Execute an autonomous development loop that picks one task per iteration, implements it, verifies it, and commits the result — each iteration in a fresh context window. Use when user runs /ralph, mentions "ralph loop", "autonomous loop", "builder verifier", "run tasks automatically", "iterate on tasks", "develop autonomously", or wants an automated build-verify-commit cycle with task tracking.

Query Salesforce data and manage sales pipelines using the `sf` CLI. Use for SOQL queries (simple to complex), opportunity pipeline analysis, forecast reporting, data exports, schema exploration, and CRM data operations. Also use for executive workflows like looking up deals by name, finding contact info to email prospects, preparing pipeline reviews, and cross-referencing CRM data with other tools. Triggers on Salesforce, SOQL, pipeline, opportunity, forecast, CRM data, deal lookup, prospect email, account info, or sf CLI questions.

This skill should be used when planning and tracking complex feature implementations that require systematic task decomposition. Use this skill to break down large features into manageable, well-documented tasks with clear dependencies, action items, and success criteria. The skill provides a structured template and methodology for iterative planning and tracking throughout implementation.

Orchestrate multiple worker agents to implement groomed tasks. Use when multiple ready tasks need implementation, when you want autonomous multi-task execution, or when coordinating batch development work. Keywords: coordinator, orchestrator, multi-task, parallel, workers, batch, autonomous.

Write B2B cold emails and follow-up sequences that get replies. Use when the user wants to write cold outreach emails, prospecting emails, cold email campaigns, sales development emails, or SDR emails. Also use when the user mentions "cold outreach," "prospecting email," "outbound email," "email to leads," "reach out to prospects," "sales email," "follow-up email sequence," "nobody's replying to my emails," or "how do I write a cold email." Covers subject lines, opening lines, body copy, CTAs, personalization, and multi-touch follow-up sequences. For warm/lifecycle email sequences, see emails. For sales collateral beyond emails, see sales-enablement.

Estimate the development cost of a codebase, branch diff, or single commit by combining repo metrics, category-based productivity rates, organizational overhead, and optional Claude ROI. Runs as a forked analysis workflow so the estimate has separate reasoning budget and stays isolated from the main task flow.

Plans development tasks through codebase exploration, exhaustive user interviews, and structured file-based plans. Use when tackling a feature, bug fix, refactor, or any task that benefits from upfront planning. Generates plan files in .agents/plans/ for later execution with /execute-plan.

Load a sharded, on-disk dataset (sharded .npy, Parquet/Arrow, raw binary, sharded HDF5, custom layouts) into a distributed cuPyNumeric ndarray via a manual partition + leaf @task launch with CPU/OMP/GPU variants. Use when no single-call loader fits, including when per-shard row counts differ across files. Prefer cupynumeric.load or legate.io.hdf5.from_file when they apply.

Formula 1 data — race schedules, results, lap timing, driver and team info. Powered by the FastF1 library. Covers F1 sessions, qualifying, practice, race results, sector times, tire strategy. Use when: user asks about F1 race results, qualifying, lap times, driver stats, team info, the F1 calendar, or Formula 1 data. Don't use when: user asks about other motorsports (MotoGP, NASCAR, IndyCar, WEC, Formula E). Don't use for F1 betting odds or predictions — use kalshi or polymarket instead. Don't use for F1 news articles — use sports-news instead.

Access local system resources including Calendar on macOS and Windows. Use this skill when you need to manage user's schedule directly on their device.

When the user wants to find, qualify, and build a list of prospects to reach out to — across B2B SaaS, general B2B, or local small businesses. Also use when the user mentions "prospecting," "build a prospect list," "find prospects," "find leads," "lead gen list," "find SaaS companies that," "find B2B companies," "find local businesses," "ICP-fit accounts," "who should we go after," "outbound list," "target account list," "find clients near me," "businesses without websites," "prospect research," or "qualified leads." Use this for the list-building and qualification phase. For writing the outbound copy after the list is built, see cold-email. For deep competitive research on specific accounts, see competitor-profiling.

Monitor SEC EDGAR for new filings and get Telegram/Slack summaries via Clawdbot. Use when setting up SEC filing alerts, adding/removing tickers to monitor, configuring form types, starting/stopping the watcher, or troubleshooting filing notifications.

