Conversion optimization — product detail pages, video hooks, urgency tactics, checkout flow

Creator relationship management — recruitment, briefing, content approval, commission optimization

Customer service on TikTok Shop — response time, dispute resolution, auto-replies, buyer satisfaction

Fulfillment setup — Fulfilled by TikTok, self-fulfillment, shipping templates, return policies

Inventory management for TikTok Shop — demand forecasting, viral stock planning, FBT optimization

Pricing strategy for TikTok — competitive pricing, commission impact, bundling, discount psychology

Product research for TikTok Shop — viral potential scoring, creator demand, category analysis

TikTok Shop deals — Flash Deals, vouchers, free shipping, bundle deals, promotion planning

Return policy and process — TikTok Shop policies, return rate reduction, customer communication

Review strategy for TikTok Shop — encouraging reviews, responding, leveraging UGC, social proof

TikTok Shop shipping setup — carrier selection, shipping templates, delivery expectations

Trending product discovery — viral product analysis, category trends, seasonal opportunities on TikTok

Security anti-pattern for timing side-channel vulnerabilities (CWE-208). Use when generating or reviewing code that compares secrets, tokens, passwords, or cryptographic values. Detects early-exit comparisons that leak information through timing differences.

Compressed communication using symbols and abbreviations. Use when context is limited or brevity is needed.

Designs robust function/tool calling schemas for LLMs with JSON schemas, validation strategies, typed interfaces, and example calls. Use when implementing "function calling", "tool use", "LLM tools", or "agent actions".

Go project toolchain -- build, test, lint, module management, and debugging.

Node.js/TypeScript project toolchain -- npm/pnpm/yarn, testing, linting, building, and debugging.

Python project toolchain -- venv, pip, testing, linting, packaging, and debugging.

Rust project toolchain -- cargo build, test, clippy, formatting, and cross-compilation.

Configure Vite, TypeScript, Biome, and Vitest for React 19 projects. Covers build configuration, strict TypeScript setup, linting/formatting, and testing infrastructure. Use when setting up new projects or updating tool configurations.

DEPRECATED in v0.4.0. Use `/aidoc-flow:doc-validator` traceability pass. This skill is a redirect stub and will be removed in v0.7.0.

Trace downstream data lineage and impact analysis. Use when the user asks what depends on this data, what breaks if something changes, downstream dependencies, or needs to assess change risk before modifying a table or DAG.

Optimize portfolio allocation using npx neural-trader mean-variance engine with risk constraints and rebalancing plan

Detect current market regime using npx neural-trader — bull/bear/ranging/volatile classification with recommended strategy

Assess portfolio risk using npx neural-trader — VaR, CVaR, Sharpe, position sizing, circuit breaker status

Train neural models (LSTM, Transformer, N-BEATS) on market data using npx neural-trader with confidence intervals

Systematic exploration + pruning + expansion via Tree of Thoughts methodology. Branch on candidate sub-thoughts; meta-judge prunes.

Manage Trello boards, lists, and cards via the REST API.

Triage and categorize findings for the CLI todo system

Triage and categorize findings for the CLI todo system

Export TripIt travel data (trips, flights, hotels) to JSON using browser automation. Use when the user asks to export, download, or backup their TripIt data.

TypeScript style standards for AIRBot reviewers

Create free SSH tunnels to expose local ports to the internet using tinyfi.sh. Use when you need to share a locally running app, test webhooks, demo a prototype, or get a public HTTPS URL for any local service — no signup or authentication required.

Index the current project for optimized search with QMD semantic search and fast file suggestions. Run this when entering a new codebase or after significant changes. Saves 60-80% tokens on exploration tasks.

Generates a technical blog post from code implementation. Use when asked to write a blog post about a feature, explain an implementation for a blog, document code as a blog article, or create technical content from source code. Triggers on phrases like "write a blog post about", "turn this into a blog", "create a technical article", or "explain this for a blog".

Send SMS, make calls, and manage phone numbers via the Twilio REST API.

Query Twitter/X — search tweets, get user profiles, timelines, and followers via the API v2.

Security anti-pattern for type confusion vulnerabilities (CWE-843). Use when generating or reviewing code in dynamic languages that compares values, processes JSON/user input, or uses loose equality. Detects weak typing exploits and type coercion attacks.

Best practices and patterns for building SwiftUI views and components. Use when creating or refactoring SwiftUI UI, designing tab architecture, composing screens, or needing component-specific guidance.

Deep thinking mode - approach problems like a craftsman, obsess over details, and create elegant solutions

Implement bundles in Umbraco backoffice using official docs

Implement entry points in Umbraco backoffice using official docs

Implement kinds in Umbraco backoffice using official docs

Restore an archived repository to active queries

Update the current development session with progress notes

Use when updating your branch with upstream changes - fetches, merges, and intelligently resolves conflicts

Update project documentation based on recent changes and current codebase state.

