writing, modifying, or running .phpt test files with Nette Tester. Invoke for any task involving Tester\Assert methods (Assert::same, Assert::match, Assert::exception, etc.), test bootstrap setup, vendor/bin/tester commands, or debugging failing test output (.expected/.actual files). Also use when the user needs to write tests for a Nette project and asks about test structure, the test() function, testException(), or assertion methods. This skill is specifically for Nette Tester – do not use for PHPUnit, Pest, Jest, Vitest, or other testing frameworks, and do not use for general PHP testing without Nette context.

Run the autonomous control plane loop — orient, identify, act, verify, update, introspect. Use for /operate, "run the loop", "what needs doing". NOT for single-task work — use specific skills instead.

Use when starting any implementation task, feature request, bug fix, or refactoring work. Triggers on /plan command, before any code is written, when requirements need structured analysis, or when transitioning from brainstorming to implementation. Forces question-asking, approach comparison, and explicit approval before any code.

Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls. Now with automatic session recovery after /clear.

Manage Power BI table partitions, named expressions (M/Power Query data sources), and calendar table configuration using pbi-cli. Invoke this skill whenever the user mentions "partitions", "data sources", "M expressions", "Power Query", "incremental refresh", "named expressions", "connection parameters", or wants to configure how tables load data. For broader modeling tasks (measures, relationships, hierarchies), see power-bi-modeling instead.

Manage projects, tasks, and priorities effectively as a solopreneur. Use when organizing work, tracking progress, managing deadlines, coordinating with contractors or clients, or building project management systems. Covers task management methods, prioritization frameworks, project planning templates, tool selection, and personal productivity workflows. Trigger on "project management", "manage my work", "organize tasks", "project planning", "task management", "prioritization", "stay organized".

Convert PRDs to prd.json format for ralph-tui execution. Creates JSON task files with user stories, acceptance criteria, and dependencies. Triggers on: create prd.json, convert to json, ralph json, create json tasks.

Use when a task already has research and plan sections and the plan needs adversarial review before implementation

Use when building anything non-trivial. Enforces a spec → plan → execute → verify loop that prevents "looks right" failures. Creates spec.md, todo.md, and decisions.md before writing code.

Parses a spec document and auto-generates a complete task state with scored, dependency-validated, and phase-organized tasks

Use when an answer arrives too fast on a high-stakes or unfamiliar task. Force one explicit verification pass before committing instead of shipping the first plausible answer.

Manages todo.txt tasks using topydo CLI. Adds, lists, completes, prioritizes, tags, and organizes tasks with dependencies, due dates, recurrence, and projects. Use for any task management, todo lists, or when the user mentions tasks, todos, or todo.txt. Requires Python 3 and pip. Works on macOS, Linux, and Windows.

Diagram user flows for a task or journey. Produces flow specification (actors, entry point, steps, decision points, outcomes), flow types (happy path / edge cases / error recovery / abandonment), per-step metadata (screen / action / system response / data / conditions), and instrumented measurement points.

Use when starting any conversation, receiving a new task, or when uncertain which skill applies - establishes how to find and use all 64 toolkit skills, requiring Skill tool invocation before ANY response including clarifying questions

Use when about to claim work is complete, fixed, or passing, before committing, creating PRs, or moving to the next task

This skill should be used when the user asks to "work with beads tasks", "create a beads ticket", "update beads status", "read task comments", "manage dependencies", "sync beads", "use bd commands", or needs guidance on beads task management workflows. Provides comprehensive beads CLI usage and workflow patterns.

This skill should be used when the user asks to "find my open action items", "show my tasks", "what do I need to do", "list my todos", "find tasks assigned to me", "find tasks for [name]", or "what are my open items". Retrieves all open action items from meeting notes (tasks tagged with a person's name) and daily notes (unchecked checkboxes) across the Obsidian vault.

Implement TODO.md items via isolated subagents, then adversarially verify correctness. Drives a phased loop that implements one checkbox at a time, runs independent lint/test/review subagents, handles human verification, and commits per subsection.

Educator peer review management for Canvas LMS. Tracks completion rates, analyzes comment quality, flags problematic reviews, sends targeted reminders, and generates instructor-ready reports. Trigger phrases include "peer review status", "how are peer reviews going", "who hasn't reviewed", "review quality", or any peer review follow-up task.

Git commit workflow pipeline: atomic unit identification, commit ordering, quality gates, message validation, and post-commit verification. Invoke whenever task involves any interaction with git commits — committing changes, staging work, splitting diffs into atomic units, or preparing work for version control.

Draft TypeScript-compliant code skeleton with TODO placeholders. Use when starting new implementations, creating code scaffolds, or preparing test structure for TDD.

