openamer

🧠 OpenAmer Wiki

Autogenerated: 2026-09-24 14:00 — 234 skills across 19 categories

📖 All Skills

📦 apple

apple-notes — Manage Apple Notes via memo CLI: create, search, edit.
apple-reminders — Apple Reminders via remindctl: add, list, complete.
findmy — Track Apple devices/AirTags via FindMy.app on macOS.
imessage — Send and receive iMessages/SMS via the imsg CLI on macOS.

📦 auto-generated

auto-best-practice-from-official — LoRA · Hugging Face — We propose Low-Rank Adaptation, or LoRA, which freezes the…
auto-competitor-intelligence-ai-coding — PowerContext, Context for work that humans and agents hand off and continue 1 pr…
auto-competitor-intelligence-an-ai — About 5-9 years in, they d notice their teams were no longer getting shit done, …
auto-competitor-intelligence-autogpt-improvem — Ctrl k GitBook Assistant Ask License GitHub More Home AutoGPT Platform Integrati…
auto-competitor-intelligence-claudepowered-ai — AI agent system prompts cannot serve as the sole enforcement layer — guardrails …
auto-competitor-intelligence-crush-glamourous —
auto-competitor-intelligence-devin-ai —
auto-competitor-intelligence-electricity-use — As a heavy Claude Code user, Simon estimates his own usage at the equivalent of …
auto-competitor-intelligence-jetbrains-ides — The AI Free tier gives you unlimited code completion and access to local AI mode…
auto-competitor-intelligence-jetbrains-zed — Protocol ACP Techzine Oct 08, 2025 Zed Code Editor Adds Agent Protocol for Fle…
auto-competitor-intelligence-mouse-precision — Mouse Precision Editing Tools for AI Coding Agents HIC Mouse gives AI coding age…
auto-competitor-intelligence-okf-agent —
auto-competitor-intelligence-opencode-ai — Terminal-Interface, Desktop-App und IDE-Extension Doku lesen Der Open-Source AI-…
auto-competitor-intelligence-opencode-open — OpenCode The open source AI coding agent — What is OpenCode? OpenCode is an op…
auto-competitor-intelligence-openhands-agent —
auto-competitor-intelligence-pythonopenaichat — Session stores conversation history for a specific session, allowing agents to m…
auto-competitor-intelligence-some-uncomfortab —
auto-competitor-intelligence-the-secret —
auto-competitor-intelligence-things-i — Dan Goodin – 8/27/2026 157 How OpenAI let a mob of LLM agents game a test and …
auto-competitor-intelligence-undisclosed-addi — The addition was a prompt injection, a form of AI attack that exploits an LLM s …
auto-competitor-intelligence-we-asked —
auto-competitor-intelligence-what-i — They re context management, tool design, policy gates, memory strategies and, if…
auto-efficiency-learning-a-visual —
auto-efficiency-learning-advanced-quantizatio — Sekunden Advanced IP Scanner genießt das Vertrauen von mehr als 70 Millionen Nut…
auto-efficiency-learning-edge-ai —
auto-efficiency-learning-efficientqat-llm — Microsoft AI, Cloud, Productivity, Computing, Gaming & Apps Explore Microsoft pr…
auto-efficiency-learning-finetuning-llms — The BitLinear layers we use in this project quantize the weights using ternary p…
auto-efficiency-learning-pushing-the —
auto-efficiency-learning-quantization-techniq —
auto-efficiency-learning-quip-2bit —
auto-efficiency-learning-ragkit-with — YouTube’s open-source SDKs (e.g., youtubei1 and youtubei2) expose the full O…
auto-efficiency-learning-show-hn — Cold start — every GPU, every model size GPU Model ZSE vLLM Speedup NVIDIA T4 (1…
