Added comprehensive guidelines and responsibilities for the Data Engineer & ETL Architect role, including pipeline design, AI remediation, and compliance rules.
- Add color: orange to YAML frontmatter on all 7 paid-media agents
- Rewrite Tooling & Automation sections to be standalone:
remove specific project links and repo names, frame as
"when Google Ads MCP tools or API integrations are available
in your environment, use them to [do X]"
- Keep all practical guidance and domain expertise intact
- Rebase onto upstream/main to resolve README conflict
Made-with: Cursor
Adds a new Paid Media Division to The Agency with 7 specialized agents:
- PPC Campaign Strategist (Google/Microsoft/Amazon Ads)
- Search Query Analyst (search term analysis, negative keywords)
- Paid Media Auditor (200+ checkpoint account audits)
- Tracking & Measurement Specialist (GTM, GA4, CAPI)
- Ad Creative Strategist (RSA, Meta creative, PMax assets)
- Programmatic & Display Buyer (GDN, DSPs, ABM, partner media)
- Paid Social Strategist (Meta, LinkedIn, TikTok)
Agents include references to open-source tooling from googleadsagent.ai
that enhance these workflows with live Google Ads API access.
Author: John Williams (@itallstartedwithaidea)
https://googleadsagent.ai
Generic memory integration pattern using any MCP-compatible memory
server. Replaces vendor-specific PR #57 based on maintainer feedback.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add game-development to AGENT_DIRS in convert.sh, lint-agents.sh,
install.sh, and the CI workflow
- Remove maxdepth 1 from find commands so nested subdirectories
(e.g., game-development/unity/) are discovered
- Update CI git diff globs to **/*.md for recursive matching
- Remove strategy from lint AGENT_DIRS (playbooks, not agents)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Prepares infrastructure for the upcoming Paid Media Division (PR #83).
Registers paid-media in convert.sh, lint-agents.sh, install.sh, and
the lint-agents GitHub Actions workflow.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Autonomous TikTok/Instagram carousel agent that analyzes websites via
Playwright, generates 6-slide carousels with Gemini, publishes via
Upload-Post API, and iteratively improves through analytics feedback.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Reflect the switch to agents/ (plural), hex color codes, mode: subagent,
and @agent-name invocation in both the OpenCode integration README and the
main README's OpenCode section.
Without mode: subagent, all 68 agents default to mode: all and appear as
primary agents the user Tab-cycles through, making the UX unusable.
With mode: subagent they are invoked on-demand via @agent-name.
OpenCode only accepts hex color codes (e.g. #00FFFF), not named colors
(e.g. cyan). Add resolve_opencode_color() with a 14-entry lookup table
and wire it into convert_opencode(). Colors already in hex pass through.
OpenCode docs now specify agents/ (plural) as the standard directory name;
agent/ (singular) is legacy backwards-compat. Update the converter output
path, installer source/dest paths, and .gitignore entry accordingly.
- Remove workflow example (too product-specific)
- Strip all install commands, API keys, and product references
- Replace tool-specific code blocks with generic JSON schemas
- Add Python matching example showing the resolution pattern
- Agent now teaches the concept, not a specific product
New specialized agent: Identity Graph Operator - operates a shared identity
graph so multiple agents in a system all resolve to the same canonical entity.
Prevents duplicate records, conflicting actions, and cascading errors when
agents encounter the same real-world entity from different sources.
New example workflow: Multi-Agent Shared Identity - step-by-step walkthrough
of 3 agents (Support, Backend, Analytics) handling the same customer across
email, phone, and web channels with shared identity resolution.
Enhanced Agentic Identity & Trust Architect with a section showing how it
complements the Identity Graph Operator (agent identity vs entity identity).
PR #67 already merged a better-fit engineering/engineering-technical-writer.md.
Keep only Compliance Auditor + lint workflow fix.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Three new specialist agents filling clear gaps in the current roster:
- engineering/engineering-data-engineer.md: ETL/ELT pipelines, Delta Lake,
Apache Spark, dbt, Medallion Architecture (Bronze/Silver/Gold), streaming
with Kafka, data quality with Great Expectations, cloud lakehouse platforms
(Fabric, Databricks, Synapse, Snowflake, BigQuery)
- engineering/engineering-technical-writer.md: Developer documentation,
API reference (OpenAPI), README templates, tutorials, docs-as-code
(Docusaurus/MkDocs), content quality standards, DX metrics
- specialized/specialized-developer-advocate.md: Developer relations,
DX auditing and improvement, technical content creation, community
building, GitHub engagement, conference talks, product feedback loops
Each agent follows the standard template with YAML frontmatter, identity,
core mission, critical rules, technical deliverables with working code,
workflow process, communication style, and success metrics.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
