Loading...
Loading...
Found 3,022 Skills
Build AI agents with Subconscious platform. Use when user wants to: build an agent, create an AI agent, use Subconscious, build with TIM, create agent with tools, research agent, search agent, tool-calling agent, subconscious.dev, TIMRUN, tim, tim-edge, timini, tim-gpt, tim-gpt-heavy. Do NOT use for generic OpenAI/Anthropic/LLM tasks without Subconscious.
QML and Qt Quick — declarative UI language for modern Qt applications. Use when building a QML-based UI, embedding QML in a Python/C++ app, exposing Python/C++ objects to QML, creating QML components, or choosing between QML and widgets. Trigger phrases: "QML", "Qt Quick", "declarative UI", "QQmlApplicationEngine", "expose to QML", "QML component", "QML signal", "pyqtProperty", "QML vs widgets", "QtQuick.Controls", "Item", "Rectangle"
Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.
Initialize new projects with proper structure, configuration, and setup from BaseProject template. Use when creating new projects, setting up directory structures, or initializing repositories.
Use this skill when diagnosing, configuring, or monitoring NICs for AF_XDP / XDP workloads. Covers driver detection, hardware queue configuration, ring buffer sizing, RSS indirection table management, interrupt coalesce tuning, offload control (GSO/GRO/TSO/LRO), VLAN offloads, Flow Director (FDIR) rules with loc pinning and ixgbe wipe bug workaround, RPS/XPS queue CPU mapping, sysctl network tuning, CPU core pinning and NUMA awareness, hardware queue and drop monitoring, softirq and rx_missed_errors analysis, BPF program inspection with bpftool (prog dump xlated, net show), kernel tracing via ftrace and dmesg, perf profiling and flamegraphs, IRQ-to-queue-to-core mapping, bonding interface diagnostics, socket inspection, and a quick diagnostic checklist.
Clean up local branches after PR merges. Syncs main with origin, identifies branches with merged PRs, and proposes safe deletion. Use when the user asks to 'clean up branches', 'delete merged branches', 'sync branches', or mentions branch cleanup.
Produces a plain-language comparison of advance directives and POLST/MOLST forms, covering legal status, clinician signatures, emergency precedence, clinical appropriateness, and document coordination. Use when the user asks about advance directive vs. POLST, living will vs. DNR, which document EMS follows, POLST vs. MOLST vs. POST, whether a healthy person needs a POLST, or document coordination in elder law, estate planning, or serious illness contexts.
Help the user systematically identify and categorize failure modes in an LLM pipeline by reading traces. Use when starting a new eval project, after significant pipeline changes (new features, model switches, prompt rewrites), when production metrics drop, or after incidents.
Sample skill for testing the skill-tester validation pipeline. Demonstrates proper skill structure with scripts, references, and assets.
Create a comprehensive product strategy using the 9-section Product Strategy Canvas — vision, segments, costs, value propositions, trade-offs, metrics, growth, capabilities, and defensibility. Use when building a product strategy, creating a strategic plan, or defining product direction.
Twitter/X research via paid API: search tweets with 50+ operators, fetch tweets with threads/replies/quotes, get user profiles with tweets/followers/following. Uses x_payment tool for automatic USDC micropayments ($0.003/call). Use when: (1) searching tweets by keyword, user, or advanced operators, (2) fetching specific tweets by ID/URL with context, (3) looking up user profiles and their activity.
LLM inference via paid API: OpenAI-compatible chat completions proxied through x402 providers. Supports Kimi K2.5, MiniMax M2.5. Uses x_payment tool for automatic USDC micropayments ($0.001-$0.003/call). Use when: (1) generating text with a specific model, (2) running chat completions through a pay-per-request LLM endpoint, (3) comparing outputs across models.