DataWorks Operations Center assistant for task and workflow operations, alert rule creation and management. Covers troubleshooting, failure recovery, baseline assurance, monitoring and alerting. Supports periodic, manual, and triggered tasks/workflows (excludes real-time/streaming tasks). Uses aliyun CLI to call dataworks-public OpenAPI (2024-05-18). Trigger keywords: query task, task instance, instance log, workflow, workflow instance, alert rule, operations center, task failure, instance status, upstream/downstream dependency, rerun, monitoring alert, custom monitoring, alert rule, task instance, workflow instance, operation log, baseline assurance, failure recovery, DataWorks operations. Do NOT trigger: data source management, compute resources, resource groups, data development, MaxCompute table management, ECS/RDS/OSS operations, workspace member management, data quality, data lineage, data preview.

Grafana dashboard authoring: JSON model (Classic and V2), panel types and selection, standard options, thresholds, value mappings, field overrides, transformations, variables (query/custom/interval/filter), repeating panels and rows, annotations, dashboard/panel/data links, and library panels. Invoke whenever task involves any interaction with Grafana dashboards — creating, editing, reviewing, debugging, or understanding dashboard configuration.

Plan yield farming and CAKE staking on PancakeSwap. Use when user says "farm on pancakeswap", "stake CAKE", "unstake CAKE", "stake LP", "unstake LP", "yield farming", "syrup pool", "pancakeswap farm", "earn CAKE", "farm APR", "harvest rewards", "deposit LP", "withdraw LP", or describes wanting to stake, unstake, or earn yield on PancakeSwap. Do NOT use this skill when the user has a token pair and asks how to earn yield or best profit with those tokens (prefer liquidity-planner instead).

Use when analyzing macOS apps for optimization opportunities, improving memory/RAM usage, reducing memory leaks, optimizing SwiftUI performance, or analyzing Swift code for efficiency. Load for any macOS app performance analysis or memory optimization task.

Mise configuration patterns, task definitions, hooks, presets, and language-specific setup guidance for dev environment management and project tooling.

Plans execution for one task from docs/<ISSUE_SLUG>-tasks.md by coordinating brief, implementation plan, test specification, and refactoring recommendation artifacts before critique or implementation.

Plans execution for one task from docs/<TICKET_KEY>-tasks.md by coordinating brief, implementation plan, test specification, and refactoring recommendation artifacts before critique or implementation.

Use when sending transactional or broadcast emails through Postmark — single sends, batch (up to 500), bulk, or template-based emails with support for attachments, tracking, and message streams.

Guide technical communication for software developers. Covers email structure, team messaging etiquette, meeting agendas, and adapting messages for technical vs non-technical audiences. Use when drafting professional messages, preparing meeting communications, or improving written communication.

Guide technical communication for software developers. Covers email structure, team messaging etiquette, meeting agendas, and adapting messages for technical vs non-technical audiences. Use when drafting professional messages, preparing meeting communications, or improving written communication.

Guides comprehensive software project planning including task breakdown, estimation, sprint planning, backlog management, resource allocation, milestone tracking, and risk management. Creates user stories, acceptance criteria, project roadmaps, and work breakdown structures. Use when planning software projects, organizing sprints, breaking down features into tasks, estimating effort, managing backlogs, or when users mention "project planning", "sprint planning", "task breakdown", "roadmap", "backlog management", "user stories", or "project estimation".

Maintain portfolio allocations over time using calendar-based, threshold-based, and tax-efficient rebalancing strategies. Use when the user asks about when to rebalance, rebalancing bands, transaction cost trade-offs, tax-efficient rebalancing, or the rebalancing premium. Also trigger when users mention 'my portfolio drifted', 'how often should I rebalance', 'rebalancing across taxable and IRA accounts', 'volatility harvesting', 'buy low sell high automatically', or ask whether to use cash flows to rebalance.

Use when implementing iOS 17+ SwiftUI patterns: @Observable/@Bindable, MVVM architecture, NavigationStack, lazy loading, UIKit interop, accessibility (VoiceOver/Dynamic Type), async operations (.task/.refreshable), or migrating from ObservableObject/@StateObject.

