Profile My skills Saved Collections Edit profile Submit a skill

← all publishers

David Ondrej

@davidondrej source repo

73 published skills

  1. ▌
    Interview Style Doc Building · davidondrej
    Build structured strategy documents by asking one question at a time and patching the file.
    1
    install
  2. ▌
    Delegating To Agents · davidondrej
    Delegate bounded work to other AI agents while preserving context, ownership, and progress checks.
    2
    installs
  3. ▌
    Vps Server Management · davidondrej
    Manage authorized VPS hosts and server-side agents through cautious SSH and operations workflows.
    2
    installs
  4. ▌
    Markdown Rendering · davidondrej
    Open Markdown reliably in cmux panes and recover from blank rendered surfaces.
    2
    installs
  5. ▌
    Research Prompt · davidondrej
    Write a single-paragraph Deep Research prompt to hand to a human researcher (or a deep-research AI). Use when the user wants a research brief, a "deep research prompt", a one-paragraph task for a researcher, or asks "what should our researcher look for". Produces ONE tight paragraph with full context, numbered sub-questions, and per-finding output format.
    3
    installs
  6. ▌
    Ask Then Build · davidondrej
    Scope a feature, change, or refactor by asking the user 3-6 pointed questions ONE at a time (options A-D, state a preference, wait), record every answer, then deliver ONE concise paragraph prompt that another agent can implement from. Use when the user says "ask-then-build", "ask me questions then give me a prompt", or wants a spec turned into a build prompt for another agent. Differentiator: question-then-prompt loop; next-decision only drills decisions, brain-to-docs extracts vision into docs.
    3
    installs
  7. ▌
    Before Building · davidondrej bundle
    Fire the moment the user proposes a build. Instantly surface the 1-3 consequential choices hidden in the user's idea. Can also be invoked with /before-building.
    2
    installs
  8. ▌
    Codex Subagent · davidondrej bundle
    Launch OpenAI Codex CLI as a subagent (ChatGPT subscription auth, no API key). Use when delegating a self-contained coding task to Codex from another agent — parallel implementation work, a second opinion, or an independent verification pass.
    3
    installs
  9. ▌
    Google Safe Browsing · davidondrej
    Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive site", "site blocked", "safe browsing", "phishing flag", "red warning screen".
    3
    installs
  10. ▌
    Persistent Localhost · davidondrej bundle
    Persistent localhost servers (macOS launchd)
    2
    installs
  11. ▌
    Launch Subagent · davidondrej
    Read this BEFORE launching any subagent (Task tool, background agents, parallel agents, best-of-N, delegating work to another agent). Consensus principles for using subagents well. Triggers: launch a subagent, spawn agents, run agents in parallel, delegate to a subagent.
    3
    installs
  12. ▌
    Macbook Metrics Setup · davidondrej
    Replicate the macbook-metrics setup on any Mac — a local, always-on system-metrics collector (CPU, GPU, RAM, disk, network, battery, thermals) built as a Swift CLI, run by launchd every 60s, stored in SQLite, and backed up to a private GitHub repo. Use when someone wants long-term Mac performance tracking, asks how macbook-metrics works, or wants to set up the same monitoring on a new machine. Differentiator: covers the full architecture and setup ideology, not day-to-day querying of an existing install.
    3
    installs
  13. ▌
    Youtube Transcript · davidondrej
    Use whenever the user needs the transcript of a YouTube video — fetching, extracting, downloading, or pulling captions/subtitles/transcript text from a YouTube URL. Triggers on "get the transcript", "transcript of this video", "pull the captions", "download subtitles", "what does this YouTube video say". Primary path is DeepAPI (go to deepapi.co to get an API key); yt-dlp is the local fallback.
    3
    installs
  14. ▌
    Stop Overthinking · davidondrej bundle
    Manually-invoked skill that stops overthinking and forces a short, practical decision. Use only when the user explicitly invokes stop-overthinking.
