caveman
claudeTalk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Build and run AI compliance agents by chatting.
Plugin pitcrew from marketplace pitcrew-plugin in pitcrew-agents/pitcrew-plugin. Commands read from the repo's manifest — yesterday.
chat-modeAnswer questions about an existing agent — tool choices, data mappings, workflow logic, what a tool does, why a decision was made. Activate when user asks a question and state.agent_spec exists. Read-only — never modifies state.
config-modeGenerate the configurations block (per-run settings panel) for a completed agent. Analyse tool_call and llm_call tasks for hardcoded params that users should be able to tune per-run. Activate after an agent has been built and knowledge has been generated.
edit-modeBuild, validate and test an agent from an approved plan. Activate when state.plan exists and user wants to build the agent, or when user requests changes to an existing agent structure, mappings, or tools.
file-handlingRead and analyze files uploaded by the user. Use when the user references a file, data, document, CSV, or PDF, or when uploaded files are relevant to the current request. Files are at /files/, workspace cache at /workspace/.
knowledge-modeGenerate the knowledge section for a completed agent: good_examples, careful_zones, and known_limitations. Activate after an agent has been built and validated, when knowledge needs to be documented.
loop-modeAdd a loop swimlane to an agent. Activate when the user's workflow needs to process each item in a list — e.g. "for each email", "for every client", "process each row". Loop is a swimlane-level feature, not a task_type.
orchestratorRoute user requests to the correct worker. Activate for every turn. Delegate to plan-worker when user wants to build a new workflow. Delegate to edit-worker when a plan is approved and agent needs building. After edit-worker completes: run knowledge-worker, then config-worker, then present the final
plan-modeGather workflow intent, discover tools from /tools/ filesystem, clarify requirement gaps, produce a structured plan spec for approval. Activate when user wants to build a new agent, state.plan is None, or user wants to change an existing plan.
studio-build-modeStep-by-step procedure for building a studio-forms JSON artifact using the studio_* MCP tools. Use when the user asks to build a form, intake, questionnaire, or any client-facing document. Always starts from source material uploaded to a document collection, then covers field types, who fills each f
trigger-automationSet up a trigger that fires an existing PitCrew agent automatically — on a cron schedule, when an external event happens in Gmail / Drive / Slack / etc., or chained to another agent's bulk run. Activate when the user asks to schedule an agent, run it on an event, or wire two agents together.
bulk-run-automationRun an existing PitCrew agent in bulk over N items at once: N PDFs, N rows of a spreadsheet, N files in a Drive folder, N objects under an S3 prefix. Activate when the user asks to process a batch, a folder, a sheet, a mailbox export, or anything phrased as "for each of these, run the agent".
chat-workerUse for read-only questions about the current agent, uploaded files, or anything that does not require building or modifying an agent. Never modifies state.
config-workerUse after knowledge-worker completes. Generates the configurations block (per-run settings panel) for a completed agent draft. Must be dispatched with the completed agent_spec JSON in the task prompt.
edit-workerUse when the user has approved a plan and the agent JSON needs to be built, or when they want to modify an existing agent. Produces the agent_spec JSON spec from an approved plan. Must be dispatched with the approved plan in the task prompt.
knowledge-workerUse after edit-worker has produced an agent_spec. Generates the knowledge section (good examples, careful zones, known limitations) for the agent. Must be dispatched with the completed agent_spec JSON in the task prompt.
plan-workerUse when the user describes a new workflow to build, or when they want to change an existing plan. Discovers available tools from the plugin's tools/ catalog and produces a plan spec (not agent JSON). The orchestrator should dispatch here first, then show the resulting plan to the user for approval.
studio-builderUse when the user wants to build, edit, or view a studio form artifact. Builds forms by calling the studio_* MCP tools in sequence. Always call studio_create_session first, then studio_write_fields, then studio_write_structure, then studio_validate_form, then show the result. Do NOT use plan-worker
PitCrew MCPconnects to: https://mcp.gopitcrew.com/mcp
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
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
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Package any website or local web build into a lightweight desktop app with Pake CLI.
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.