Implement a spec-kit feature phase. Executes tasks one at a time, committing after each, with diff verification before closing. Use --all to continue through subsequent phases. For standalone bug/task beads outside a feature plan, use /fix instead.

/learn - Extract Reusable Patterns. After completing a complex task (5+ tool calls with cross-scenario reuse potential), suggest "/learn" to the user. When invoked, analyze the current task's approach and distill it into a reusable skill or improve an existing one. Also use when user says "save this as a skill", "remember this approach", or "this is reusable".

Generates offer code distribution strategies and configuration guides for subscription and IAP promotions — including partner campaigns, influencer programs, and email re-engagement. Use when setting up offer codes for distribution.

Use this skill when decomposing complex work into structured tasks before implementation. Activates on mentions of write a plan, create a plan, break this down, task decomposition, implementation plan, what are the steps, plan the work, spec this out, or decompose this feature.

Execute multiple plans with automatic dependency resolution and parallel execution. Builds dependency graph, runs independent plans simultaneously, handles sequential dependencies, and applies configuration options. Use when user wants to run multiple plans, batch execute plans, or execute all plans for a feature.

Execute a single plan file with full dependency validation, configuration options (auto-commit, README update, CLAUDE.md update), conflict detection, and PROGRESS.md tracking. Blocks execution if dependencies are not met. Use when user wants to run a specific plan, execute a plan file, or implement a single plan.

Background jobs, long-running processes, and task management

This skill should be used when the user asks about "Rake", "rake tasks", "Rakefile", "task dependencies", "rake namespace", "rake desc", "rake file tasks", "invoke", "execute", "task arguments", or needs guidance on creating and managing Rake tasks.

Activate autonomous Ralph Wiggum loop mode for iterative task completion. Use when you have a well-defined task with clear completion criteria that benefits from persistent, autonomous execution.

Use when asked to draft, write, or format a message for Slack. Produces raw text the user can copy into Slack, then format with Cmd+Shift+F.

Initializes an AI development session by reading workflow guides, developer identity, git status, active tasks, and project guidelines from .trellis/. Classifies incoming tasks and routes to brainstorm, direct edit, or task workflow. Use when beginning a new coding session, resuming work, starting a new task, or re-establishing project context.

Project status report generation from git history, task context, and milestone tracking. Use when creating weekly updates, sprint reviews, stakeholder reports, or project dashboards.

Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or dependencies - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates

Transform overwhelming development tasks into manageable units. This skill should be used when the user says 'task too big', 'can't estimate', 'overwhelmed by scope', 'where do I start', 'epic needs breakdown', or has dependency problems. Keywords: decomposition, breakdown, estimate, scope, INVEST, vertical slice, spike, dependencies.

Implement engineering tasks from task specifications using TDD in isolated git worktrees. Use when user wants to implement a task from docs/tasks/, build a feature from TASKS.md, code a specific epic/story/task, or says "implement task X", "build task X", "work on task X". Reads task specs, PRD, and architecture docs for context, creates a feature branch worktree, writes tests first, implements code, verifies coverage, updates docs, and creates a PR.

Use when breaking work into discrete steps, tracking progress through multi-step implementations, or managing implementation task lists. Triggers when an approved plan needs to be converted into tracked tasks, when progress reporting is needed during execution, or when checkpoint reviews are required between task batches.

Reverse-engineer a company's tech stack from public signals — job listings, StackShare, GitHub, engineering blog, and their live website. Use this skill when a user asks "what tech does Stripe use", "what's Linear's stack", "what does Notion run on", "reverse engineer [company]'s tech stack", "what framework does [company] use", "how is [company] built", "what languages does [company] hire for", or any request to figure out what technology a company uses under the hood.

This skill should be run only when the user explicitly invokes it. Orchestrates end-to-end task implementation — understands the task, assesses complexity, implements directly or via a team of subagents for complex work, and always finishes with a code-polish pass.

Proactive git worktree orchestration -- detects WIP state (uncommitted changes, stashes, unpushed commits) and offers to isolate work into worktrees. MUST activate BEFORE any implementation task (add, create, build, implement, develop, make, fix, refactor) when the working directory has uncommitted changes or stashes. Also provides dashboard, context recovery, multi-worktree creation, cleanup advisor, and conflict early warning across parallel development sessions. Triggers: any implementation request when WIP exists, "show my worktrees", "what am I working on", "help me manage parallel tasks", "worktree status", "coordinate my work". TRIGGER WHEN: before any implementation task (add, create, build, fix, refactor) when the working directory has uncommitted changes, stashes, or unpushed commits; when the user asks about worktrees, branches, or parallel development. DO NOT TRIGGER WHEN: the repo state is clean and the user is doing a single-file read-only task.

