caveman
claudeTalk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Build, run, review, and share version-controlled Python financial models in Bridge Town.
Plugin bridge-town from marketplace bridge-town in Bridge-Town/claude-plugins. Commands read from the repo's manifest — 1 month ago.
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.
collaborate-on-projectSet up and manage multi-analyst collaboration on a Bridge Town project. Use this skill when a user wants to share a project with teammates, run a pull-request review workflow, or create/clone internal templates. For solo what-if / sensitivity / compare-assumptions work that does not need PR review c
commit-filesAtomically commit multiple file creates, updates, and deletes in one git commit. Use this skill when you need to land related changes (model, entrypoint, docs, fixtures) together so the repo is never in a half-updated state.
connect-google-sheetsConnect a Google Sheet to a Bridge Town project and import data for modelling. Use this skill when your source data lives in Google Sheets and you want to pull it into a Bridge Town project for version-controlled analysis.
convert-excel-workbookConvert an existing Excel financial model into a reviewable Bridge Town Python project — profile, generate, review findings, apply, run, and dashboard. Use when a user wants to migrate a spreadsheet model rather than ingest spreadsheet data.
create-cash-flow-modelBuild a cash flow model covering operating, investing, and financing activities. Use this skill to translate P&L and balance-sheet assumptions into a direct or indirect cash flow statement showing runway and burn.
create-dashboardCreate a visual dashboard from a Bridge Town model run output. Use this skill when the user wants a chart or table view of their model results. Covers chart type discovery, model output structure, and the full create → share flow.
create-expense-modelBuild an operating expense (OPEX) model with departmental budgets in Python. Use this skill to forecast non-headcount spend across categories such as marketing, software, and facilities, and produce a three-statement-ready OpEx schedule.
create-headcount-modelBuild a headcount plan with loaded costs, hiring schedules, and attrition. Use this skill when you need to model team growth over time and see total personnel costs by department and year.
create-marketplace-gmv-modelForecast GMV, take rate revenue, and supply/demand dynamics for a marketplace. Use this skill to project transaction volume across buyer and seller cohorts and translate GMV to net revenue via a configurable take rate.
create-revenue-modelBuild a bottom-up or top-down revenue forecasting model in Python. Use this skill when you need a structured ARR forecast with per-product-line growth rates, churn, and multi-year outputs.
create-unit-economics-modelModel CAC, LTV, payback period, and expansion revenue for a SaaS business. Use this skill when you need to evaluate the health and efficiency of your go-to-market motion at the cohort level.
create-usage-based-pricing-modelForecast revenue for usage-based or consumption pricing models (API calls, seats, compute). Use this skill when a product charges by consumption rather than flat subscription, and you need to tie usage growth curves to revenue.
discover-and-query-dataDiscover data sources attached to a project and query them with SQL. Use this skill when the user wants to explore or analyse project data without knowing what tables or columns are available.
gsheet-finance-stylesUse this skill whenever a Bridge Town agent has published values to a Google Sheet and the user wants finance-grade visual formatting. Bridge Town no longer applies cell formatting programmatically — use `get_google_spreadsheet_metadata` with `include_format_presets=true` to discover the style vocab
gsheet-formattingUse this skill whenever a Bridge Town agent is about to publish model output to Google Sheets, or whenever a user asks to push, send, export, publish, sync, or write model results to a spreadsheet. Shape the model output for the bounded preview-and-confirm publish flow before any write.
native-sheetsUse this skill whenever an agent is deciding whether to create a native Bridge Town sheet vs. a Google Sheet, is about to hand-author or patch a `.btsheet.json` file, is calling any of create_native_sheet, get_native_sheet, write_native_sheet_cells, format_native_sheet, recalculate_native_sheet, or
run-scenario-analysisRun what-if / sensitivity / compare-assumptions analysis on an existing Bridge Town project using a branch-based workflow. Create a branch, edit assumptions there, run and compare against the base case, then merge, keep, or discard. Use this when the user wants to explore how changing assumptions af
scenario-analysisBuild a *new* scenario/sensitivity model from scratch in Python — defines BASE_ASSUMPTIONS, SCENARIOS, and SENSITIVITY_DRIVERS for a project that does not yet have a what-if model. Use this when the user needs model code authored. For running what-if analysis on an *existing* model via branches, use
scenario-sheetsUse this skill when a user wants to explore what-if changes to a native sheet's input assumptions -- branch, edit cells, run the model, compare against the base case, then merge/keep/discard -- without overwriting main. Trigger on requests like \"what if the growth rate were 8% instead of 5%\", \"tr
working-with-bridge-townOperating guide for the Bridge Town MCP tools. Use at the start of any Bridge Town task: building, editing, or running a financial model, reading run outputs or native sheets, working with branches and pull requests, or publishing dashboards and Google Sheets. Covers tool discovery, the sandbox cont
/bridge-town:statusCheck the Bridge Town connection and summarize recent model activity
model-reviewerReviews a Bridge Town model change (a branch or pull request) before it is merged. Use when the user asks to review, check, or sanity-test a model branch, scenario, or pull request. Runs both sides and reports findings; never merges or edits.
bridge-townconnects to: https://api.bridgetown.builders/mcp
printf '%s\n' '{"hookSpecificOutput":{"hookEventName":"PreToolUse","permissionDecision":"ask","permissionDecisionReason":"Bridge Town: this action cannot be undone, or it publishes, shares, or changes
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
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
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.