agentsclimarketplace

Context & AI engineering

25,729 rows, by stacks then stars

1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid

  • Worktree env file isolation

    kjuhwa/skills-hub/skills/devops/worktree-env-file-isolation Skill

    0★ repo

    Per-git-worktree environment files (.env.worktree) with deterministically derived unique database names and ports, sharing one Postgres container.

  • Electron bun dev orchestrator

    kjuhwa/skills-hub/skills/electron/electron-bun-dev-orchestrator Skill

    0★ repo

    Cross-platform Electron dev launcher that parallel-builds main/preload/MCP subprocess bundles, waits for file stability, watches with esbuild's JS API, and spawns Vite + Electron - replaces a fragile tree of npm scripts.

  • Karpathy llm coding guidelines

    kjuhwa/skills-hub/skills/engineering/karpathy-llm-coding-guidelines Skill

    0★ repo

    Umbrella behavioral guideline that bundles the four Karpathy principles — Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution — to reduce common LLM coding mistakes. Use when you want all four applied at once.

  • Setup engine

    kjuhwa/skills-hub/skills/engineering/setup-engine Skill

    0★ repo

    Configure the project's game engine and version. Pins the engine in CLAUDE.md, detects knowledge gaps, and populates engine reference docs via WebSearch when the version is beyond the LLM's training data.

  • Fastapi sse mcp protocol

    kjuhwa/skills-hub/skills/fastapi-streaming-endpoints/fastapi-sse-mcp-protocol Skill

    0★ repo

    Host a hosted MCP (Model Context Protocol) server over FastAPI's StreamingResponse using API-key auth, a session dict, and a tool registry surfaced via the 2025-03-26 Streamable HTTP spec.

  • Svg image asset embedding

    kjuhwa/skills-hub/skills/flutter/svg-image-asset-embedding Skill

    0★ repo

    Flutter SVG asset handling with flutter_svg in desktop UI.

  • Git worktree isolation per thread

    kjuhwa/skills-hub/skills/git/git-worktree-isolation-per-thread Skill

    0★ repo

    Use git worktrees to isolate filesystem state per conversation thread, avoiding conflicts between concurrent edits

  • Tensor memory accelerator descriptor construction

    kjuhwa/skills-hub/skills/gpu-kernels/tensor-memory-accelerator-descriptor-construction Skill

    0★ repo

    Build Hopper/Blackwell TMA descriptors at host time via cuTensorMapEncodeTiled so kernels can issue async tiled loads without per-address arithmetic.

  • Lm prompt kv cache reuse

    kjuhwa/skills-hub/skills/inference/lm-prompt-kv-cache-reuse Skill

    0★ repo

    Pre-compute and cache LM KV state for a fixed prompt, then reuse across multiple target generations

  • Rdev global input hook

    kjuhwa/skills-hub/skills/input/rdev-global-input-hook Skill

    0★ repo

    rdev crate for global keyboard/mouse event hooking and input simulation.

  • Claude cli grace kill after success result

    kjuhwa/skills-hub/skills/integration/claude-cli-grace-kill-after-success-result Skill

    0★ repo

    When driving `claude -p --output-format stream-json`, treat a `result:success` event as completion even if the child doesn't self-exit; arm a 15s grace timer to kill, and return ok=true regardless of exit code.

  • Computer use agent

    kjuhwa/skills-hub/skills/integration/computer-use-agent Skill

    0★ repo

    Build an agent that controls a computer (screenshots, clicks, keyboard) using ComputerTool.

  • Mcp multi transport config pydantic

    kjuhwa/skills-hub/skills/integration/mcp-multi-transport-config-pydantic Skill

    0★ repo

    Single Pydantic config that supports three MCP transports (stdio, sse, streamable-http) with per-transport required-field validation in a model_validator(after) so users get a clear error when the wrong combination is set.

  • Mcp streamable http detached httpx client

    kjuhwa/skills-hub/skills/integration/mcp-streamable-http-detached-httpx-client Skill

    0★ repo

    Inject a caller-owned httpx.AsyncClient into the official MCP streamable_http transport via httpx_client_factory, using a no-op async-context-manager so the transport never closes the underlying client on exit.

  • Agent handoff routing

    kjuhwa/skills-hub/skills/llm-agents/agent-handoff-routing Skill

    0★ repo

    Route a conversation to a specialist agent via handoff, making that agent own the next turn.

