LLM access, durable agent jobs and batch content pipelines in one library. Consolidation of llm-scripting-kit, job-kit and content-pipeline-kit.
Plugin llm-kit from marketplace plugins-kit in kitaekatt/plugins-kit. Commands read from the repo's manifest — today.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
background-pipelineUse when orchestrating a content-pipeline run through Claude background sessions. Do NOT use for a worker's own unit (execute-work-unit) or the inline driver.
content-pipeline-domainUse when designing, building, or porting an LLM-in-the-loop batch content pipeline. Do NOT use for one-off LLM calls or non-batch chat interactions.
directUse when the user types /direct to list machines, read or message a session, or ask a local LLM via the llm-kit relay. Do NOT use on the model's own initiative.
execute-work-unitUse when acting as a content-pipeline background worker completing one work unit. Do NOT use for orchestrating a run (background-pipeline) or interactive use.
openrouter-accountUse when checking, setting, or rotating the OpenRouter API key, or diagnosing 401/402 errors. Do NOT use for general LLM/translation work.
workflow-pipelineUse when orchestrating a content-pipeline run via the Workflow tool. Do NOT use for a worker's own unit (execute-work-unit) or driver (background-pipeline).
pipeline-workerOne-unit content-pipeline worker. Claims exactly one unit through a consumer's protocol mount, produces an answer, and submits it. An agent definition a consumer may select when launching a background session through llm-kit's dispatcher (`llm_kit.pipeline.execution.drivers.claude_bg`), by passing t
bash "${CLAUDE_PLUGIN_ROOT}/hooks/run-direct-hook.sh" userpromptsubmit/direct_enable.py
bash "${CLAUDE_PLUGIN_ROOT}/hooks/run-direct-hook.sh" pretooluse/direct_gate.py
bash "${CLAUDE_PLUGIN_ROOT}/hooks/run-direct-hook.sh" sessionend/direct_revoke.py
Provides plugin-ecosystem, orchestrate, debug-context, verbose-updates, and arewedone skills for plugin browsing, delegated work, answering why-did-you questions from context, progress communication, and auditing whether session work is complete.
5 skills · 5 agents
Multi-agent pre-push code review for git (/git-code-review) with per-finding validation and declined-findings memory.
1 skill · 5 agents
Multi-agent code review for pending Perforce changelists (/p4-code-review) -- auto-shelves, reviews, cleans up.
1 skill · 5 agents
Unreal Engine automation: Python API for asset inspection and data extraction; MCP server for live Editor authoring (actors, Blueprints, materials, PIE)
4 skills · hooks
Is the user at the keyboard, away, or has the work been handed over, and how should Claude wait, ask and recap in each case? Sits above bootstrap, which provisions the environment, because presence is a policy question bootstrap cannot answer for any session.
3 skills · hooks
Author and audit every md file a project loads or ships -- CLAUDE.md, SKILL.md, project docs, and their cross-references -- for placement, cohesion, and drift.
4 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.
5 commands
5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.
5 skills · 16 commands · 4 agents · hooks
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.