This skill should be used when the user wants to learn a new domain from scratch using structured cognitive phases, or when they say "dln", "dln list", "dln reset [domain]", "learn [domain]", "teach me [domain] from zero", "cold-start [domain]", "start learning [domain]", "continue learning [domain]", "resume [domain]", "pick up [domain]", "review [domain]", "dln exam [domain] by [date]", "dln exam [domain] status", "dln mock [domain]", "dln cram [N]d [domain]", "exam mode", "exam prep", or reference the Dot-Linear-Network framework. It orchestrates three phase skills (dln-dot, dln-linear, dln-network) based on the learner's current phase stored in a Notion database, routing them to the appropriate learning protocol for their level of understanding. Also handles exam mode: metadata capture, Blueprint creation, priority scoring, time-horizon presets, and exam lifecycle management.

Phase 3 of the /ds workflow — analysis task execution. Invoked by the ds-plan chain; not user-invocable.

This skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space). It creates a JSON file with resource information and strategic recommendations that inform computational approach decisions such as whether to use parallel processing (joblib, multiprocessing), out-of-core computing (Dask, Zarr), GPU acceleration (PyTorch, JAX), or memory-efficient strategies. Use this skill before running analyses, training models, processing large datasets, or any task where resource constraints matter.

This skill should be used when searching, fetching, or downloading emails from Gmail. Use for queries like "search Gmail for...", "find emails from John", "show unread emails", "emails about project X", or "download attachment from email".

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.

Create a safe implementation plan as both markdown and JSON DAG artifacts. Challenge scope with the user first, explore real code before decomposing, then emit atomic TASK-NNN entries with explicit dependencies, write scope, validation, and assigned agents. Use when the user asks to plan, decompose, or break work into execution-ready tasks.

Evaluate and respond to inbound PostHog sales leads from Salesforce. Use this skill when any PostHog TAE needs to triage an inbound lead — deciding whether to qualify for a call, route to self-serve, or disqualify — and then draft an appropriate response email. Checks Vitally for existing account context before qualifying. Triggers on "respond to this lead", "triage this inbound", "write a response to this lead", "disposition this lead", "evaluate this Salesforce lead", or any request involving an inbound sales inquiry that needs qualification and a reply. Also trigger when a TAE pastes or describes lead details and asks what to do with them.

Reviewer-only refinement for Jira tickets, Jira epics, GitHub issues, and GitHub epic-style parent issues. Use when the user asks to triage, refine, assess readiness, review acceptance criteria, find blockers, validate technical claims, suggest splits, recommend subtasks, or draft/post the single allowed refinement comment while leaving tracker metadata, issue content, and existing comments unchanged.

Use when coordinating complex tasks with orchestration, delegation, or parallel workstreams - provides structured workflows for orchestrate:brainstorm, orchestrate:spawn, and orchestrate:task.

Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims, heuristics, and pivots, and writing them into the ara/ directory with user-vs-AI provenance tags. Use as a session epilogue — never during execution — to maintain a faithful, auditable trace of how a research project actually evolved.

Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims, heuristics, and pivots, and writing them into the ara/ directory with user-vs-AI provenance tags. Use as a session epilogue — never during execution — to maintain a faithful, auditable trace of how a research project actually evolved.

Recommends production-ready Golang libraries and frameworks. Apply when the user explicitly asks for library suggestions, wants to compare alternatives, needs to choose a library for a specific task, or when a new dependency is being added to the project.

Manages Google Docs, Sheets, and Slides through the Docs, Sheets, and Slides APIs. Create, read, and edit documents, spreadsheets, and presentations programmatically. Format content, manage collaboration, extract data, and automate document workflows. Use when working with Google Workspace documents, editing content, extracting data, or automating document creation.

Capture an idea, task, or issue that surfaces during a Kata session as a structured issue for later work. This skill creates markdown issue files in the .planning/issues/open directory with relevant metadata and content extracted from the conversation. Triggers include "add issue", "capture issue", "new issue", "create issue", "log issue", "file issue", "add todo" (deprecated), "capture todo" (deprecated), "new todo" (deprecated).

