# Invoke EDD workflow
/edd "Define memory-search feature"

# CLI script (if available)
ralph edd define memory-search
ralph edd check memory-search

# Memory Search Eval

**Status**: DRAFT
**Created**: 2026-01-30

## Capability Checks
- [ ] CC-1: Search across semantic memory
- [ ] CC-2: Support filtering by type

## Behavior Checks
- [ ] BC-1: Returns ranked results
- [ ] BC-2: Handles empty queries gracefully

## Non-Functional Checks
- [ ] NFC-1: Search completes in <2s
- [ ] NFC-2: Memory usage <100MB

## Implementation Notes
- Use parallel search for performance
- Cache frequent queries

## Verification Evidence
- Test results attached

Task:
  subagent_type: "general-purpose"
  model: "sonnet"
  team_name: "edd-evaluation-team"
  name: "edd-coordinator"
  mode: "delegate"
  run_in_background: true
  prompt: |
    Execute Eval-Driven Development workflow for: $ARGUMENTS

    EDD Pattern:
    1. DEFINE - Create structured eval specifications
    2. DISTRIBUTE - Assign check types to specialists
    3. VERIFY - Validate against eval criteria
    4. CONSOLIDATE - Merge findings from all evaluators

User invokes: /edd "Define memory-search feature"

1. Team "edd-evaluation-team" created
2. Coordinator (edd-coordinator) receives task
3. 3 Teammates spawned with check-type specializations
4. Eval definition distributed:
   - Teammate 1 → Capability Checks (CC-)
   - Teammate 2 → Behavior Checks (BC-)
   - Teammate 3 → Non-Functional Checks (NFC-)
5. Teammates work in parallel (background execution)
6. Coordinator monitors progress and gathers results
7. Findings consolidated into single eval specification
8. Final eval document returned

# Teammate 1: Capability Checks
CC-1: Feature can perform X
CC-2: Feature supports Y configuration
CC-3: Feature integrates with Z system

# Teammate 2: Behavior Checks
BC-1: Feature handles error case A gracefully
BC-2: Feature returns expected response for B
BC-3: Feature maintains state across C

# Teammate 3: Non-Functional Checks
NFC-1: Response time < 100ms
NFC-2: Memory usage < 50MB
NFC-3: Security vulnerability scan passes

# Teammate sends finding to coordinator
SendMessage:
  type: "message"
  recipient: "edd-coordinator"
  content: "CC-3 defined: Feature integrates with auth system via OAuth2"

# Location: ~/.claude/tasks/edd-evaluation-team/tasks.json

# Example tasks:
[
  {"id": "1", "subject": "Define Capability Checks", "owner": "teammate-1"},
  {"id": "2", "subject": "Define Behavior Checks", "owner": "teammate-2"},
  {"id": "3", "subject": "Define Non-Functional Checks", "owner": "teammate-3"},
  {"id": "4", "subject": "Consolidate eval specification", "owner": "edd-coordinator"}
]

/edd "Define feature X" --no-swarm

# Evals saved to ~/.claude/evals/
ls ~/.claude/evals/

# View last eval
cat ~/.claude/evals/latest.md

bats tests/test_v264_edd_framework.bats

# Test swarm team creation
tests/edd/test-swarm-team-creation.sh

# Test parallel evaluation
tests/edd/test-parallel-evaluation.sh

# Listar todos los reportes de esta skill
ls -lt docs/actions/edd/

# Ver el reporte más reciente
cat $(ls -t docs/actions/edd/*.md | head -1)

# Buscar reportes fallidos
grep -l "Status: FAILED" docs/actions/edd/*.md

source .claude/lib/action-report-lib.sh
start_action_report "edd" "Task description"
# ... ejecución ...
complete_action_report "success" "Summary" "Recommendations"