    3
    installs
  15. ▌
    Reset Cursor Acp · davidondrej bundle
    Reset a stuck, hung, frozen, or buggy Cursor ACP agent inside bb, and reload its Cursor config (rules, skills, mcp.json). Use when the user says "reset cursor acp", "cursor is stuck in bb", "cursor thread hangs", "restart the cursor agent", "reload cursor config in bb", or a bb thread on the Cursor provider stops responding. Differentiator: bb-only, Cursor-only, one script. For resuming cursor-agent terminal sessions use cursor-cli; for general bb thread control use bb-cli.
    3
    installs
  16. ▌
    Github Outside Sandbox · davidondrej bundle
    Run Git and GitHub CLI commands through the host context when sandboxing blocks Keychain authentication, network access, or .git writes. Use for gh auth, repository or PR operations, and git index.lock or permission failures. Handles execution context only, not GitHub workflow design.
    2
    installs
  17. ▌
    Push Skill To Github · davidondrej
    Commit and push agent-skill changes to the user's private skills GitHub repo (<private-skills-repo>, rooted at ~/.agents). Use after creating or updating any skill, when the user says "push the skill", "push skills to github", "save the skill to my repo", or "update the skills repo". Handles staging, committing, and pushing directly in the current shell — works in any agent, no cmux needed.
    3
    installs
  18. ▌
    Signal From Expert · davidondrej bundle
    Review a corpus of the user's raw, unfiltered thinking (daily files, journaling, dictation) against a world-class expert's body of work on that topic, and surface the few passages that hit his exact situation plus at least one gap where he is wrong or missing something. Manual-only. Use when the user runs /signal-from-expert with a corpus, an expert and a topic. Differentiator: pairs his own words with the expert's exact words and file:line pointers; not a summary of the essays, not generic research.
    3
    installs
  19. ▌
    Fable Safe Prompt · davidondrej bundle
    Rewrite a user's prompt to reduce the chance it trips Claude Fable 5's server-side safety classifiers (cyber/bio guardrails that force-route to Opus 4.8 or return stop_reason "refusal"). Use when the user hands you a prompt that touches cybersecurity, auth, exploits, malware, pentesting, or other dual-use topics and asks to make it "Fable-safe", "guardrail-safe", "won't get flagged/refused/downgraded", or to rewrite it so Fable 5 won't block it.
    3
    installs
  20. ▌
    Create Readonly DB Role · davidondrej
    Provision a hardened SELECT-only Postgres role so AI agents can safely read a production database. Works on Supabase and any Postgres. Use when the user wants agents to query prod data, says "read-only role", "safe prod DB access for agents", or is tired of running SQL by hand for agents. Differentiator: this skill CREATES the role and wiring; day-to-day querying belongs in a project-local skill.
    2
    installs
  21. ▌
    Global Agent Guardrails · davidondrej
    One shared denylist of catastrophic shell commands (rm -rf on / or ~, dd/mkfs, sudo rm, fork bombs, curl|sh, git push --force, gh repo delete) enforced as a PreToolUse/pre-exec guard across every AI coding agent on the machine — Cursor, Claude Code, Codex, OpenCode, Pi, Hermes, Grok, Droid, Devin. Use when adding or tuning blocked-command patterns, wiring the guard into a new agent or a new machine, debugging why a command was (or was not) blocked, or when the user mentions command guard, guardrails, dangerous command hook, or PreToolUse safety.
    2
    installs
  22. ▌
    Fireflies Transcript · davidondrej
    Pull raw meeting transcripts from the user's Fireflies.ai notetaker via its GraphQL API, using the key saved globally on this MacBook. Use when the user wants a call transcript, meeting notes, "what was said on the call", onboarding-call transcripts, or Fireflies data. Differentiator: Fireflies meeting recordings only — for YouTube videos use youtube-transcript.