Prometheus instrumentation discipline: right metric type, right name, right labels. Invoke whenever task involves any interaction with Prometheus metrics — instrumenting application code, writing PromQL queries, defining alerting or recording rules, choosing metric types, managing label cardinality, building exporters, or reviewing monitoring configuration.

Comprehensive QA toolkit for creating test plans, manual test cases, automated Playwright tests, regression suites, and bug reports. Uses safe, non-executable templates following skill best practices. Ideal for QA Automation engineers.

StatsD metric instrumentation: push metrics over UDP, choose the right metric type, name consistently. Invoke whenever task involves any interaction with StatsD metrics — emitting counters, gauges, timers, histograms, sets, or distributions; configuring DogStatsD tags; tuning sampling rates; or integrating with Graphite, Prometheus, or Telegraf backends.

Perform bidirectional synchronization between local markdown files and Notion pages via the `notion-sync` CLI, with conflict resolution and integrity verification. Use when syncing documentation to Notion, pulling Notion pages to local files, or resolving conflicts between local and remote versions.

Use this skill when working with State Tree, StateTree, UStateTree, state machine, StateTreeTask, StateTreeCondition, StateTreeEvaluator, StateTreeSchema, AI State Tree, Mass StateTree, FStateTreeExecutionContext, or data-driven state logic in Unreal Engine. See references/state-tree-patterns.md for task/condition/evaluator templates and references/state-tree-mass-integration.md for Mass Entity integration.

This skill should be used when the user asks to "write TypeScript", "create a TS module", "implement a TypeScript class", "model this type", "add types", "type this function", "use generics", "use branded types", "use discriminated unions", "fix this TypeScript", "refactor this TS code", "use modern TypeScript", "configure tsconfig", or any task involving writing, reviewing, or improving TypeScript code. Provides best practices for type modeling, modern language features (TypeScript 5.5-5.8), error handling, module patterns, and project configuration. This skill covers TypeScript (.ts/.tsx) files, NOT plain JavaScript with JSDoc.

Systematic framework for extracting actionable items from documents and organizing them into prioritized, trackable checklists. Use when converting reports, meeting notes, audits, or any document with embedded action items into structured TODO lists.

Grafana unified alerting: rule types, evaluation lifecycle, state transitions, notification policies, contact points, silences, mute timings, recording rules, and alert/notification templates. Invoke whenever task involves any interaction with Grafana alerting — creating or editing alert rules, configuring contact points and routing, templating annotations or notifications, debugging alert state, or reviewing alerting configuration.

Use when user requests autonomous operation across multiple issues. Orchestrates parallel workers using Task tool, monitors with TaskOutput, handles SLEEP/WAKE cycles, and works until scope is complete without user intervention.

When the user wants to reduce churn, build cancellation flows, set up save offers, recover failed payments, or implement retention strategies. Also use when the user mentions 'churn,' 'cancel flow,' 'offboarding,' 'save offer,' 'dunning,' 'failed payment recovery,' 'win-back,' 'retention,' 'exit survey,' 'pause subscription,' 'involuntary churn,' 'people keep canceling,' 'churn rate is too high,' 'how do I keep users,' or 'customers are leaving.' Use this whenever someone is losing subscribers or wants to build systems to prevent it. For post-cancel win-back email sequences, see emails. For in-app upgrade paywalls, see paywalls.

Execute TDD task pairs autonomously with RED-GREEN-REFACTOR verification. Orchestrates wave-based execution with strategic parallelism, routing TDD tasks to tdd-executor agents and non-TDD tasks to standard task-executor. Use when user says "execute tdd tasks", "run tdd tasks", "start tdd execution", or wants to execute TDD-paired tasks from create-tdd-tasks.

Execute a Flow spec or task systematically with git setup, task tracking, quality checks, and commit workflow. Use when implementing a plan or working through a spec. Triggers on /flow-next:work with Flow IDs (fn-1-add-oauth, fn-1-add-oauth.2, or legacy fn-1, fn-1.2, fn-1-xxx, fn-1-xxx.2).

