mindforge-list-phase-assumptions
This Claude Code skill analyzes a specified project phase and explicitly surfaces the agent's underlying assumptions about technical approach, implementation sequence, scope boundaries, risk areas, and dependencies before planning begins. Use it when starting a new phase to identify potentially flawed assumptions early, enabling stakeholders to course-correct through conversation rather than discovering misalignments during execution.
git clone --depth 1 https://github.com/sairam0424/MindForge /tmp/mindforge-list-phase-assumptions && cp -r /tmp/mindforge-list-phase-assumptions/.agent/skills/mindforge-list-phase-assumptions ~/.claude/skills/mindforge-list-phase-assumptionsSKILL.md
<objective> Analyze a phase and present the agent's assumptions about technical approach, implementation order, scope boundaries, risk areas, and dependencies. Purpose: Help users see what the agent thinks BEFORE planning begins - enabling course correction early when assumptions are wrong. Output: Conversational output only (no file creation) - ends with "What do you think?" prompt </objective> <execution_context> @.agent/workflows/mindforge-list-phase-assumptions.md </execution_context> <context> Phase number: $ARGUMENTS (required) Project state and roadmap are loaded in-workflow using targeted reads. </context> <process> 1. Validate phase number argument (error if missing or invalid) 2. Check if phase exists in roadmap 3. Follow list-phase-assumptions.md workflow: - Analyze roadmap description - Surface assumptions about: technical approach, implementation order, scope, risks, dependencies - Present assumptions clearly - Prompt "What do you think?" 4. Gather feedback and offer next steps </process> <success_criteria> - Phase validated against roadmap - Assumptions surfaced across five areas - User prompted for feedback - User knows next steps (discuss context, plan phase, or correct assumptions) </success_criteria>
Publish a skill to the npm registry (or private registry).
Add an idea to the backlog parking lot (999.x numbering)
Add phase to end of current milestone in roadmap
Generate tests for a completed phase based on UAT criteria and implementation
Capture idea or task as todo from current conversation context
Audit milestone completion against original intent before archiving
Cross-phase audit of all outstanding UAT and verification items
Run all remaining phases autonomously — discuss→plan→execute per phase