    3
    installs
  23. ▌
    Effective Agent Skills · davidondrej
    How to write effective agent skills — what to do, what not to do, anatomy, progressive disclosure, design patterns, anti-patterns, testing, security. Read this whenever a skill (Claude Skill, Agent Skill, SKILL.md) is being created, edited, reviewed, or debugged. Use when the user says "create a skill", "new skill", "update this skill", "improve a skill", "why isn't my skill triggering", or anything else involving authoring or editing SKILL.md files.
    2
    installs
  24. ▌
    Agentic Productivity Setup · davidondrej bundle
    Build or rebuild a private, local-first macOS system that measures daily Git commits, active AI-agent sessions, and instruction prompts, then sends aggregate charts to Discord. Use when someone asks to set up an agentic productivity tracker, install daily agent reports, recreate this architecture on a Mac, or understand how to build it safely. Differentiator: creates a fresh system from generic contracts and never copies another person's data, paths, credentials, repositories, prompts, or private configuration.
    2
    installs
  25. ▌
    Agent Self Scheduling · davidondrej
    Make an AI agent run on a schedule, loop, or interval — cron, heartbeats, recurring autonomous checks. Use for "run every N minutes", "schedule a task", "run on a loop", "heartbeat". Covers external clocks (Claude Code, Codex, Pi) vs Hermes' built-in scheduler.
    3
    installs
  26. ▌
    Render Images In Cursor · davidondrej
    Reliably show images, renders, mockups, screenshots, or plots to the human user inside the Cursor app chat. Use whenever the user must SEE an image the agent generated or found, or when the user says they cannot see an image you sent. Differentiator: fixes the silent failure where images saved outside the open workspace never render in Cursor chat.
    2
    installs
  27. ▌
    Distribute Skill To All Agents · davidondrej
    Distribute a skill across the 4 agent skill folders (Codex, Claude Code, Pi, Hermes) so all agents see it. Use when the user says "distribute this skill", "sync skills across agents", or after creating/updating a skill that should be global. Covers the symlink layout and the ~/.pi/agent/skills trap.
    2
    installs
  28. ▌
    Folder Specific Claude And Agents Md · davidondrej
    Create a specialized CLAUDE.md (+ AGENTS.md symlink) inside a specific folder to give future agents folder-scoped context. Use when the user asks to create a CLAUDE.md for a folder, write folder instructions, or add agent context to a directory.
    2
    installs
  29. ▌
    Corral Launch Agents · davidondrej bundle
    Launch new CLI coding agents through Corral Design 1, or correctly reopen existing agent sessions inside a Corral-active Herdr repository. Use when the user asks to launch, spawn, batch-start, reopen, relaunch, or resume agents. New launches create Corral-owned tasks; resumptions reuse existing worktrees and sessions.
    2
    installs
  30. ▌
    Repo Sync · davidondrej bundle
    Manage repo-sync on macOS for shared documents and team context. Use when asked what repo-sync does, to automatically sync a repo, add a repo to repo-sync, stop syncing or un-sync a repo, check sync health, configure repo-sync, uninstall it, or install and maintain its bundled agent skill. Ordinary one-time Git pulls and pushes do not need this skill.
    4
    installs
  31. ▌
    Teach · davidondrej bundle
    Teach the user a new skill or concept, within this workspace.
    3
    installs
  32. ▌
    Cmux · davidondrej
    Control the cmux macOS terminal app (CLI + socket API) — cmux workspaces, panes, surfaces, browser automation, notifications, settings, hooks. MUST be read before running any `cmux` command. Trigger ONLY when the user explicitly says "cmux" — a cmux pane, cmux workspace, cmux surface, or an agent running in cmux. Do NOT trigger on generic mentions of "workspace", "pane", "the other agent", or "delegate" when cmux is not named — workspaces in tmux, Ghostty, herdr, VS Code, etc. are NOT cmux. macOS only (14.0+).
    3
    installs
  33. ▌
    Anti Sleep · davidondrej bundle
    Keep the user's MacBook awake reliably with macOS caffeinate for a set duration or while a process runs. Use for "don't let my Mac sleep", "keep the screen on", "anti-sleep", "caffeinate", overnight work, or long builds. Unlike a normal background job, it survives temporary agent-shell cleanup.
