maestro-flow 0.3.37 → 0.3.39

package/.codex/skills/maestro-analyze/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: maestro-analyze
-description: Multi-dimensional analysis via CSV wave pipeline. Diamond topology — CLI exploration agents (Wave 1), 6-dimension scoring agents (Wave 2), decision synthesis agent (Wave 3). Supports dual depth with -q quick mode and --gaps issue root cause analysis. Replaces maestro-analyze command.
+description: Multi-angle analysis with CLI-assisted exploration
 argument-hint: "[-y|--yes] [-c|--concurrency N] [--continue] \"<phase|topic> [-q|--quick] [--gaps [ISS-ID]]\""
 allowed-tools: spawn_agents_on_csv, Read, Write, Edit, Bash, Glob, Grep, AskUserQuestion
 ---
@@ -54,6 +54,7 @@ Wave-based multi-dimensional analysis using `spawn_agents_on_csv`. Diamond topol
 |                                                                           |
 +---------------------------------------------------------------------------+
 ```
+
 </purpose>
 
 <context>
@@ -210,14 +211,14 @@ Create both directories.
 
 3. **Quick mode routing**: If QUICK_MODE, generate only wave 3 (synthesis/decide) task in CSV. Skip exploration and scoring.
 
-3b. **Gaps mode routing** (if GAPS_MODE):
+3b. **Gaps mode routing** (if GAPS_MODE) — follow `~/.maestro/workflows/issue-gaps-analyze.codex.md` for full CSV wave pipeline:
    - Load issues from `.workflow/issues/issues.jsonl`
    - If `gapsIssueId`: load single issue, validate existence
    - If no ISS-ID: filter `status == "open" || status == "registered"`
-   - For each issue, generate an exploration task (wave 1) focused on issue context
-   - Generate a synthesis task (wave 2) that writes analysis records back to issues.jsonl
-   - Skip standard dimension scoring (wave 2 in normal mode)
-   - Pipeline: Load Issues → CLI Exploration per issue → Root Cause Synthesis → Write issue.analysis → Output context.md
+   - Classify & group issues by location/component overlap
+   - Generate tasks.csv: wave 1 = one exploration row per issue, wave 2 = one synthesis row per group
+   - Execute via spawn_agents_on_csv (wave 1 parallel per issue, wave 2 parallel per group)
+   - Pipeline: Load Issues → Classify & Group → CSV Generation → Wave 1: Explore → Wave 2: Synthesize → Write issue.analysis → Output context.md
    - On completion: append history entry `{ action: "analyzed", at: <ISO>, by: "maestro-analyze --gaps" }` per issue
 
 4. **Dimension and perspective selection** (full mode):
@@ -250,7 +251,7 @@ Filter `wave == 1 && status == pending` from master CSV. No prev_context (no pre
 spawn_agents_on_csv({
   csv_path: `${sessionFolder}/wave-1.csv`,
   id_column: "id",
-  instruction: buildExplorationInstruction(sessionFolder),
+  instruction: buildExplorationInstruction(sessionFolder),  // agent: ~/.codex/agents/cli-explore-agent.toml
   max_concurrency: maxConcurrency,
   max_runtime_seconds: 3600,
   output_csv_path: `${sessionFolder}/wave-1-results.csv`,
@@ -275,7 +276,7 @@ Filter `wave == 2 && status == pending` from master CSV. Build `prev_context` fr
 spawn_agents_on_csv({
   csv_path: `${sessionFolder}/wave-2.csv`,
   id_column: "id",
-  instruction: buildScoringInstruction(sessionFolder),
+  instruction: buildScoringInstruction(sessionFolder),  // agent: ~/.codex/agents/workflow-analyzer.toml
   max_concurrency: maxConcurrency,
   max_runtime_seconds: 3600,
   output_csv_path: `${sessionFolder}/wave-2-results.csv`,