auto-efficiency-learning-small-language —
auto-efficiency-learning-splitquantv2-enhanci — Subquadratic Attention Harvard NVIDIA Arya Tschand Yaosheng Fu Vijay Janapa Redd…
auto-efficiency-learning-towards-optimal — GB RTX 3060 12GB (Q4) / RTX 3070 8GB (Q4_K_S) 13B (Llama 2 13B) 26 GB 14 GB 8 GB…
auto-efficiency-learning-vptq-extreme — B @ 3/4 bits models [2024-10-18] Open source community contributes Mistral Large…
auto-explain-how-sleep-consolidation —
auto-how-does-energy-efficiency —
auto-internet-learning-40-of — Home Artificial Intelligence by Lynn Greiner Many autonomous agents doomed by go…
auto-internet-learning-ai-agent —
auto-internet-learning-ai-agents — Conclusion Key takeaways Agent reflection is a feedback loop where AI agents cri…
auto-internet-learning-amazon-demands — Amazon demands Perplexity stop using AI agent to make purchases Amazon has sent …
auto-internet-learning-an-ai — ChatGPT Work - 12th September 2026 OpenAI agents attacked RubyGems back in May -…
auto-internet-learning-autonomous-ai — AUTONOMOUS - the world’s largest summit for AI innovators — Sept 9-10 World’s …
auto-internet-learning-llm-agents — Neuromorphic Computing - Fraunhofer Institute for … — Neuromorphic computing is …
auto-internet-learning-mit-researchers —
auto-internet-learning-openai-and — Southbound 4 Train at Manhattan’s Spring Street Station A 24-year-old woman and …
auto-internet-learning-rogue-cursor — April 29, 2026 Key Takeaways PocketOS, a company that designs software for car r…
auto-internet-learning-spain-to — An unpaid ticket picks up $10 at 30 days, another $20 at 60, and another $30 at …
auto-internet-learning-strengthening-ai — Hijacking, Red-Team Evals, and Continuous Evaluation A technical reference on ag…
auto-internet-learning-the-ai —
auto-latest-research-insight-adaptive —
auto-latest-research-insight-ai — AshleysBrain 3 hours ago 9 comments 77 Neovim have a ~$800k Bitcoin donation s…
auto-latest-research-insight-an —
auto-latest-research-insight-arxiv — No thanks “Sebastian is an incredible educator and always has invaluable insight…
auto-latest-research-insight-bitnet — F16 on BitNet-embedding-270M prefill (8 threads) Supports I2_S conversion with o…
auto-latest-research-insight-deepseekr1 — Training Details of the Second RL Stage 4 Experiment 5 Ethics and Safety Stateme…
auto-latest-research-insight-hardware — I-A LLMs Large Language Models (LLMs) are extensive, general-purpose models that…
auto-latest-research-insight-ladder — August 24, 2026 1 Introduction Reinforcement Learning (RL) has emerged as a high…
auto-latest-research-insight-largescale — In each setting, LLM-based methods substantially outperform classical baselines,…
auto-latest-research-insight-llms —
auto-latest-research-insight-megatrain — MegaTrain Full Precision Training of 100B+ Parameter LLMs on a Single GPU A RAM-…
auto-latest-research-insight-opensourced —
auto-latest-research-insight-proofofthought —
auto-latest-research-insight-recursively — To address this, we propose to recursively generate summaries/ memory using larg…
auto-latest-research-insight-selfretrieval — Self-Retrieval generates relevant passage $p$ using the knowledge embedded withi…
auto-latest-research-insight-solving —
auto-latest-research-insight-teuken7bbase — Sifa 1 , Fabian Küch 6 , Andreas Herten 4 , René Jäkel 3 , Georg Rehm 5 , Stefan…
auto-latest-research-insight-the —
auto-latest-research-insight-understanding —