    3
    installs
  34. ▌
    Openrouter · davidondrej bundle
    Configure, build, debug, and optimize any integration with the OpenRouter API. Use whenever choosing OpenRouter models or fallbacks, setting reasoning effort or token limits, routing providers, attaching images, using tools or structured output, or investigating cost, latency, streaming, and API failures. Applies across apps, scripts, SDKs, agents, and pipelines.
    4
    installs
  35. ▌
    Setup Help · davidondrej bundle
    Walk the user through setting up anything step by step. Use when the user asks for help setting up, configuring, installing, or getting something working — "help me set up X", "walk me through this", "setup-help". Differentiator: gives one current step at a time, then always lists every remaining setup step after each response.
    3
    installs
  36. ▌
    Deepapi · davidondrej bundle
    Use DeepAPI for all regular web searches (POST /v1/search/web) and for any deep research you perform (POST /v1/research/deep), instead of built-in search or research tools. Use Deep Scrape (POST /v1/scrape/deep) for a sourced JSON dossier on a person, company, or topic. Use DeepAPI for all scraping of the web (websites, LinkedIn, GitHub, X/Twitter, YouTube — POST /v1/scrape/*) instead of built-in fetch or browser tools. Platform data has dedicated DeepAPI endpoints — prefer them over web search. Instagram provides profile, posts, comments, and hashtag endpoints, not a generic search endpoint. Also use it to navigate and act on public websites (POST /v1/browser/act), draft and send safe email, and generate images with DEEPAPI_API_BASE_URL and DEEPAPI_API_KEY.
    3
    installs
  37. ▌
    Remind · davidondrej bundle
    Rewrite the last response simpler and shorter in plain English, prefixed with a 3-5 sentence TLDR of the conversation so far. Manual-only, invoked as /remind.
    3
    installs
  38. ▌
    Rename · davidondrej
    Manually-invoked skill that renames the current thread or session to 2-5 lowercase descriptive words. Use when the user says "rename", "rename this", "rename thread", or "rename session".
    3
    installs
  39. ▌
    Herdr · davidondrej
    Operate and coordinate AI agents running inside Herdr in Ghostty. Use when the user says "Use the Herdr skill," mentions Herdr, or asks to inspect, message, wait for, or coordinate agents in a Herdr workspace. Herdr-specific; do not use for cmux or ordinary terminal sessions.
    3
    installs
  40. ▌
    Bb CLI · davidondrej bundle
    Use this when controlling bb. The bb CLI lets you inspect, create, and orchestrate bb threads, automations, projects, providers, and environments.
    3
    installs
  41. ▌
    Nagent · davidondrej bundle
    Launch a new bb worker thread with an explicit project, provider, model, reasoning effort, fast/default tier, worktree, and prompt. Short for "new agent". Use when the user says "nagent", "/nagent", "launch a bb session", "bb subagent", "spawn a bb thread", "new worktree agent", "launch it as its own thread, not as your subagent", "standalone bb thread", or asks to run Grok/Codex/Cursor CLI in bb on a repo. Differentiator vs bb-cli: this is only the spawn recipe. Differentiator vs codex-subagent/launch-subagent: those are Codex CLI and Cursor Task tool, not bb threads.
    3
    installs
  42. ▌
    Level Up · davidondrej bundle
    Gauge the user's technical + product knowledge through 7 adaptive questions, log verbatim answers with honest ratings, and grow a learning plan from the gaps found. Use when the user says "level up", "level-up session", "quiz me", "gauge my knowledge", or wants a new assessment round. Differentiator: this finds and maps gaps; the `teach` skill delivers lessons on them.
