Add autonomous agent team configurations and task completion hooks - #26
Merged
Conversation
Sets up the .claude directory with settings, team configs, and quality-gate hooks to enable Claude Code agent teams for the three org-wide skill hierarchies defined in the README: - research-team: computer-scientist lead → principal-scientist → lead-researcher → task-layer specialists (hypothesis-generation, literature-synthesis, experiment-design, code-replication, research-writing, ieee-paper-generator, ai-engineer, auto-website-builder) + auto-benchmark (continuous) - marketing-team: cmo-marketing lead → VP orchestrators (content-marketing, demand-gen, product-marketing, community-growth, events-webinars, retention-marketing) → task-layer specialists (seo-automation, whitepaper-engine, paid-ads-manager, lead-routing, customer-intel, community-builder) - gtm-team: pm-ai-research lead → pm-lead → task-layer specialists (stakeholder-intel, competitive-research, idea-generation, prd-writer, roadmap-planner, proposal-writer, proposal-automation, calendar-pipeline) Each team config includes skill references, layer metadata, spawn prompts, and task-sizing guidance. Hooks enforce output-file quality gates on task completion and teammate idle transitions. https://claude.ai/code/session_01BMXMiDLdCm4SPh5Up4bu7M
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
This PR introduces a comprehensive agent team framework for Claude Code, enabling autonomous multi-agent workflows across marketing, research, and GTM functions. It includes three fully-configured team hierarchies, task completion validation hooks, and teammate idle detection to ensure quality output.
Key Changes
Team Configurations
.claude/teams/marketing-team/config.json): 11-agent hierarchy with CMO lead overseeing content, demand generation, product marketing, community, events, and retention functions.claude/teams/research-team/config.json): 10-agent research organization spanning hypothesis generation, literature synthesis, experimentation, engineering, and publication workflows.claude/teams/gtm-team/config.json): 8-agent product intelligence and sales enablement team with portfolio-level PM strategy, competitive research, and proposal automationQuality Gates & Hooks
.claude/hooks/TaskCompleted.sh): Validates that task-layer teammates produce required deliverables (PRDs, whitepapers, hypotheses, roadmaps, proposals, papers) before marking tasks complete.claude/hooks/TeammateIdle.sh): Prevents teammates from going idle without producing output files; applies layer-specific validation (task-layer requires file output, orchestrators require coordination notes)Configuration
.claude/settings.json): Enables experimental agent teams feature and registers both hooks for automatic execution on task completion and teammate idle eventsImplementation Details
Each team follows a hierarchical structure:
All agents include:
.mdfiles inskills/directoryThe hooks use bash pattern matching to detect required output files and provide feedback to teammates, ensuring accountability and preventing incomplete work from being marked done.
https://claude.ai/code/session_01BMXMiDLdCm4SPh5Up4bu7M