  • Chain of thought prompting

    kjuhwa/skills-hub/skills/llm-agents/chain-of-thought-prompting Skill

    0★ repo

    Apply chain-of-thought prompting (zero-shot CoT, few-shot CoT, Self-Consistency) to improve LLM multi-step reasoning.

  • Deterministic agent chain

    kjuhwa/skills-hub/skills/llm-agents/deterministic-agent-chain Skill

    0★ repo

    Chain multiple agents sequentially in code, feeding each agent's output as the next agent's input.

  • Dispatching parallel agents

    kjuhwa/skills-hub/skills/llm-agents/dispatching-parallel-agents Skill

    0★ repo

    Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

  • Gui agent sft qwen2vl os kairos

    kjuhwa/skills-hub/skills/llm-agents/gui-agent-sft-qwen2vl-os-kairos Skill

    0★ repo

    SFT Qwen2-VL-7B on the OS-Kairos GUI dataset using LLaMA-Factory, converting data to ShareGPT format, and running inference.

  • Handoff input filter

    kjuhwa/skills-hub/skills/llm-agents/handoff-input-filter Skill

    0★ repo

    Filter or transform the conversation history passed to a specialist agent on handoff.

  • Handoff with typed input

    kjuhwa/skills-hub/skills/llm-agents/handoff-with-typed-input Skill

    0★ repo

    Provide structured data from the LLM to an on_handoff callback via input_type on handoff().

  • Hermes acp agent server

    kjuhwa/skills-hub/skills/llm-agents/hermes-acp-agent-server Skill

    0★ repo

    Expose an LLM agent via the Agent Client Protocol (VS Code / Zed / JetBrains) with per-session state and MCP injection.

  • Hermes anthropic prompt cache system and 3

    kjuhwa/skills-hub/skills/llm-agents/hermes-anthropic-prompt-cache-system-and-3 Skill

    0★ repo

    Place Anthropic 4 cache_control breakpoints as system + last 3 messages so multi-turn chats keep a hot cache.

  • Hermes context compression handoff

    kjuhwa/skills-hub/skills/llm-agents/hermes-context-compression-handoff Skill

    0★ repo

    Compress long agent conversations with a handoff-framed summary that prevents re-answering resolved turns.

  • Hermes cron agent scheduler

    kjuhwa/skills-hub/skills/llm-agents/hermes-cron-agent-scheduler Skill

    0★ repo

    Run an LLM agent on a cron schedule with inactivity timeout, silent marker, and cross-platform delivery.

  • Hermes delegate subagent

    kjuhwa/skills-hub/skills/llm-agents/hermes-delegate-subagent Skill

    0★ repo

    Spawn child LLM agents with restricted toolsets, isolated context, and summary-only parent feedback.

  • Hidden state capture layer hook

    kjuhwa/skills-hub/skills/llm-agents/hidden-state-capture-layer-hook Skill

    0★ repo

    Capture hidden states from specified transformer layers by wrapping them with a small proxy that records the output and forwards all other attribute access to the original layer.

  • Llm api zero few shot prompting

    kjuhwa/skills-hub/skills/llm-agents/llm-api-zero-few-shot-prompting Skill

    0★ repo

    Call Qwen (DashScope) or OpenAI APIs for zero-shot and few-shot prompting, including streaming responses.

  • Llm as judge loop

    kjuhwa/skills-hub/skills/llm-agents/llm-as-judge-loop Skill

    0★ repo

    Run an agent in a loop with an evaluator agent that provides feedback until the output meets a quality threshold.

  • Output guardrail with agent

    kjuhwa/skills-hub/skills/llm-agents/output-guardrail-with-agent Skill

    0★ repo

    Use a fast/cheap agent to validate the main agent's output before returning it to the user.

  • Parallel agent runs

    kjuhwa/skills-hub/skills/llm-agents/parallel-agent-runs Skill

    0★ repo

    Run multiple agent instances concurrently with asyncio.gather() and pick the best result.

  • Plan based multi step task decomposition

    kjuhwa/skills-hub/skills/llm-agents/plan-based-multi-step-task-decomposition Skill

    0★ repo

    Plan mode for multi-step agent tasks — exploration via subagent, gated planning with user confirmation, strict execution loop, and adversarial verification.