Operate the joelclaw gateway daemon — the always-on pi session that receives events, notifications, and messages. Use the joelclaw CLI for ALL gateway operations. Use when: 'restart gateway', 'gateway status', 'is gateway healthy', 'push to gateway', 'gateway not responding', 'telegram not working', 'messages not going through', 'gateway stuck', 'gateway debug', 'check gateway', 'drain queue', 'test gateway', 'stream events', or any task involving the gateway daemon.

Core JavaScript language conventions, idioms, and modern practices. Invoke whenever task involves any interaction with JavaScript code — writing, reviewing, refactoring, debugging, or understanding .js/.jsx files and JavaScript projects.

This skill should be used when the user asks to "provide liquidity", "create LP position", "add liquidity to pool", "become a liquidity provider", "create v3 position", "create v4 position", "concentrated liquidity", "set price range", or mentions providing liquidity, LP positions, or liquidity pools on Uniswap. Generates deep links to create positions in the Uniswap interface.

Plan liquidity provision on PancakeSwap. Use when user says "add liquidity on pancakeswap", "provide liquidity", "LP on pancakeswap", or describes wanting to deposit tokens into liquidity pools without writing code. Also use when a user holds two tokens and asks how to earn yield, get best profit, or put tokens to work — especially on Solana or any chain where farming is unavailable.

VictoriaLogs LogsQL query language: filters (word, phrase, prefix, regexp, range, IPv4 range, exact, stream, time), pipe operators (stats, sort, fields, format, extract, unpack_json, unpack_logfmt, math, limit, top, uniq), stats functions, log stream filtering with Prometheus-style label selectors, field extraction, and performance patterns. Invoke whenever task involves any interaction with LogsQL — writing, debugging, optimizing, or reviewing VictoriaLogs queries.

Meta-cognitive reasoning specialist for evidence-based analysis, hypothesis testing, and cognitive failure prevention. Use when conducting reviews, making assessments, debugging complex issues, or any task requiring rigorous analytical reasoning. Prevents premature conclusions, assumption-based errors, and pattern matching without verification.

Use when writing async/await code, enabling strict concurrency, fixing Sendable errors, migrating from completion handlers, managing shared state with actors, or using Task/TaskGroup for concurrency.

Break down large projects into dependency-aware tasks with progress tracking and visualization. This skill should be used when users want to plan complex implementations, create task breakdowns with dependencies, or visualize project structure.

Python patterns for system reliability — background jobs and task queues (Celery, async), resilience and recovery (retries, backoff, timeouts, circuit breakers via tenacity), and observability (structured logging via structlog, metrics, distributed tracing, golden signals). USE WHEN building async workers, queueing tasks, handling transient network/IO failures, instrumenting Python services for production, designing retry policies, configuring logging or tracing, or any combination of these system-reliability concerns. NOT FOR language idioms or type hygiene (use `writing-python`) or project setup and dependency management (use `uv`).

Orchestrate multiple code-writing agents in parallel when the work contains 3 or more genuinely independent build tasks. Use for execution lanes with disjoint write scope, clear task boundaries, and no dependency edges that would force sequencing.

Shell script conventions, defensive patterns, and correctness rules: strict mode, quoting, portability, error handling, and common pitfalls. Invoke whenever task involves any interaction with shell scripts — writing, reviewing, debugging, or understanding .sh, .bash, .zsh files.

templ templating: syntax, components, attributes, styling, and JavaScript integration. Invoke when task involves any interaction with templ — writing .templ files, creating components, composing templates, testing rendered output, or understanding templ syntax.

Manage TickTick tasks and projects for JMO. Use when the user asks to add, create, or capture a task or todo; list, show, or review pending tasks; complete or check off a task; update a task's priority, due date, notes, or tags; delete a task or list; create or manage a project/list; or see what's due today or overdue. Also handles quick captures like "remind me to..." or "don't let me forget...".

Use this skill when working with GAS, Gameplay Ability System, GameplayAbility, GameplayEffect, AttributeSet, GameplayTags, ability system, buffs, debuffs, cooldowns, or attribute modification. See references/ for detailed setup patterns, effect configuration, and ability task usage.

Vitest testing framework conventions and practices. Invoke whenever task involves any interaction with Vitest — writing tests, configuring vitest.config.ts, mocking modules, debugging test failures, snapshots, coverage, or migrating from Jest.