auto-latest-research-insight-wikidata —
auto-multidomain-learning-agentic-ai — Topics on Secure Hardware, Fall 2018 Decentralized Technologies Decentralized Fi…
auto-multidomain-learning-business-automation — 10 Beste KI-Agenten für die Automatisierung von … - Unite.AI — 17. Juli 2026 ·…
auto-multidomain-learning-climate-science — Artificial intelligence for modeling and understanding extreme weather … — 24….
auto-multidomain-learning-education-ai —
auto-multidomain-learning-financial-markets — Esperanto Español Eesti Euskara فارسی Suomi Na Vosa Vakaviti Français Nordfriisk…
auto-multidomain-learning-if-ai — August 16, 2026 12 min read Nvidia AI Infrastructure GPUs FinOps Wall Street Nvi…
auto-multidomain-learning-legal-ai —
auto-multidomain-learning-llms-are —
auto-multidomain-learning-medical-diagnosis — Artificial intelligence-driven transformative applications in disease … — In c…
auto-multidomain-learning-nasa-ibm — It took several weeks and dozens of GPUs to train the model on 40 years of histo…
auto-multidomain-learning-neural-architecture —
auto-multidomain-learning-neural-duhagery — Sep 24, 2025 Deep Dive into Context Engineering for Agents Sep 18, 2025 Architec…
auto-multidomain-learning-openaiembeddings25- — OpenAI(api_key=’your-api-key’) model = OpenAIEmbeddingsModel(model=’text-embeddi…
auto-multidomain-learning-opensource-medical — Updated Sep 14, 2026 Python ProjectNeura / MIPCandy Sponsor Star 294 Code Issues…
auto-multidomain-learning-philosophy-of —
auto-multidomain-learning-physics-simulation — Distinction between classical and modern physics 2.
auto-multidomain-learning-python-climate — This article presents a comprehensive, open-source Python framework that democra…
auto-multidomain-learning-python-legalaiautom —
auto-multidomain-learning-pytorch-physics — A collection of methods in an intelligent software structure allows the user to …
auto-multidomain-learning-show-hn —
auto-security-learning-agent-sandboxing —
auto-security-learning-ai-agent —
auto-security-learning-ai-supply — MetaBackdoor trains the model to activate hidden behavior when the total token c…
auto-security-learning-detecting-prompt —
auto-security-learning-how-are —
auto-security-learning-jailbreak-prevention —
auto-security-learning-llm-prompt —
auto-security-learning-mcp-server — Attack Success Rate (360 runs 60 payloads 2 models ~3 reps) Paradigm gemma4-e2b …
auto-security-learning-microsoft-bets —
auto-security-learning-owasp-just — LLM) can be manipulated through prompt injection, whether a retrieval pipeline l…
auto-security-learning-owasp-llm — Autonomous by Design, Uncontrolled in Practice 2026-09-08 Executive Summary Betw…
auto-security-learning-owasp-top —
auto-security-learning-prompt-engineering — Prompt Engineering Is Dead in 2025 Introduction Prompt engineering, once hailed …
auto-share-a-lesson-you — Fertig, Damir! ✅ Das 3-Tier-Routing ist eingerichtet und live verifiziert.
auto-structural-connection-between-energy —
auto-structural-connection-between-learning —
auto-structural-connection-between-system —
auto-structural-connection-between-tool —
auto-what-are-the-most —
auto-what-did-you-learn — Mamba-3 ist schneller als Transformer beim Decode und stärker als Mamba-2 — open…
auto-what-is-the-difference —
auto-what-makes-a-selfimproving —
auto-what-new-agent-architectures — Top 20 GitHub Repositories for AI Agents in 2026 (Ranked by Stars) — 6. Apr. 202…