  • Subagent driven development

    kjuhwa/skills-hub/skills/llm-agents/subagent-driven-development Skill

    0★ repo

    Use when executing implementation plans with independent tasks in the current session

  • Macos privilege scripts embedding

    kjuhwa/skills-hub/skills/macos/macos-privilege-scripts-embedding Skill

    0★ repo

    Embed shell scripts via include_dir!() for privilege elevation + system operations.

  • Hosted mcp tool

    kjuhwa/skills-hub/skills/mcp-integration/hosted-mcp-tool Skill

    0★ repo

    Let OpenAI's Responses API call a remote MCP server on your behalf using HostedMCPTool.

  • Mcp pool http proxy for subprocess sdks

    kjuhwa/skills-hub/skills/mcp-integration/mcp-pool-http-proxy-for-subprocess-sdks Skill

    0★ repo

    Expose a pool of MCP sources (Linear, GitHub, Notion, ...) to Codex/Copilot SDK subprocesses through a single Streamable-HTTP MCP endpoint, instead of having each subprocess open independent connections.

  • Mcp sse streamable http

    kjuhwa/skills-hub/skills/mcp-integration/mcp-sse-streamable-http Skill

    0★ repo

    Connect an agent to a remote MCP server via HTTP+SSE or Streamable HTTP transport.

  • Mcp stdio server

    kjuhwa/skills-hub/skills/mcp-integration/mcp-stdio-server Skill

    0★ repo

    Connect an agent to a local MCP server running as a subprocess over stdio.

  • Mcp tool intent metadata injection

    kjuhwa/skills-hub/skills/mcp-integration/mcp-tool-intent-metadata-injection Skill

    0★ repo

    Inject a hidden _intent / _displayName field into every MCP tool schema via a fetch interceptor so large-response summarization and UI rendering have context that the LLM never sees.

  • Session scoped mcp stdio server

    kjuhwa/skills-hub/skills/mcp-integration/session-scoped-mcp-stdio-server Skill

    0★ repo

    Ship a per-session MCP stdio server bundled as CJS that provides session-scoped tools (SubmitPlan, config_validate) and uses stderr __CALLBACK__ lines to pause execution for async host-process callbacks.

  • Fastmcp stdio http dual transport

    kjuhwa/skills-hub/skills/mcp/fastmcp-stdio-http-dual-transport Skill

    0★ repo

    Single MCP server entry point that supports both STDIO (default) and Streamable HTTP / SSE transports via a --http flag, using FastMCP + Starlette + uvicorn, with localhost-binding-by-default and a warning banner on non-localhost binds.

  • Layered memory tiering system

    kjuhwa/skills-hub/skills/memory-management/layered-memory-tiering-system Skill

    0★ repo

    Hierarchical L1/L2/L3/L4 memory architecture for long-running LLM agents, anchored by action-verified facts and explicit garbage-collection rules.

  • Write a skill

    kjuhwa/skills-hub/skills/misc/write-a-skill Skill

    0★ repo

    Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

  • Sequential two phase training orchestrator

    kjuhwa/skills-hub/skills/ml-ops/sequential-two-phase-training-orchestrator Skill

    0★ repo

    Drive a two-phase training pipeline (e.g. tokenizer then predictor) with one command, CLI skip flags, and auto-skip if an earlier phase's best_model already exists.

  • Tts trailing silence and hallucination trim

    kjuhwa/skills-hub/skills/ml-ops/tts-trailing-silence-and-hallucination-trim Skill

    0★ repo

    Post-process TTS output to cut long internal silences plus any trailing hallucinated noise with a cosine fade-out.

  • Mega moe fusion with symmetric memory

    kjuhwa/skills-hub/skills/moe-optimization/mega-moe-fusion-with-symmetric-memory Skill

    0★ repo

    Fuse EP dispatch, FP8×FP4 GEMM×2, SwiGLU, and EP combine into a single kernel that reads across ranks via symmetric-memory (same VA on every rank) to overlap NVLink collectives with compute.

  • Fhs wrapper mcp server support

    kjuhwa/skills-hub/skills/nix/fhs-wrapper-mcp-server-support Skill

    0★ repo

    Wrap a NixOS application derivation in buildFHSEnv to provide a FHS-compliant filesystem view. Enables subprocess execution of dynamically linked native binaries (like MCP servers) that expect /usr, /lib, /bin at standard paths.

