claude-code-config
ListedOpinionated Claude Code harness — idea → merged PR via a multi-agent AGILE pipeline with cmux observability, worktree-isolated parallel builds, and TDD+review gates.
Bundles
Everything this plugin ships — skills, agents, commands, hooks, and MCP servers it bundles.
Skills (20)
gamma-deck
Create professional presentations using Gamma.app's AI generation platform. This skill handles the full pipeline: conducting an iterative interview to build a detailed brief, writing a structured synopsis optimized for slide generation, then calling the Gamma MCP tools (get_themes, get_folders, generate) to produce the deck. MANDATORY TRIGGERS: Any request involving "presentation", "deck", "slides", "pitch deck", "keynote", "gamma", "gamma.app", or any mention of creating a visual presentation from content. Also trigger when the user asks to "present" findings, results, a project, or a plan — even if they don't explicitly say "presentation". If the user says "make a deck about X" or "I need to present X to Y", this skill applies. REQUIRES: Gamma MCP connector must be connected. If the Gamma MCP tools (generate, get_themes, get_folders) are not available, inform the user they need to connect the Gamma connector first via the MCP registry.
vision-doc-review
Conduct a thorough multi-dimensional review of a high-level vision or concept document for an AI-powered application. Use this skill whenever a user wants to review, critique, analyse, or stress-test a vision document, approach document, concept paper, or high-level design spec — especially in the context of Temenos T24/jBC modernisation, core banking transformation, or AI/LLM pipeline applications. Trigger this skill when the user says things like "review this document", "critique this vision doc", "analyse this approach", "stress-test this concept", "give me feedback on this spec", or uploads/pastes a document and asks for structured feedback. Also trigger when the user asks for a "multi-angle review" or wants findings with recommendations in a structured format.
build-stories
Batch build all incomplete stories across epics — thin wrapper that shells out to the external `sdlc` controller, which owns the deterministic state machine.
coverage
Use when the user wants to assess test coverage, close meaningful gaps, and raise confidence with targeted tests and verification.
brainstorm
Senior PM persona — interview-driven requirements discovery that produces REQUIREMENTS.md. Integrates with project-init and generate-epics.
create-epic
Interactively brainstorm and generate a new AGILE epic file with user stories. Creates docs/stories/epic-XX-[name].md and updates STORIES.md.
create-story
Interactively add one or more new stories to an epic. If no epic number is given, infers the best-fit epic from the requirement and STORIES.md. If the requirement is too large for a single story, recommends running /create-epic instead.
fix-issue
Autonomously fix one or many GitHub issues end-to-end — thin wrapper that shells out to the external `sdlc` controller, which owns the deterministic fix pipeline.
generate-epics
Generate modular AGILE epics and user stories from REQUIREMENTS.md. Creates STORIES.md overview and individual epic files in docs/stories/.
project-init
Bootstrap a new repo with git, GitHub remote, labels, CLAUDE.md, and a PROJECT-SEED.md for handoff to /brainstorm.
resume-build-agents
Resume development work using specialized agents (backend, frontend, DevOps, QA, containers). Auto-selects agents based on story type and tech stack.
claude-docs
Explore and research official Claude Code documentation at code.claude.com/docs. Auto-triggers on Claude Code usage questions.
Show all 20 bundled skills Showing all 20 bundled skills
create-agent
Use when you want to create a new sub-agent that Claude can delegate tasks to. Generates an agents/<name>.md definition.
create-command
Use when you want to create a simple slash command (single markdown file). For complex needs, use /create-skill instead.
create-skill
Use when you want to create a new skill with supporting files, tool restrictions, or auto-invocation. Generates a skills/<name>/ directory.
demo
Demonstrate completed features using Playwright MCP browser automation. Auto-discovers latest sprint/story and walks through a live demo.
design-e2e
Design and execute Playwright E2E test cases from epic/story acceptance criteria. Generates test specs and runs them.
execute-e2e-tests
Run and manage Playwright E2E tests. Setup, write, execute, and debug end-to-end tests for any project.
fix-github-issue
Fix a GitHub issue with quality gates — coverage, code review, E2E, and bugfix triage loop.
telegram
Post messages to Telegram via Bot API. Supports Markdown formatting, reply-to, and silent mode.
Agents (9)
Commands (11)
Hooks (9)
Quality Score: 49/100
Details
- Author
- fxmartin
- Repository
- fxmartin/claude-code-config
- Created
- 4 months ago
- Last Updated
- today
- Language
- Python
- License
- MIT