🤖 autonomous-ai-agents

a2a-swarm — Run and grow the OpenAmer Agent-to-Agent swarm: identity, trust, node-to-node as…
agent-mesh — Agent mesh: master/worker nodes, HTTP delegation, heartbeat.
bug-bounty — Use for autonomous bug-hunt: scan, reproduce, fix, bounty.
claude-code — Delegate coding to Claude Code CLI (features, PRs).
codex — Delegate coding to OpenAI Codex CLI (features, PRs).
computer-use — Drive the user’s desktop in the background — clicking, typing, scrolling, draggi…
crew-manager — Role subprocesses for Dev/Tester/Reviewer/Architect tasks.
goal-engine — Use for mission: define, prioritize, –tick, progress, scan.
openamer-agent — Use, configure, theme, extend, and orchestrate OpenAmer Agent.
openamer-brain-train — Train an OpenAmer-specific small model from the collected brain data (QLoRA on N…
openamer-finetune-plan — Plan and prepare an OpenAmer-specific fine-tune from the collected brain data: d…
opencode — Delegate coding to OpenCode CLI (features, PR review).
security-agent — Use for pip CVE scanning and auto-patching via OSV.dev API.

📦 creative

architecture-diagram — Dark-themed SVG architecture/cloud/infra diagrams as HTML.
ascii-art — ASCII art: pyfiglet, cowsay, boxes, image-to-ascii.
ascii-video — ASCII video: convert video/audio to colored ASCII MP4/GIF.
baoyu-infographic — Infographics: 21 layouts x 21 styles (信息图, 可视化).
claude-design — Design one-off HTML artifacts (landing, deck, prototype).
comfyui — Generate images, video, and audio via diffusion workflows.
design-md — Author/validate/export Google’s DESIGN.md token spec files.
excalidraw — Hand-drawn Excalidraw JSON diagrams (arch, flow, seq).
humanizer — Humanize text: strip AI-isms and add real voice.
manim-video — Manim CE animations: 3Blue1Brown math/algo videos.
p5js — p5.js sketches: gen art, shaders, interactive, 3D.
popular-web-designs — 54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.
pretext — Build creative browser demos with DOM-free text layout.
sketch — Throwaway HTML mockups: 2-3 design variants to compare.
songwriting-and-ai-music — Songwriting craft and Suno AI music prompts.
touchdesigner-mcp — Control TouchDesigner via twozero MCP.

🖥️ desktop

desktop-evidence-ledger — Prove what a desktop action did — pixel-proof ledger.
multi-monitor-control — Use when driving two monitors on Windows with cua-driver.

⚙️ devops

auto-backup — Use when setting up OpenAmer auto-backup.
internet-learner-stall-fix — Use when internet_learner cycles all report rejected.
openamer-desktop-triage — Use when an OpenAmer Desktop build/launch log shows errors.
openamer-install-and-update-diagnostics — Diagnose and harden OpenAmer install/update failures (EXE, iex).
openamer-install-diagnostics — Use when an OpenAmer install or update fails on a machine.
predictive-health — Use for health trend, anomaly, disk forecast
ssh-manager — SSH hosts: add, list, exec, exec-all, scp, health-check.
traffic-cop — Use for API-key health checks, rotation, and monitoring.

📧 email

himalaya — Himalaya CLI: IMAP/SMTP email from terminal.

🐙 github

codebase-inspection — Inspect codebases w/ pygount: LOC, languages, ratios.
git-remote-state-verification — Verify what is actually pushed or released, then act.
github-auth — GitHub auth setup: HTTPS tokens, SSH keys, gh CLI login.
github-code-review — Review PRs: diffs, inline comments via gh or REST.
github-issues — Create, triage, label, assign GitHub issues via gh or REST.
github-pr-workflow — GitHub PR lifecycle: branch, commit, open, CI, merge.
github-repo-management — Clone/create/fork repos; manage remotes, releases.
openamer-local-source-workflow — Use when editing, testing or pushing OpenAmer source.
openamer-release-hotfix — Use when rebuilding or verifying an OpenAmer release EXE.
wsl-git-on-windows — Use when git from WSL hangs on a /mnt/c repo.

🎬 media

gif-search — Search/download GIFs from Tenor via curl + jq.
songsee — Audio spectrograms/features (mel, chroma, MFCC) via CLI.
youtube-content — YouTube transcripts to summaries, threads, blogs.

📦 mlops

huggingface-hub — HuggingFace hf CLI: search/download/upload models, datasets.

📝 note-taking

obsidian — Read, search, create, and edit notes in the Obsidian vault.

📋 productivity

airtable — Airtable REST API via curl. Records CRUD, filters, upserts.
docx — Create, read, edit Word .docx documents and templates.
google-workspace — Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.
maps — Geocode, POIs, routes, timezones via OpenStreetMap/OSRM.
nano-pdf — Edit text in existing PDFs via natural-language prompts.
notion — Notion API + ntn CLI: pages, databases, markdown, Workers.
ocr-and-documents — Extract text from PDFs/scans (pymupdf, marker-pdf).
pdf — Create, merge, split, fill, and secure PDF files.
powerpoint — Create, read, edit .pptx decks, slides, notes, templates.
teams-meeting-pipeline — Teams meeting summaries, job replay, Graph subscriptions.
xlsx — Create, read, edit Excel .xlsx spreadsheets and CSVs.

🔬 research

arxiv — Search arXiv papers by keyword, author, category, or ID.
blogwatcher — Monitor blogs and RSS/Atom feeds via blogwatcher-cli tool.
llm-wiki — Karpathy’s LLM Wiki: build/query interlinked markdown KB.
polymarket — Query Polymarket: markets, prices, orderbooks, history.
research-paper-writing — Write ML papers for NeurIPS/ICML/ICLR: design→submit.