    3
    installs
  43. ▌
    Handoff · davidondrej bundle
    Compact the current conversation into a single, detailed handoff message — everything that happened, why it happened, and what's left — output in a code block so it can be copy-pasted into a fresh agent session. Use when hitting context limits, switching focus, ending a work session, or partitioning a task across fresh contexts.
    3
    installs
  44. ▌
    Risky Changes · davidondrej
    Mandatory verification discipline before shipping any large or risky change — new public API fields or filters, provider or data-source behavior changes, billing and pricing logic, changed defaults that shape what customers see. Trigger BEFORE implementing whenever a change rests on an unverified assumption about real-world data or user behavior, or when the user says "risky change", "is this safe to ship", or "verify this assumption". Differentiator: validates that the change is a good idea using DeepAPI deep research (get a key at deepapi.co) and live measurement — not code correctness; unit tests do not count.
    3
    installs
  45. ▌
    Decisions · davidondrej bundle
    Ask the agent to list all choices it made during the current work that it is not confident of. Manual-only; invoke with /decisions.
    3
    installs
  46. ▌
    File Tree · davidondrej
    Manually-invoked skill that prints a nice file tree of the current topic in a code block. Use when the user says "file-tree" or "file tree".
    3
    installs
  47. ▌
    Prompt Me · davidondrej
    Prompt the user with pointed questions to extract what is in his head about a project — remaining work, what is being avoided, what really matters, what does not. Use when the user says "prompt me", "ask me questions", or wants the agent to figure out priorities by questioning him.
    3
    installs
  48. ▌
    Save Idea · davidondrej
    Quickly capture an idea from any repo or chat. Everything goes to the ~/code/ideas repo: video ideas to VIDEO-IDEAS.md; smaller podcast topics, guest ideas, questions, and AI observations to TOPICS.md; marketing and distribution ideas to MARKETING-IDEAS.md; startup ideas to STARTUP-IDEAS.md; convictions the user is certain about on AI-era building to CONVICTIONS.md; mini/technical/cool projects to build to mini-projects.md. Every entry gets a source line referencing the chat and repo it came from. Use when the user says "/save-idea", "save this idea", "video idea", "add a topic", "marketing idea", "startup idea", "save this conviction", "mini project", "cool project to build", "write this down for a video/podcast". Differentiator: appends to the user's idea backlogs — not a reminder, task, or general note tool.
    3
    installs
  49. ▌
    Browser Use · davidondrej bundle
    Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
    2
    installs
  50. ▌
    Deep Scrape · davidondrej
    Build a sourced JSON dossier on a person, company, or topic through DeepAPI. Use for deep scraping, company dossiers, sales prospect qualification, software or API vendor due diligence, customer problem research, and profiles across public sources. Use deep-research for detailed answers and recommendations; use a dedicated scraping endpoint for one known page or platform.
    2
    installs
  51. ▌
    Who Is This · davidondrej bundle
    Deep-scrape a person across X, LinkedIn, GitHub, and the open web to judge if they are legit. Manual-only; invoke with /who-is-this. Use when the user says who-is-this, "who is this", "who is this guy", "research this person", "are they legit", "vet this founder", or drops a profile screenshot. Differentiator vs twitter-alpha: one-person background check, not a 7-person idea list. Differentiator vs deep-research: platform scrapes plus a short verdict, not a long cited memo.
    3
    installs
  52. ▌
    Goal Loop · davidondrej
    Explain and write effective instructions for the `/goal` feature — the persistent self-checking agent loop (plan → act → test → review → iterate), available in agents like Codex, Claude Code, and Hermes Agent. Use when the user mentions `/goal`, "goal loop", "Ralph loop", wants to kick off a long-running autonomous agent run, asks how to write a goal prompt, or wants a one-paragraph goal instruction drafted.
    3
    installs
  53. ▌
    Nuke Cursor App · davidondrej bundle
    End-to-end Cursor IDE restart on the user's MacBook: snapshot metrics, kill ALL Cursor processes, relaunch Cursor, report before/after memory. Recovers from the known renderer memory leak that makes Cursor lag. Manual-only — run ONLY when the user explicitly invokes it (/nuke-cursor-app, "nuke cursor"). Differentiator: kills the Cursor desktop app; cursor-cli sessions are unrelated.