Checkpoint and resume workflow state for context persistence across sessions. Use when the user says 'save progress', 'checkpoint', 'I need to stop', or runs /checkpoint or /rehydrate. Saves current workflow phase, task progress, and artifacts for later resumption. Do NOT use for workflow initialization (handled by ideate/debug/refactor commands).

This skill should be used when the user wants to bulk-build ArcKit artefacts in parallel rather than running individual /arckit:* commands one at a time. Invoke manually with /arckit:arckit-build when the task sounds like 'kick off a build', 'build everything', 'generate all artefacts', 'run all the commands', 'rebuild this project from scratch', 'resume the build', 'pick up where we left off', 'refresh the artefacts', 'run the recipe', 'build the whole project end-to-end', or 'parallel build', or mentions `--plan`, `--resume`, `--target`, `--refresh`, `--recipe`, or `.arckit/state.json`. The skill orchestrates parallel /arckit:* generation using subagent isolation: reads project state, computes the artefact dependency DAG, dispatches one subagent per target per wave (each subagent invokes a /arckit:* skill in its own context), validates outputs, commits the wave, and persists progress to .arckit/state.json for resumability.

Create custom job steps for B2C Commerce batch processing. Use this skill whenever the user needs to write a batch job, data export script, scheduled cleanup task, or any server-side processing that runs on a schedule. Also use when they ask about steptypes.json, chunk-oriented vs task-oriented job steps, read/process/write patterns, or how to get a custom job to appear in Business Manager — even if they just say "I need a script that runs nightly" or "batch process orders".

Book club management: generate Slack announcements, reminders, article roundups, eve (day-before + spark questions), one-pagers, and communication timelines. Use when user mentions book club, reading group, book of the month, or wants book-club-related communications or materials.

Transform SDD tasks into test-first TDD task pairs. Reads existing tasks from /create-tasks and generates paired test tasks with RED-GREEN dependencies. Use when user says "create tdd tasks", "add tdd pairs", "convert to tdd", or wants to apply test-first ordering to SDD tasks.

Fetch full email MIME content and attachment files from IMAP by message reference. Use when downstream steps already have a stage-1 mail_ref and need full headers/body/attachments for a specific message, with message_id_norm as the primary lookup key and uid only as fallback.

Exports Amazon RDS or Aurora database snapshots to Amazon S3 in Apache Parquet format for analytics, backup, or data migration. Handles snapshot selection or creation, IAM role setup, KMS encryption, S3 bucket preparation, export task execution, progress monitoring, and data verification. Use when exporting RDS/Aurora data to S3 for Athena, Glue, or Redshift Spectrum consumption.

Go language conventions, idioms, and toolchain. Invoke when task involves any interaction with Go code — writing, reviewing, refactoring, debugging, or understanding Go projects.

Google Chat CLI operations via gws. Use when users need to list/create/manage chat spaces, read/send messages, manage members, track read state, handle attachments, or monitor space events. Triggers: google chat, gchat, chat spaces, chat messages.

Google Gmail CLI operations via gws. Use when users need to list emails, read messages, send email, manage labels, drafts, attachments, batch operations, or trash messages. Triggers: gmail, email, inbox, send email, mail, labels, archive, trash, drafts, attachments.

Google Sheets CLI operations via gws. Use when users need to read, write, or manage Google Sheets spreadsheets including cell values, rows, columns, sheets, sorting, merging, formatting, and find-replace. Triggers: sheets, spreadsheet, google sheets, cells, rows, columns, formulas, formatting.

Google Slides CLI operations via gws. Use when users need to create, read, or edit Google Slides presentations. Triggers: slides, presentation, google slides, deck.

Use when a Mantle DeFi task needs discovery, venue comparison, or execution-ready planning with verified contracts, preflight evidence, and an external handoff.

Select the next backlog task and drive it through isolated implementation, review, docs, verification, and publish gates from a git-branchless detached HEAD. Use when "next task", "work the backlog", "pick the next issue", "do the next thing", or "start the next task".

