Back to list
ReinaMacCredy

designing

by ReinaMacCredy

Agent Skills (compatible with Claude Code, Codex, and more—for details visit: https://agentskills.io/home) with Conductor planning, Beads tracking, and TDD for AI-assisted development

23🍴 3📅 Jan 17, 2026

SKILL.md


name: designing description: Design Session - collaborative brainstorming to turn ideas into actionable implementation plans using the Unified Pipeline methodology. Use when user types "ds" or wants to explore/design a feature before implementation. "pl" triggers phases 5-10 (STANDALONE/ALIAS/NO-OP modes). MUST load maestro-core skill first for routing.

Design & Planning

Turn ideas into fully-formed, implementation-ready designs through a unified 10-phase pipeline.

Entry Points

TriggerAction
dsStart unified pipeline (all 10 phases)
/conductor-designStart unified pipeline (alias)
cn, /conductor-newtrackCreate spec + plan + beads from existing design.md
pl, /planPlanning phases (5-10) - see pl Entry Modes below
"design a feature"Start unified pipeline
"let's think through X"Start unified pipeline

Quick Reference

Unified Pipeline (10 Phases)

#PhaseTypePurposeExit Criteria
1DISCOVERDivergeExplore problem + research contextProblem articulated
2DEFINEConvergeFrame problem + select approachApproach selected
3DEVELOPDivergeArchitecture + componentsInterfaces defined
4VERIFYConvergeOracle audit + risk assessmentOracle APPROVED
5DECOMPOSEExecuteCreate beads (fb)Beads filed
6VALIDATEExecuteDependency check (bv) + Oracle reviewDependencies valid
7ASSIGNExecuteTrack assignmentsTracks assigned
8READYCompleteHandoff to ci/co/caExecution ready
9EXECUTEImplementRun ci/co/ca on tracksAll beads completed
10FINISHArchiveExtract learnings + archive trackTrack archived

See pipeline.md for full details.

Mode Routing

Complexity scoring determines execution mode:

ScoreModePhasesA/P/CResearch
< 4SPEED1,2,4,8No1 hook (start)
4-6ASKUser choosesOptionalUser chooses
> 6FULL1-10Yes2 hooks

Mode Comparison

AspectSPEED (< 4)FULL (> 6)
Phases1,2,4,8All 10
A/P/CNoYes
Research1 hook2 hooks
BeadsNoYes
TracksNoYes
VerificationAdvisoryMandatory
Use [E] to escalateYesN/A

Core Principles

  • One question at a time - Don't overwhelm
  • Multiple choice preferred - Easier to answer
  • YAGNI ruthlessly - Remove unnecessary features
  • Explore alternatives - Always propose 2-3 approaches
  • Research consolidated - 2 strategic hooks, not 5

⛔ EXECUTION BLOCKS (CRITICAL)

This skill contains EXECUTION BLOCKS marked with ⛔. When you encounter one, you MUST:

  1. STOP what you're doing
  2. EXECUTE the tool calls specified (Task(), oracle(), skill())
  3. WAIT for results before proceeding

EXECUTION BLOCKS are NOT documentation - they are COMMANDS you must execute.

See pipeline.md for all execution blocks.

Session Flow

  1. Load Core - Load maestro-core for routing table and fallback policies
  2. Initialize - Load handoffs, CODEMAPS, verify conductor setup → session-init.md
  3. Research - ⛔ EXECUTION BLOCK at Phase 1 start (spawn 3 Task() agents)
  4. Route - Score complexity (< 4 = SPEED, > 6 = FULL) → design-routing-heuristics.md
  5. Execute - 10-phase pipeline with A/P/C checkpoints → pipeline.md
  6. Validate - ⛔ EXECUTION BLOCK at Phase 4 (call oracle())
  7. Complete - Phase 8 (READY) triggers ci/co/ca → Phase 9 (EXECUTE) → Phase 10 (FINISH)

Research Hooks (Consolidated)

HookTriggerAgentsPurpose
research-startPhase 1 (DISCOVER)Locator + Pattern + CODEMAPS + ArchitectureAll initial context
research-verifyPhase 3→4 (DEVELOP→VERIFY)Analyzer + Pattern + Impact + WebDesign verification

Validation Gates

CheckpointFocusEnforcement
CP1 (DISCOVER)Product alignment, no duplicate featuresWARN
CP2 (DEFINE)Problem clear, success measurable, scope explicitWARN
CP3 (DEVELOP)3+ options, tech-stack alignment, risk analysisWARN
CP4 (VERIFY)Full validation + grounding + impact scanSPEED=WARN, FULL=HALT

Adaptive A/P/C System

A/P/C checkpoints work adaptively across the entire workflow.