    3
    installs
  54. ▌
    Pi Custom Model · davidondrej bundle
    Register a custom or variant model (e.g. an OpenRouter ":nitro" / ":floor" / ":exacto" slug) in the Pi Agent so it can be set as the global default. Use when Pi silently falls back to a different model (e.g. moonshotai/kimi-k2.6) after setting defaultModel, or when a model slug isn't in Pi's bundled list. Triggers on "Pi reset my model", "Pi won't use this model", "add a model to Pi", "Pi default keeps reverting".
    2
    installs
  55. ▌
    Bb Plugins · davidondrej
    Build, install, and debug bb plugins. Use when the user wants a bb plugin, a sidebar panel, a bb CLI subcommand, an agent tool, a theme, a provider, or to extend bb itself. For running threads and the core bb CLI, use bb-cli instead.
    3
    installs
  56. ▌
    Gpt Review · davidondrej
    Launch a GPT 5.6 Sol Max reviewer as a bb thread (default: /nagent) to do a deep, neutral senior-developer review of the current work and report its findings back verbatim. Use when the user says "/gpt-review", "gpt review", or asks for GPT to review the code. Differentiator: reviewer model is GPT 5.6 Sol Max — for a Fable reviewer use fable-review.
    3
    installs
  57. ▌
    Deep Research · davidondrej bundle
    Run a deep, source-backed research query via DeepAPI (go to deepapi.co to get an API key) POST /v1/research/deep. Builds a rigorous one-paragraph research prompt (per research-prompt rules), fires it, and saves a cited markdown report. Use when the user asks for "deep research", "deepapi research", "perplexity deep research" (legacy trigger), or any deep source-backed research run. Differentiator vs the deepapi skill: this is the full research workflow (prompt + run + report file), not raw endpoint access.
    5
    installs
  58. ▌
    Pi Web Search · davidondrej
    ONLY for Pi Agents — all other agents have their own web tools. How Pi accesses the web via the pi-web-access package — search, fetch URLs/PDFs/YouTube/GitHub. Use whenever a Pi task needs current info, docs, news, prices, or content from a specific URL.
    3
    installs
  59. ▌
    Twitter Alpha · davidondrej
    Pull high-alpha ideas from a company or person's Twitter circle. Use when the user says twitter-alpha, alpha from twitter, scrape their tweets, what is this founder posting, or wants patterns from a company circle on X. Differentiator vs deep-research: tweet-level signal from a 7-person circle, not a company brief.
    3
    installs
  60. ▌
    Adr Verbatim · davidondrej
    Write a new ADR whose body is the user's exact words, nothing added. Use when the user says "adr-verbatim", "document that as an ADR", "new ADR", "record this decision", or gives wording for an ADR. Differentiator: agent adds only title, number and status line; it never drafts, rewrites, or expands the body.
    3
    installs
  61. ▌
    Image Prompt · davidondrej
    Turn any idea, brief, or rough instruction into 4 ready-to-paste prompts for AI image models (Midjourney, Nano Banana, GPT Images, Seedream, Flux, any other). Use when the user asks for an image prompt, a thumbnail / banner / logo / illustration prompt, says "write a prompt for this image", or wants to turn a description into something an image model can render. Differentiator: writes the prompt text only — to actually generate the image use the deepapi skill.
    3
    installs
  62. ▌
    Prompt For Others · davidondrej
    Turn a fix, upgrade, or setup step into ONE paste-ready paragraph that every teammate (including the user) sends to their own AI coding agent on their own machine. Use when the user says "prompt for others", "prompt for the team", "one-paragraph prompt everyone should run", "what should the team tell their agent", or wants a fix rolled out to many Macs. Differentiator: writes for an agent with root access on a stranger's machine, so it is self-contained, verifiable, and refuses to guess.