  • Agent tracing spans

    kjuhwa/skills-hub/skills/observability/agent-tracing-spans Skill

    0★ repo

    Wrap multi-agent workflows in named traces and custom spans for debugging in the OpenAI Traces dashboard.

  • Threadpool benchmark with warmup

    kjuhwa/skills-hub/skills/observability/threadpool-benchmark-with-warmup Skill

    0★ repo

    Run a concurrent HTTP load test against an LLM server with a warmup phase, tqdm progress on completion, and per-prompt result aggregation — all using the stdlib ThreadPoolExecutor.

  • Claude cli unattended wrapper

    kjuhwa/skills-hub/skills/operations/claude-cli-unattended-wrapper Skill

    0★ repo

    Spawn `claude -p` non-interactively from a Node parent process so a long-running loop can drive slash commands without any human at the keyboard. Layers a prompt tempfile, a piped "y\n" stream, hook-bypass env vars, and a stream-json consumer to keep the child from ever blocking.

  • Multi format native package orchestrator

    kjuhwa/skills-hub/skills/packaging/multi-format-native-package-orchestrator Skill

    0★ repo

    Orchestrate building a single Electron app source into .deb, .rpm, AppImage, and Nix outputs from one script. Handles architecture detection, distro-family detection, format-specific build dispatch, and shared staging.

  • Input guardrail agent

    kjuhwa/skills-hub/skills/safety/input-guardrail-agent Skill

    0★ repo

    Block off-topic or policy-violating user input before the main agent runs using @input_guardrail.

  • R judge agent safety evaluation

    kjuhwa/skills-hub/skills/safety/r-judge-agent-safety-evaluation Skill

    0★ repo

    Use R-Judge to evaluate an LLM agent risk awareness over multi-turn ReAct records, producing a risk description and safe/unsafe label.

  • Mcp subprocess env filtering

    kjuhwa/skills-hub/skills/security/mcp-subprocess-env-filtering Skill

    0★ repo

    When spawning a stdio MCP server (or any untrusted subprocess), allowlist/denylist environment variables so app-level auth tokens and third-party API keys don't leak into the child process.

  • Benchmark

    kjuhwa/skills-hub/skills/testing/benchmark Skill

    0★ repo

    Performance regression detection using the browse daemon. Establishes baselines for page load times, Core Web Vitals, and resource sizes. Compares before/after on every PR. Tracks performance trends over time. Use when: "performance", "benchmark", "page speed", "lighthouse", "web vitals", "bundle size", "load time". (gstack) Voice triggers (speech-to-text aliases): "speed test", "check performance".

  • Llm integration test failure diagnosis

    kjuhwa/skills-hub/skills/testing/llm-integration-test-failure-diagnosis Skill

    0★ repo

    Wire an LLM-based diagnosis step into your CI for integration-test failures — summarize noisy logs, identify probable root cause, post findings to the code-review/PR UI. Based on Google's Auto-Diagnose system (90%+ accuracy on 71-case study, adopted across 52k tests).

  • Credential prompt dialog abstraction

    kjuhwa/skills-hub/skills/ui/credential-prompt-dialog-abstraction Skill

    0★ repo

    Credential dialog abstraction across platforms via ui_interface::msgbox callback.

  • Agent feedback loop

    kjuhwa/skills-hub/skills/workflow/agent-feedback-loop Skill

    0★ repo

    Run an agent repeatedly in a while loop with user or evaluator feedback until a quality threshold is met.

  • Async subagent resume on missing artifact

    kjuhwa/skills-hub/skills/workflow/async-subagent-resume-on-missing-artifact Skill

    0★ repo

    When an async subagent is reported "completed" but its final message hints at unfinished work (e.g., "Now let me build…"), verify the expected on-disk artifact before moving on; if missing, use SendMessage to the agent id to finalize rather than re-dispatching a fresh agent.

  • Delegate bulk scans to explore subagent

    kjuhwa/skills-hub/skills/workflow/delegate-bulk-scans-to-explore-subagent Skill

    0★ repo

    Scan-heavy slash commands (repo imports, full-project extracts, corpus-wide refactors) must delegate bulk file/web scanning to an Agent(subagent_type=Explore) in a single call, then synthesize drafts in the main thread. Prevents the 50-70 tool call thrashing that fragments conversation history.