opencue

Use when you need to drive a real browser to open a page, fill forms, click, screenshot, scrape, or test a login flow. Triggers on "automate the browser", "test the page", "scrape this site".

Use when the user says "lightpanda", "scrape this page", "headless browse", or "dump the DOM". Fast headless browser for rendering URLs without Chromium, scraping, and CDP automation.

Use when user says "does it work?", "screenshot the page", "show me the form", "check the checkout flow", or "open the browser". Drives Chromium/Firefox/WebKit via Playwright MCP to verify storefront/admin UI changes, reproduce reported UI bugs, test Medusa dev servers on localhost, or explore third-party sites.

Track resume versions, maintain one master resume, and manage per-job tailored copies. Use when user says "manage my resumes", "track resume versions", "which resume did I send", "master resume", "organize my resumes", or "version of my resume for this job".

Use when user says "extract text from pdf", "merge pdfs", "split a pdf", "fill out a pdf form", "extract tables from pdf", or "create a pdf". Complete PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

End-to-end pipeline that chains trendradar → article-writer → X thread → Higgsfield hero image → Postiz draft in a single shot, turning a current trend topic into a posted-ready social thread with a generated hero image. Use when user says "/trend-to-thread", "post a trend thread", "build a thread from trends", "új X thread mai trendből", or "Postiz X poszt mai trendekből".

Use when user says "Coolify", "deploy backend", or "check deploy logs". Env vars, builds, restarts, logs, rollback.

AI image generation Creative Director powered by Google Gemini Nano Banana models. Use this skill for ANY request involving image creation, editing, visual asset production, or creative direction. Triggers on: generate an image, create a photo, edit this picture, design a logo, make a banner, visual for my anything, and all /banana commands. Handles text-to-image, image editing, multi-turn creative sessions, batch workflows, and brand presets.

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no p

AI-optimized browser automation CLI with context-efficient snapshots. Use for long autonomous sessions, self-verifying workflows, video recording, and cloud browser testing (Browserbase).

Audit Flowser context routing, shared-skill discoverability, and Claude/Codex wiring. Use when context docs or skill surfaces move, split, or drift.

Audit active Flowser plan files for staleness, completion, and routing truth. Use when cleaning up plans, reconciling active work, or archiving completed artifacts.

Audit agent harness health: Claude/Codex agent parity, skill registry consistency, README.md sync, and protocol file wiring. Use when agents, skills, README.md, or development-protocol files move, split, or drift.

Autonomous iterative optimization loop for measurable metrics like coverage, performance, or bundle size. Use when repeated experiments can be judged by a mechanical score.

Automate browsers with Puppeteer CLI scripts and persistent sessions. Use for screenshots, performance analysis, network monitoring, web scraping, form automation, JavaScript debugging.

Check context limits, optimize token usage, and debug context failures. Use when asking about rate limits, usage warnings, memory systems, or context-aware agent design.

Coordinate repository work through Colony MCP. Use when an agent starts, resumes, chooses work, claims files, hands off work, records working state, or finishes a task in a repo where Colony tools are available.

Bucket Claude Code and Codex session tokens into Colony tasks and surface improvement suggestions. Use when the user runs `/co:tokens`, asks how many tokens a task spent, why a session got expensive, or what to change next time.

This skill should be used when building data processing pipelines with CocoIndex, a Python library for incremental data transformation. Use when the task involves processing files/data into databases, creating vector embeddings, building knowledge graphs, ETL workflows, or any data pipeline requiring automatic change detection and incremental updates. CocoIndex is Python-native (supports any Python types), has no DSL, and uses version 1.0.0 or later.

Validate, three-way-merge, and archive a colonykit change. Use when the user runs `/co:archive <slug>` or says the change is done. Atomic — either the archive and root-write both land, or neither does.

Execute the next §T task on the current colonykit change. Use when the user runs `/co:build` or asks you to proceed with the next task. Pulls cite-scoped context, executes, on test failure records via backprop gating.

Open a new colonykit spec change. Use when the user runs `/co:change <slug>` or asks to start a new proposal, delta, or change-in-flight. Creates openspec/changes/<slug>/CHANGE.md and opens a task-thread on spec/<slug>.

Read-only drift check across root SPEC.md, the active change's delta, and the code. Use when the user runs `/co:check` or asks whether the spec and code are in sync. Writes nothing.

Use when reviewing active multi-agent work, PRs, or handoffs where you need Cavemem's hivemind tool to map branch and task ownership before reading full session memory.

Repo guardrail check and repair.

Run GitHub Actions workflows locally with nektos/act before pushing, so CI failures are caught on the laptop and the PR can be squash-merged on the first remote run.

Use when you need to merge SKILL.md updates from agent branches/worktrees into the local base branch (default: dev) with the multiagent-safety flow.

Repo guardrail check and repair.

Legacy alias for gitguardex.

Use when you need to merge SKILL.md updates from agent branches/worktrees into the local base branch (default: dev) with the multiagent-safety flow.

Use when multiple Codex agents collaborate in worktrees and you need explicit owner/joined handoff control for checklist items 4.1-4.4 before cleanup.

Use when the user wants to take a screenshot, paste an image into a terminal AI agent (Claude Code, Codex, Aider), hand content off between tmux panes, or debug clipboard issues on GNOME Wayland. flashpaste provides one unified CLI (`flashpaste shoot`, `flashpaste paste`, `flashpaste daemon`, `flashpaste doctor`, `flashpaste mcp`, `flashpaste dispatch`) plus an MCP server giving the agent real eyes (screenshots returned as PNG content) and hands (clipboard read/write + cross-pane paste).

Read and mutate any Google Ads account via the `gads` CLI. Use for budget changes, asset creation, bid strategy, performance reports, and campaign creation. Dry-run-by-default safety.

Manage the multi-account Codex fleet: lifecycle, task assignment, status, and stalled-lane recovery.