claude-api
claudeClaude API and SDK documentation skill for building LLM-powered applications
19 skills
Automated regression testing and improvements for your prompts, context, and tool calls.
Not in a marketplace yet, so it loads for one session with --plugin-dir.
Plugin bitfab in Project-White-Rabbit/bitfab-claude-plugin. Commands read from the repo's manifest — today.
This plugin runs code on your machine — its hooks fire automatically on events like tool use and it starts local MCP servers. The exact commands are listed below; read them before installing.
assistantRetired. Only use when the user explicitly types the bitfab assistant command by name; it tells them the assistant has been retired. Never use it for requests about traces, datasets, labels, verdicts, replays, experiments, or improving a traced function: handle those directly with the Bitfab MCP too
setup-analyze-repoAnalyze Repo phase of the Bitfab Setup flow. Invoked by the setup flow; not run directly
setup-approachApproach phase of the Bitfab Setup flow. Invoked by the setup flow; not run directly
setup-cleanupCleanup phase of the Bitfab Setup flow. Invoked by the setup flow; not run directly
setup-cloudCloud replay phase of the Bitfab Setup flow. Invoked by the setup flow; not run directly
setup-db-snapshotDB Snapshot phase of the Bitfab Setup flow. Invoked by the setup flow; not run directly
setup-explainExplain phase of the Bitfab Setup flow. Invoked by the setup flow; not run directly
setup-inspectInspect phase of the Bitfab Setup flow. Invoked by the setup flow; not run directly
setup-instrumentInstrument phase of the Bitfab Setup flow. Invoked by the setup flow; not run directly
setup-loginLogin phase of the Bitfab Setup flow. Invoked by the setup flow; not run directly
setup-modifyModify phase of the Bitfab Setup flow. Invoked by the setup flow; not run directly
setup-replayReplay phase of the Bitfab Setup flow. Invoked by the setup flow; not run directly
setup-session-logsSession Logs phase of the Bitfab Setup flow. Invoked by the setup flow; not run directly
setup-switch-orgSwitch Org phase of the Bitfab Setup flow. Invoked by the setup flow; not run directly
setup-templatesTemplates phase of the Bitfab Setup flow. Invoked by the setup flow; not run directly
setupSet up and maintain Bitfab tracing, replay registries, and cloud replay. Use for instrumenting AI/LLM code, adding observability or evaluation, tracing another workflow, changing captured inputs/outputs, re-instrumenting a function, moving side effects across trace boundaries, inspecting missing tra
update-pluginUpdate plugin phase of the Bitfab Update flow. Invoked by the update flow; not run directly
update-sdkUpdate SDK phase of the Bitfab Update flow. Invoked by the update flow; not run directly
updateUpdate Bitfab plugin and SDK to the latest versions. TRIGGER when: user wants to update Bitfab, upgrade the SDK, get the latest version, or says 'update bitfab', 'upgrade SDK', 'latest version'. SKIP when: user wants to instrument code or iterate on traces
Bitfabruns: ${CLAUDE_PLUGIN_ROOT}/scripts/mcp-server
${CLAUDE_PLUGIN_ROOT}/scripts/session-start
${CLAUDE_PLUGIN_ROOT}/scripts/user-prompt-submit
${CLAUDE_PLUGIN_ROOT}/scripts/capture-hook PreToolUse
${CLAUDE_PLUGIN_ROOT}/scripts/capture-hook Stop
${CLAUDE_PLUGIN_ROOT}/scripts/capture-hook SubagentStop
${CLAUDE_PLUGIN_ROOT}/scripts/capture-hook PreCompact
${CLAUDE_PLUGIN_ROOT}/scripts/capture-hook SessionEnd
Problems found in this repo's manifests
Claude API and SDK documentation skill for building LLM-powered applications
19 skills
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
2 skills · 2 commands · 2 agents · 1 MCP server
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF, hardcoded secrets, and 25+ other vulnerability classes.
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
RuVLLM local inference with chat formatting, MicroLoRA fine-tuning, and SONA adaptation
3 skills · 1 command · 1 agent
Skill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.
1 skill
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.