Use when there is a spec or requirements for a multi-step task, before touching code

Use when you have a spec or requirements for a multi-step task, before touching code.

Surface in-task-collaboration protocols when the user describes an AI workflow informally — URL-as-entity-reference, PR-comment threads as session memory. Trigger when the user names entities by colloquial label instead of stable URL, asks "how should I structure this for Claude", or describes a multi-step Claude workflow without a durable handle. Apply reactively, not as a checklist.

Annotate Airflow tasks with data lineage using inlets and outlets. Use when the user wants to add lineage metadata to tasks, specify input/output datasets, or enable lineage tracking for operators without built-in OpenLineage extraction.

Plan and execute parallel, repeatable migrations across code, docs, research artifacts, ops configs, or mixed task sets.

Discussion forum facilitator for Canvas LMS. Helps students and educators browse, read, reply to, and create discussion posts. Trigger phrases include "discussion posts", "reply to students", "check discussions", "forum participation", "post a discussion", or any discussion-related Canvas task.

Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise. This skill should be used when code-quality checks pass but the code would benefit from structural cleanup — deduplication, branching simplification, naming improvements, or dead-code removal. Invoked as a subagent from /code-quality or directly via the Task tool.

Use when creating a new Jira ticket in a regular project (CRD, CO, etc.) — the standard Story workflow with summary, markdown description, priority, and optional story points. Triggers on phrases like "create a story", "open an issue", "new CRD ticket", "new CO story", "file a ticket for X", "scaffold a new ticket", or any conversational request to shape a fresh Jira issue. Default issue type is Story (not Task — Task has an incomplete workflow). Do NOT use this for CHANGE-project CAB tickets — those have a different field layout and belong to the `/create-change-issue` skill.

Plans and implements data retention policies with archival strategies, compliance requirements, automated cleanup jobs, and cold storage migration. Use for "data retention", "data archival", "GDPR compliance", or "storage optimization".

This skill should be used when implementing features from a PRD spec, tracking implementation progress, or resuming work across sessions. Covers Dex task management for PRD story execution, daily workflows, and skill auto-loading.

Email header injection and spoofing playbook. Use when testing contact forms, email APIs, password reset flows, or any feature that constructs SMTP messages with user-controlled fields. Covers CRLF injection in headers, SPF/DKIM/DMARC bypass, and phishing amplification.

Executes an approved implementation plan produced by the planning skill. Creates a git worktree, critically reviews the plan for blockers, tracks tasks via TodoWrite, and delegates each task to the right subagent one at a time. Runs code-reviewer after every task and a final holistic review before creating a PR. Use after /planning produces an approved plan.md.

Execution discipline that translates plans into tracked tasks with orchestration and verification loops. Use when driving a plan through cortex’s task system, coordinating workstreams across agents, or ensuring every plan item is tracked, executed, and verified.

Stress-test financial plans across scenarios (bull/bear/base), sensitivity tables, and Monte Carlo-style analysis. Use when evaluating financial assumptions, modeling risk scenarios, or building scenario-based financial plans.

Manually trigger plan-sync to update downstream task specs after implementation drift. Use when code changes outpace specs.

Google Classroom: Manage classes, rosters, and coursework.

Quick install of the Google Workspace CLI (gws) on an additional machine using existing OAuth credentials. Requires client_secret.json from a previous gws-setup. Use whenever the user wants to install gws on a new computer, reinstall after a fresh OS, configure a second workstation, or says 'install gws', 'gws on new machine', 'set up gws again'.

Google People: Manage contacts and profiles.

Start a new intent with spec-driven development. Use when the user wants to begin working on a new feature, bug fix, or task and needs to document the problem, solution, and requirements.

Creates Jira epics for large features following Prowler's standard format. Trigger: When user asks to create an epic, large feature, or multi-task initiative.

Execute the next task from the kanban board. Use when the user says "kanban", "/kanban", "next task", "what's the next task", or "pick up work". Picks up the next ready task from the board and drives it through doing to review.

Guidelines for creating responsive email templates using MJML framework with .NET Razor syntax integration. Use when building responsive email templates in .NET applications, integrating MJML with Razor views, or creating email layouts that work across email clients.

Use during all development - no TODOs, no FIXMEs, no "we'll add this later"; do it now or get explicit deferral permission

Configure OAuth providers (Google, Apple, Microsoft, Facebook, GitHub, etc.) to work with portless local dev URLs. Use when setting up OAuth redirect URIs, fixing "redirect_uri_mismatch" or "invalid redirect" errors, configuring sign-in providers for local development, or when a provider rejects .localhost subdomains. Triggers include "OAuth not working with portless", "redirect URI mismatch", "Google/Apple/Microsoft sign-in fails locally", "configure OAuth for local dev", or any task involving OAuth callback URLs with portless domains.