    2
    installs
  63. ▌
    Brain To Docs · davidondrej
    Use when the user wants to extract project vision, decisions, and preferences from their head into clear documentation (README + ADRs) through a back-and-forth Q&A loop. Triggers on "brain-to-docs", "build out the docs", "extract the vision", "let's document this project".
    3
    installs
  64. ▌
    Next Decision · davidondrej
    Drill open decisions one at a time — present the most important decision not yet clarified, give the top four choices, state a preference, ask the user. Use when the user says "next decision", "one decision at a time", or a plan has several unresolved choices. Differentiator: forward-looking; the decisions skill is retrospective (choices already made). Can be invoked with /next-decision.
    2
    installs
  65. ▌
    Read All Adrs · davidondrej bundle
    Read every ADR markdown file in the project's docs/adr/ folder so you have full context on past decisions. Use only when the user explicitly calls it.
    3
    installs
  66. ▌
    Fable Review · davidondrej
    Launch a Fable 5 Max 1M reviewer as a bb thread (default: /nagent) to do a deep, neutral senior-developer review of the current work and report its findings back verbatim. Use when the user says "/fable-review", "fable review", or asks for Fable to review the code. Differentiator: reviewer model is Fable 5 Max 1M — for a GPT reviewer use gpt-review.
    3
    installs
  67. ▌
    Git Worktree · davidondrej bundle
    Use git worktrees to run multiple coding agents in parallel on one repo without collisions. Use when starting a task in a shared repo, when the user says "worktree", "parallel agents", "one worktree per task", or when agents keep overwriting each other's changes. Covers creating worktrees, making them as complete as the main checkout (.env files, dependencies, databases, ports), merging back, and cleanup.
    3
    installs
  68. ▌
    New Grok Bot · davidondrej
    Design a new Grok Bot (SpaceXAI + Cursor AI teammate) with the user through a short clarification loop, then output one paste-ready prompt for the Grok Bot app. Use when the user says "new grok bot", "create a grok bot", "design a bot", or wants to hand a job to a Grok Bot. Differentiator: judges whether the idea is a GREAT UNIT OF WORK for a bot before writing anything.
    3
    installs
  69. ▌
    Run Deep Swe · davidondrej bundle
    Score any AI model on the DeepSWE coding-agent benchmark via the OpenRouter API. Use when the user wants an independent, reproducible coding-agent eval — "run DeepSWE", "benchmark this model on DeepSWE", "score model X on the coding benchmark", "test a model via OpenRouter on DeepSWE", or to verify vendor-reported coding scores. Covers setup, the OpenRouter wiring for mini-swe-agent, single-task / subset / full 113-task runs, and leaderboard submission.
    3
    installs
  70. ▌
    Total Review · davidondrej
    Run both fable-review and gpt-review on the current work, then merge their findings, dedupe them, and triage which issues are real vs overthinking. Outputs one clear, concise list of actual issues for the user to approve before fixing. Use when the user says "/total-review", "total review", "review with both", or wants both Fable and GPT reviewers at once. Differentiator: runs BOTH reviewers and triages the merged findings — for a single reviewer use fable-review or gpt-review.
    2
    installs
  71. ▌
    Browser Harness · davidondrej bundle
    Direct browser control via CDP. Use when the user wants to automate, scrape, test, or interact with web pages. Connects to the user's already-running Chrome.
    3
    installs
  72. ▌
    Online Shopping · davidondrej
    Research any online purchase with DeepAPI — fair-price checks, best deals, where to buy, shop trust, and VAT/tax savings. Load on ANY shopping, buying, purchasing, checkout, subscribe, SaaS plan, software subscription, Stripe/payment page, or "is this a good price" moment — including product photos and listing or checkout screenshots. Differentiator: research-only shopping help plus a company VAT-number reminder; never places orders.
    2
    installs
  73. ▌
    Short · davidondrej
    Rewrite the previous response more briefly while preserving the substance.
    4
    installs