Builds SwiftUI views with modern MV architecture, state management, and view composition patterns. Covers @Observable ownership rules, @State/@Bindable/@Environment wiring, view decomposition, custom ViewModifiers, environment values, async data loading with .task, iOS 26+ APIs, Writing Tools, and performance guidelines. Use when structuring a SwiftUI app, managing state with @Observable, composing view hierarchies, or applying SwiftUI best practices.

This skill should be used when the user asks to "write JavaScript", "create a JS module", "implement a JS class", "type this with JSDoc", "add JSDoc comments", "add type annotations", "model this type", "use modern JS", "convert to ESM", "use ES modules", "fix this JavaScript", "refactor this JS code", or any task involving writing, reviewing, or improving JavaScript code. Provides best practices for type modeling with JSDoc, modern language features (ES2024/2025), web APIs, error handling, and module patterns. This skill covers plain JavaScript with TypeScript-checked JSDoc, NOT TypeScript (.ts) files.

Bun runtime conventions, APIs, and toolchain. Invoke whenever task involves any interaction with Bun — serving HTTP, file I/O, shell scripting, testing, bundling, or package management with Bun.

Creates or reconciles GitHub child task issues for an approved Phase 4 task plan. Use after docs/<ISSUE_SLUG>-tasks.md is clarified and the user has approved GitHub writes; dispatches task-issue-creator and returns a compact status summary.

Creates or reconciles Jira subtasks for an approved Phase 4 task plan. Use after docs/<TICKET_KEY>-tasks.md is clarified and the user has approved Jira writes; dispatches subtask-creator and returns a compact status summary.

Expert customer lifecycle marketing guidance for retention, expansion, and advocacy. Use when designing onboarding programs, creating upsell strategies, preventing churn, building referral programs, or writing customer success content. Use for NPS programs, win-back campaigns, customer segmentation, and lifecycle email sequences.

Parallel/distributed computing. Scale pandas/NumPy beyond memory, parallel DataFrames/Arrays, multi-file processing, task graphs, for larger-than-RAM datasets and parallel workflows.

Use when the task involves reading, creating, or editing `.docx` documents, especially when formatting or layout fidelity matters; prefer `python-docx` plus the bundled `scripts/render_docx.py` for visual checks.

Google Docs CLI operations via gws. Use when users need to read, create, or edit Google Docs documents. Triggers: google docs, document, gdoc, word processing.

Transforms product or technical specifications into concrete implementation plans and task notes within Obsidian. Parses spec documents, extracts requirements, creates structured implementation plans with linked tasks, and manages development workflow from requirements to completion using markdown files and frontmatter.

Open-source pull request creation: PR descriptions, titles, fork workflows, and contribution compliance. Invoke whenever task involves any interaction with pull requests for external repositories — contributing code, opening PRs from forks, writing PR descriptions, or preparing changes for upstream submission.

Universal project planning for non-technical projects. Domains: business, personal, creative, academic, organizational, events. Capabilities: goal setting, milestone planning, resource allocation, timeline creation, risk assessment, progress tracking. Actions: create, plan, structure, breakdown, track projects. Keywords: project plan, roadmap, strategy, goal setting, milestones, timeline, action plan, project management, business plan, personal goals, creative project, academic planning, event planning, organizational change, OKRs, SMART goals, Gantt chart. Use when: creating project plans, setting goals/milestones, planning business initiatives, organizing events, structuring academic work, developing strategies/roadmaps.

Rigor Intake helper for README-first deep learning repo reproduction. Use when the task is specifically to scan a repository, read the README and common project files, extract documented commands, classify inference, evaluation, and training candidates, and return the smallest trustworthy reproduction plan to the main orchestrator. Do not use for environment setup, asset download, command execution, final reporting, paper lookup, or end-to-end orchestration.

Run a high-quality decision process and produce a Decision Process Pack (decision brief/pre-read, options + criteria matrix, RAPID/DACI roles, decision meeting plan, decision log entry, comms, review plan). Use for decision making, decision memo, decision log, one-way door vs two-way door, RAPID, DACI, RACI, exec alignment.

Run a full RED-GREEN-REFACTOR TDD workflow for a feature. Accepts a feature description, task ID, or spec section as input. Presents a plan for confirmation then runs autonomously through all TDD phases.