From atum-workflows
Surface and validate Claude's hidden assumptions about the project for user confirmation. Use when starting a new project, onboarding to a codebase, before major architectural decisions, or when the user says "hypotheses", "tu pars du principe que", "assumptions", "common ground". Invoke with /common-ground [--list] [--check] [--graph].
npx claudepluginhub arnwaldn/atum-plugins-collection --plugin atum-workflowsThis skill uses the workspace's default tool permissions.
Surface Claude's implicit assumptions about the project so the user can validate or correct them before work begins.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Executes pre-written implementation plans: critically reviews, follows bite-sized steps exactly, runs verifications, tracks progress with checkpoints, uses git worktrees, stops on blockers.
Surface Claude's implicit assumptions about the project so the user can validate or correct them before work begins.
Parse $ARGUMENTS:
| Flag | Mode | Description |
|---|---|---|
| (none) | Default | Surface & Adjust: two-phase interactive flow |
--list | List | Read-only view of all tracked assumptions |
--check | Check | Quick validation of current assumptions |
--graph | Graph | Generate Mermaid diagram of reasoning structure |
| Topic | Reference | Load When |
|---|---|---|
| Assumption Types & Tiers | references/assumption-classification.md | Classifying assumptions, determining type or tier |
| File Management | references/file-management.md | Storage operations, project ID, ground file format |
| Reasoning Graph | references/reasoning-graph.md | Using --graph flag, generating Mermaid diagrams |
git remote get-url origin 2>/dev/null
If found, use URL as project ID. Fallback: current working directory path. Sanitize to filesystem-safe string for storage path.
Read configuration files to infer assumptions:
package.json, tsconfig.json, .eslintrc*, .prettierrc (JS/TS)pyproject.toml, setup.py, ruff.toml (Python)Cargo.toml (Rust), go.mod (Go), pom.xml (Java)docker-compose.yml, .env.example, Dockerfile.github/workflows/, CI configsCLAUDE.md, .claude/ configPhase 1 — Surface & Select: Present assumptions grouped by category via AskUserQuestion (multiSelect):
For uncertain items, ask direct clarifying questions.
Phase 2 — Adjust Tiers: Present selected assumptions with proposed tiers via AskUserQuestion:
Write to ~/.claude/common-ground/{project_id}/COMMON-GROUND.md and ground.index.json.
See references/file-management.md for formats.
## Common Ground Complete
**Project:** {project_name}
**Tracked Assumptions:** {count}
- ESTABLISHED: {n} (high confidence)
- WORKING: {n} (medium confidence)
- OPEN: {n} (needs validation)
Load and display COMMON-GROUND.md grouped by tier. If no file exists, redirect to default mode.
Quick validation: present assumptions via AskUserQuestion with options "All valid", "Some need updates", "Full review needed". Update last_validated timestamp.
## Reasoning Graph