🔒 security

pen-tester — Port-scan, deps, permissions, network, password hygiene.

📦 self-management

introspection — Selbst-Auskunft mit ECHTEN Zahlen: zaehle die tatsaechlichen SKILL.md- und Tool-…

🏠 smart-home

openhue — Control Philips Hue lights, scenes, rooms via OpenHue CLI.

xurl — X/Twitter via xurl CLI: raw post search, posting, DM, media.

💻 software-development

auto-code-review — Security scan + code quality + auto-fix on git push.
auto-docs — Generate docs from live git+skills+cron state.
capture-thinking — Use at the end of every important response. Save your decision-making thoughts a…
code-generator — Scaffolding für Scripts, Skills und Plugins aus Templates.
code-intelligence — Use for AST/dep graph/complexity analysis of Python code.
commander — Use for OpenAmer central CLI Commander with 28 subcommands.
dogfood — Exploratory QA of web apps: find bugs, evidence, reports.
git-remote-state-audit — Use when asked if work is pushed/published to a remote.
node-inspect-debugger — Debug Node.js via –inspect + Chrome DevTools Protocol CLI.
openamer-agent-skill-authoring — Author in-repo SKILL.md files: frontmatter and structure.
plan — Write a markdown plan to .openamer/plans/; no execution.
python-debugpy — Debug Python: pdb REPL + debugpy remote (DAP).
requesting-code-review — Pre-commit review: security scan, quality gates, auto-fix.
self-modify — Use when modifying OpenAmer’s own core code safely. Gate every change behind the…
simplify-code — Parallel 4-agent cleanup of recent code changes.
skill-validator — Use for 100-point QA validation of all skills + auto-fix + report.
spike — Throwaway experiments to validate an idea before build.
systematic-debugging — 4-phase root cause debugging: understand bugs before fixing.
test-driven-development — TDD: enforce RED-GREEN-REFACTOR, tests before code.
vision-audio — vision-audio: screenshot, describe, transcribe, diagram.
voice-assistant — Use for the Windows TTS+STT voice interface in OpenAmer.

🖥️ system

ab-test-engine — Use for A/B experiments on OpenAmer configs and skills.
context-compressor — Use for session compression and full-text search.
cross-profile-sync — Sync skills/cron/config between OpenAmer profiles.
dashboard — Use for the Live-Web-Dashboard on port 8899.
file-organizer — Clean Desktop/DL: temp, MD5 dedupe, type-sort, undo.
global-sync — Use for multi-machine HTTP delta sync with peer management.
learning-loop — Use for auto error capture, categorization and skill gen.
log-analyzer — Use for log analysis, error tracking, alerts, and dashboard.
model-benchmarker — Use when: benchmark model latency, throughput, or quality.
multi-profile — Use when running OpenAmer commands against another profile.
notification-engine — ‘Use for alerting: desktop, sound, log, webhook, daemon.’
perf-optimizer — Use when running or debugging the perf-optimizer on Windows.
remote-web — Use when starting/stopping the Remote Web UI on port 8901.
resource-monitor — Live-CPU/RAM/DISK/NET-Dashboard + Top-Prozesse + Alarm.
self-hosted — Use for local LLM fallback, failover, and Ollama health.
smart-cache — Use for cache scan, cleanup, skill archiving, and warm-cache reports.
smart-session-saver — Use for session archiving, search, restore, and stats.
system-snapshot — Use for full system-state snapshot + diff + HTTP:8898.
task-queue — Use for persistent task-queue with priorities + daemon.
webhook-engine — Use for Webhook Engine on port 8900: rules, actions, API.

This site is open source. Improve this page.

openamer

🧠 OpenAmer Wiki

📂 Categories

📖 All Skills

📦 apple

📦 auto-generated

🤖 autonomous-ai-agents

📦 creative

🖥️ desktop

⚙️ devops

📧 email

🐙 github

🎬 media

📦 mlops

📝 note-taking

📋 productivity

🔬 research

🔒 security

📦 self-management

🏠 smart-home

📦 social-media

💻 software-development

🖥️ system