Create or update repository skills and instructions when major learnings are discovered during a session. Use when the user says "learn!", when a significant pattern or pitfall is identified, or when reusable domain knowledge should be captured for future sessions.

Upgrade Python dependencies using uv, then run post-upgrade checks to ensure nothing is broken.

Provision a zero-config, no-signup Upstash Redis database for an AI agent via a single POST to `https://upstash.com/start-redis`. Use when an agent needs scratch Redis for short-term memory, conversation history, sub-agent work queues, or ranked recall and the user has not provided credentials. The database lives 3 days unless the user claims it.

Use when understanding your capabilities, how to use skills, or the rules of the Co-Researcher system.

Use when starting any conversation - establishes mandatory workflows for finding and using skills, including using Skill tool before announcing usage, following brainstorming before coding, and creating TodoWrite todos for checklists

Use when starting any conversation - establishes mandatory skill invocation for both Development AND Operations workflows

Use when starting new feature work to create isolated git worktrees with smart directory selection and safety verification. Keeps main branch clean while developing.

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Applies JAX patterns for scientific Python development. Use when working with JAX, distrax, numpyro, blackjax, or scientific computing. Covers vmap, JIT, RNG handling.

Use when exploring codebases with Serena MCP tools for architectural understanding and pattern discovery - guides efficient symbolic exploration workflow minimizing token usage through targeted symbol reads, overview tools, and progressive narrowing

Use and customize workflow templates for common scenarios. Use when user wants to use a template, asks about available templates, or wants to customize existing workflows.

Use when tracking time, managing time entries, listing projects/tags, or interacting with Toggl

Answers design and architecture questions from plans and docs. Use for /ask.

Create session handoff document for transferring work to another session

Generate or update project documentation

Logging auditor focused on signal over noise. Use for /logging.

Add, fix, or update logging in project code

Token-efficient code analysis reference. Use when analyzing large codebases or needing structured code intelligence.

Use `uv` instead of pip/python/venv. Run scripts with `uv run script.py`, add deps with `uv add`, use inline script metadata for standalone scripts.

UX Vern - Cool architecture, but can the user find the button? Empathy-driven design thinking.

Write or review UX copy — microcopy, error messages, empty states, CTAs

Build consistent design systems with tokens, components, and theming. Use when creating component libraries, implementing design tokens, building theme systems, or ensuring design consistency. Triggers on design system, design tokens, component library, theming, dark mode.

Unified validation dispatcher. Auto-detects validation type from argument or presents selection menu. Routes to test, implement (verify), or hooks-test.

Validate a Claude Code plugin structure, frontmatter, and MCP tool references

Validate skill structure, frontmatter, and best practices

Hygiene pass over active notes, ideas, and projects

Evaluate a vendor — cost analysis, risk assessment, and recommendation

Identify and evaluate publication venues. Considers scope, impact factor, review timeline, acceptance rate, and fit. Produces a ranked shortlist with submission strategy guidance. Updates .papermill/state.md.

Security pattern for self-contained token authentication (e.g., JWT). Use when implementing stateless authentication, designing tokens with embedded claims, or building systems where tokens contain principal information and can be verified without server-side storage. Specialization of Authentication pattern.

Evidence-based verification methodology before claiming work is complete. Use when about to claim work is done, before committing, before creating PRs, or when verification-reminder hook fires. Triggers on: 'verify', 'verification', 'is it done', 'complete', 'ready to merge'.

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Evidence before claims, always. No completion claims without fresh verification. The final gate before declaring success.

Architecture review in hindsight — what to question, dependency analysis, abstraction assessment

Fake code detection — performative implementations, test theater, misleading patterns, red flags

Use this skill to verify that PostHog instrumentation is firing correctly on a website. Drives a real browser at one or more URLs, observes which PostHog events actually arrive, and reports a pass/fail summary. Use after installing the PostHog SDK on a site, after a deploy that touches tracking code, or when events appear missing in the PostHog dashboard.

Code cleanliness — AI-generated slop, naming, dead code, over-engineering, simplification

Verify a claim with fresh local evidence: restate it falsifiably, capture baseline and treatment, compare artifacts, and return VERIFIED, NOT VERIFIED, or INCONCLUSIVE.

Downloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.

Video editing with ffmpeg

Generate short videos for e-commerce products using Veo. Use this when the user asks for a video, motion, or animation of a product.

Refactor SwiftUI view files for consistent structure, dependency injection, and Observation usage. Use when asked to clean up a SwiftUI view's layout, handle view models safely, or standardize how dependencies are initialized and passed.