Reasoning Orchestrator

Reasoning Orchestrator

CRITICAL: This skill does NOT perform any reasoning itself. It plans and delegates. All reasoning is done by reading and applying individual skill files, or by spawning subagents. Do not shortcut by reasoning inline.

How to Execute This Skill

Follow these steps exactly, in order. Do not skip or collapse steps.

STEP 1 — Triage (no skill file needed)

Classify the situation across these dimensions and write the classification before proceeding:

Temporal direction: Forward-looking / Present-state / Backward-looking

Problem maturity:

• Unframed — problem itself may not be correctly defined
• Framed, unsolved — problem understood, solution not found
• Solved, needs validation — solution exists, needs stress-testing
• Decided, needs learning — something happened, extract signal

Primary obstacle:

• Don't understand the system → diagnostic track
• Understand it, stuck on solutions → generative track
• Have solutions, need to choose → convergence track
• Something went wrong → retrospective track
• About to commit to something → adversarial track
• Don't know what we don't know → epistemic track
• Incentives misaligned / need to design rules → strategic track

Domain complexity (if unclear, assign unknown and include cynefin-framework in Step 2): Clear / Complicated / Complex / Chaotic / Unknown

Write the triage output:

TRIAGE
Temporal: [forward / present / backward]
Maturity: [label]
Obstacle: [label] → [track]
Domain: [label]

STEP 2 — Build the Execution Plan (no skill file needed)

Using the triage and the routing table, produce a numbered execution plan. Label each step SEQUENTIAL or PARALLEL. Do not execute yet.

Routing table — entry points by obstacle:

Write the plan:

EXECUTION PLAN
Step 1 — PARALLEL: [skill-a] ∥ [skill-b] ∥ [skill-c]
Step 2 — SEQUENTIAL: [skill-d]
Step 3 — PARALLEL: [skill-e] ∥ [skill-f]
Step 4 — SEQUENTIAL: [skill-g]

STEP 3 — Execute the Plan (step by step, never all at once)

Work through one step at a time.

For a SEQUENTIAL step:

1. Read the skill file: view: skills/[skill-name]/SKILL.md
2. Apply the skill to the current problem context, following the methodology exactly
3. Write the output in the skill's output format
4. Write the routing decision:

   STEP [N] COMPLETE — SEQUENTIAL: [skill-name]
   Key finding: [1–2 sentences]
   Routing to Step [N+1]: [reason based on finding]
   

5. Proceed to next step

For a PARALLEL step:

1. Spawn one subagent per skill using the Task tool. Each receives:

   • Full problem description
   • Findings from prior sequential steps
   • This instruction: "Read skills/[skill-name]/SKILL.md then apply that skill's full methodology to the problem. Output your findings in that skill's output format. Do not perform other reasoning."

2. Wait for all subagents to complete

3. Synthesize their outputs:

   SYNTHESIS — Step [N] PARALLEL: [skill-a] ∥ [skill-b] ∥ [skill-c]
   
   Convergent findings (2+ skills agree — higher confidence):
   - [finding]
   
   Divergent findings (1 skill only — worth noting):
   - [finding] (from [skill])
   
   Contradictions (skills disagree — resolve before proceeding):
   - [skill-a] says [X], [skill-b] says [Y] → resolution: [...]
   
   Key inputs for Step [N+1]: [what the next step needs]
   

4. Proceed to next step

STEP 4 — Terminate

Stop when:

• decision-synthesis has produced a decision with acceptable confidence
• The problem is understood well enough to act without further analysis
• 4+ steps without converging: stop, flag as likely unframed, restart from Step 1 with epistemic-mapping as the only entry point

Write the termination output:

CHAIN COMPLETE
Steps executed: [list with SEQUENTIAL/PARALLEL labels]
Key finding: [1–2 sentences]
Recommended action: [what to do now]

Then propose follow-up skills. Do NOT auto-execute. Common follow-ups:

• Decision made → "Want me to write this up? (technical-writing for ADR/RFC, argument-craft to structure the case)"
• Plan needed → "Want me to break this into an execution plan? (execution-planning)"
• Communication needed → "Want a presentation? (presentation-craft) or draft announcement? (technical-writing)"

Present only relevant follow-ups. If none needed, say so.

Parallelization Reference

Skills within a cluster apply independent lenses and never depend on each other's output.

Post-Step Routing Reference

After completing any step, adjust the plan if findings warrant:

Skill Registry