State Ladder

INLINE → MICRO_APC → NUDGE → DS_FULL → DS_BRANCH → BRANCH_MERGE
StateDescriptionTrigger
INLINENormal flow (conductor/beads)Default
MICRO_APCLightweight checkpoint at boundariesEnd of spec/plan section
NUDGESuggest upgrade to DS3+ design iterations
DS_FULLFull 10-phase with A/P/Cds command or upgrade
DS_BRANCHDS attached to design branchDesign rethink in track
BRANCH_MERGEApply branch changesBranch complete

A/P/C in FULL Mode

At end of phases 1-4:

  • [A] Advanced - Phase-specific deep dive
  • [P] Party - Multi-agent feedback (BMAD v6) → bmad/
  • [C] Continue - Proceed to next phase
  • [↩ Back] - Return to previous phase
After PhaseA Option
1 (DISCOVER)Advanced assumption audit
2 (DEFINE)Scope stress-test
3 (DEVELOP)Architecture deep-dive
4 (VERIFY)Oracle runs BEFORE showing menu

Priority Rules

  1. Explicit commands (ds) always win
  2. Active DS/Branch blocks passive triggers
  3. Branch safety preferred when in implementation
  4. Micro A/P/C at checkpoint boundaries
  5. Nudge after 3+ iterations

See apc-checkpoints.md for implementation details.

Phase 4: VERIFY - Spike Execution

When risk assessment identifies HIGH risk items:

HIGH risk items → MUST spawn spike Task()
                       │
                       ▼
              For each HIGH risk:
              1. Create spike bead + dir
              2. MUST spawn Task() with time-box
              3. Wait for completion
              4. Capture result (YES/NO)
                       │
                       ▼
              MUST call oracle() for 6-dimension audit
                       │
               ┌───────┴───────┐
               │               │
        All spikes YES   Any spike NO
               │               │
               ▼               ▼
           Continue       HALT - user decision

⚠️ MANDATORY: You MUST call oracle() at Phase 4 - see pipeline.md

Phase 6: VALIDATE - Oracle Beads Review

⚠️ MANDATORY: After bv validation, you MUST call oracle() to review beads completeness.

See pipeline.md

Phase 8: READY - Auto-Orchestration

Ready to execute. Found N tracks:
• Track A (BlueLake): 4 beads
• Track B (GreenCastle): 3 beads

[O] Orchestrate (spawn workers)
[S] Sequential (run ci manually)
[R] Ralph (autonomous loop - ca)

Default: [O] after 30s

Note: [R] is available when ralph.enabled == true in track metadata.json.

⚠️ MANDATORY: If user selects [O] and ≥2 tracks exist, you MUST spawn Task() for each track.

See pipeline.md

pl Entry Gate

⚠️ MANDATORY: Before running pl, detect input and bootstrap if needed:

pl triggered
    │
    ▼
Input detection (priority order):
    1. design.md exists? → ALIAS mode (skip discovery)
    2. PRD file exists?  → STANDALONE mode (parse PRD)
    3. User file attached? → STANDALONE mode
    4. No input?         → BOOTSTRAP mode (prompt → create track)
Input SourceModeAction
design.mdALIASSkip Phase 5, run 6-10
PRD fileSTANDALONEParse PRD, run 5-10
User fileSTANDALONEUse as context, run 5-10
NoneBOOTSTRAPPrompt → create track → run 5-10

BOOTSTRAP creates: conductor/tracks/<id>/ with design.md + metadata.json

pl Compatibility

ScenarioModeBehavior
pl after ds Phase 4NO-OPNot needed - phases 5-10 auto-run in FULL mode
pl with design.mdALIASSkip Phase 5 discovery, run 6-10
pl with PRD fileSTANDALONEParse PRD, run full 5-10
pl with user requestSTANDALONERun full discovery, phases 5-10
pl without any inputERRORPrompt for input source

Anti-Patterns

  • ❌ Jumping to solutions before understanding the problem
  • ❌ Skipping verification at Phase 4 (VERIFY)
  • ❌ Asking multiple questions at once
  • ❌ Over-engineering simple features (use SPEED mode)
  • ❌ Running pl after ds completes (no longer needed)

Next Steps (after Phase 8: READY)

CommandDescriptionPhase
ci/conductor-implement - Execute trackPhase 9 (EXECUTE)
co/conductor-orchestrate - Spawn parallel workersPhase 9 (EXECUTE)
ca/conductor-autonomous - Ralph loopPhase 9 (EXECUTE)
/conductor-finishArchive track + extract learningsPhase 10 (FINISH)

See maestro-core for full routing table.

Dependencies

Auto-loads: maestro-core for routing and fallback policies.

Score

Total Score

75/100

Based on repository quality metrics

SKILL.md

SKILL.mdファイルが含まれている

+20
LICENSE

ライセンスが設定されている

+10
説明文

100文字以上の説明がある

+10
人気

GitHub Stars 100以上

0/15
最近の活動

1ヶ月以内に更新

+10
フォーク

10回以上フォークされている

0/5
Issue管理

オープンIssueが50未満

+5
言語

プログラミング言語が設定されている

+5
タグ

1つ以上のタグが設定されている

+5

Reviews

💬

Reviews coming soon