lespaceman/athena-workflow-marketplace

Semantic browser interface for LLM agents - token-efficient page snapshots via Puppeteer/CDP, with a skill for live page interaction

Shared feature mapping plus live product exploration and evidence capture for downstream testing workflows

Use ClickUp tasks, lists, docs, and workspace state from agents via the official ClickUp MCP server

Exploratory testing charters — frame risk hypotheses and investigation focus before coverage planning begins

Create distinctive, production-grade frontend interfaces with high design quality. Generates creative, polished code that avoids generic AI aesthetics.

Use Linear issues, projects, and workflow state from engineering agents via the official Linear MCP server

Bundled non-deprecated skills from Matt Pocock's Skills For Real Engineers (https://github.com/mattpocock/skills): engineering skills plus caveman, handoff, write-a-skill, git-guardrails-claude-code, and setup-pre-commit.

Export markdown files to clean, dark-themed PDFs

Playwright execution layer for analysis, authoring, review, and flake repair; full workflows also require app-exploration and test-analysis

Regression testing scopes — define rerunnable confidence across changed and high-risk areas before automation selection

Robot Framework execution layer for analysis, authoring, review, and flake repair; full workflows also require app-exploration and test-analysis

Set up the engineering workflow's per-repo context: an `## Agent skills` block in AGENTS.md/CLAUDE.md plus `docs/agents/` capturing the issue tracker (GitHub, GitLab, or local markdown), triage label vocabulary, and domain doc layout, with the full workflow skill map recorded as a reference inventory.

Browse, search, and install shadcn/ui components via the shadcn MCP server, plus project-aware knowledge of shadcn/ui patterns, theming, and registry authoring

Site-specific automation patterns and knowledge for popular websites (Airbnb, Amazon, Apple Store)

Smoke testing scopes — define the minimum critical-path confidence checks before selecting runnable automation

TanStack Start guidance for scaffolding examples, routing patterns, full-stack app structure, and agent-friendly implementation workflows

Shared coverage planning, test-case generation, and spec review grounded in exploration evidence

WebBench benchmark runner - executes real-world browser tasks from the Halluminate/WebBench dataset, scores via LLM-as-judge, and produces evaluation reports

Scaffold complete Athena workflow packages with workflow definitions, plugin pins, marketplace registration, and validation gates