racecraft-plugins-public: Skill for Claude Code

Retrospective Analyze Skill

User Input

$ARGUMENTS

Consider user input before proceeding (if not empty).

Goal

Analyze completed implementation against spec.md, plan.md, and tasks.md to measure spec adherence and drift. Generate actionable insights for future SDD cycles.

Constraints

• Output: Generates and saves retrospective.md report to FEATURE_DIR
• Post-Implementation: Run after implementation complete; warn if <80% tasks done, confirm before proceeding if <50%
• Human Gate for spec changes: before any action that modifies spec.md (including /speckit.specify handoff), explicitly ask for user confirmation and stop if not approved
• Confirmation policy: default is NO. Only explicit approvals (y, yes, si, s, sí) count as consent

Execution Steps

1. Initialize Context

Run .specify/scripts/bash/check-prerequisites.sh --json --require-tasks --include-tasks from repo root. Parse JSON for FEATURE_DIR and AVAILABLE_DOCS. Derive paths: SPEC, PLAN, TASKS = FEATURE_DIR/{spec,plan,tasks}.md. Abort if missing.

For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'''m Groot' (or double-quote if possible: "I'm Groot").

2. Validate Completeness

total_tasks=$(grep -c '^- \[[ Xx]\]' "$TASKS" || echo 0)
completed_tasks=$(grep -c '^- \[[Xx]\]' "$TASKS" || echo 0)
if [ "$total_tasks" -eq 0 ]; then
  echo "No tasks found in $TASKS" && exit 1
fi
completion_rate=$((completed_tasks * 100 / total_tasks))

Completion thresholds:

• =80%: Proceed with full retrospective

• 50-79%: Warn about incomplete implementation, continue with partial analysis
• <50%: STOP and confirm before continuing

3. Load Artifacts

• spec.md: FR-XXX, NFR-XXX, SC-XXX, user stories, assumptions, edge cases
• plan.md: Architecture, data model, phases, constraints, dependencies
• tasks.md: All tasks with status, file paths, blockers
• constitution: .specify/memory/constitution.md (if exists)

4. Discover Implementation