Autonomous TDD pipeline for building features end-to-end. Chains PRD → gate tests → implementation → live validation → remediation in a self-correcting loop. Uses headless Claude sessions via the relentless CLI for multi-phase execution. Includes autoresearch for autonomous skill optimization.
Plugin relentless from marketplace fe-vibe in sarah-hord-db/vibe. Commands read from the repo's manifest — 1 month ago.
autoresearchAutonomously optimize any Claude Code skill by running it repeatedly, scoring outputs against binary evals, mutating the prompt, and keeping improvements. Based on Karpathy's autoresearch methodology. Use when: optimize this skill, improve this skill, run autoresearch on, make this skill better, sel
relentless-devloopRun the app and test it with Chrome DevTools MCP as a headless browser. Navigates routes, clicks elements, fills forms, captures screenshots, checks console/network errors. Returns structured pass/fail results. Usable standalone or delegated from validator/implementer.
relentless-gatesRead a PRD's Agent Handoff block and generate failing TDD gate tests for each machine-verifiable acceptance criterion. Run between relentless-prd and relentless-implement.
relentless-implementRun relentless auto-continuing implementation on a PRD or task description. Launches headless Claude sessions in the background with progress tracking.
relentless-orchestrateMaster orchestrator for the relentless pipeline. Chains implement → validate → remediate → re-validate in a loop until all gates pass and live execution is clean. Owns the circuit breaker and escalation decisions. Follows RelentlessAgent principles — fresh context per phase, first-person progress su
relentless-prdGenerate a structured PRD through interactive discovery. Outputs a markdown file with testable acceptance criteria and an agent handoff block, ready for `relentless` auto-continuing implementation.
relentless-preflightPre-flight environment check before running the relentless pipeline. Validates dependencies, Databricks profile, ports, PRD structure, and writes _relentless_config.json for downstream phases.
relentless-remediateTargeted code fixer. Reads _validation_report.json, patches only auto-fixable errors with minimal changes. Never runs tests or validates its own fixes — the validator re-checks independently.
relentless-validatePure QA agent. Runs live execution validation after TDD gates pass. Uses Chrome DevTools (frontend) and Databricks CLI (backend) to detect integration failures. Reports structured errors — never writes code fixes.
Common Field Engineering workflows for Aha! Ideas, sizing, documentation, security, support, troubleshooting, TODO management, account transitions, RFP responses, QBR decks, humanizer, SA daily/weekly planning, and showcases
33 skills · 12 agents
Complete Databricks workflow tools: authentication, queries, deployments, workspace setup, and demos
15 skills · 1 agent
Internal Databricks tools: Aha! Ideas and eng blocker search, GTM data queries, Genie Rooms, Confluence, Glean search, Slack messaging, and AWS authentication
12 skills · 1 agent
Google Docs, Sheets, Slides, Drive, Gmail, Calendar, Tasks, and Forms with professional formatting, charts, formulas, and hyperlinks
10 skills · 1 agent
Setup, configuration, and validation for the vibe environment
7 skills · 1 agent
Databricks AI development toolkit (for FE and customers) with skills for data engineering, ML, and AI agents plus MCP tools for direct Databricks operations
6 skills · hooks
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 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
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
8 skills · 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.