reasoning-orchestrator

name

reasoning-orchestrator

description

Apply this skill first whenever the user presents a problem, question, or situation that requires structured thinking — before reaching for any specific reasoning framework. Triggers on any substantive request to evaluate, analyze, diagnose, decide, design, improve, understand, or learn from something. This is the entry point for the reasoning skill collection. If you are unsure which reasoning skill to use, always start here.

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:

Obstacle	Execution plan
Don't know what we're dealing with	PARALLEL: epistemic-mapping ∥ cynefin-framework ∥ cognitive-bias-detection → re-triage
Don't understand the system / why it's failing	PARALLEL: system-thinking ∥ theory-of-constraints → SEQUENTIAL: five-whys-root-cause → decision-synthesis
Don't understand the system / strategic agents involved	PARALLEL: system-thinking ∥ game-theoretic-analysis → SEQUENTIAL: five-whys-root-cause → decision-synthesis
Plan / design needs validation	PARALLEL: inversion-premortem ∥ red-teaming ∥ second-order-thinking → SEQUENTIAL: cognitive-bias-detection → decision-synthesis
Scaling / trajectory / "what if we push this?"	SEQUENTIAL: limit-thinking → PARALLEL: second-order-thinking ∥ scenario-planning → decision-synthesis
Stuck, all solutions feel the same	SEQUENTIAL: epistemic-mapping → PARALLEL: lateral-thinking ∥ analogical-thinking ∥ first-principles-thinking → SEQUENTIAL: inversion-premortem → decision-synthesis
Need to decide between options	PARALLEL: scenario-planning ∥ probabilistic-thinking ∥ fermi-estimation → decision-synthesis
Something went wrong / post-mortem	SEQUENTIAL: retrospective-counterfactual → PARALLEL: five-whys-root-cause ∥ epistemic-mapping → SEQUENTIAL: cognitive-bias-detection
Long-term strategic commitment	PARALLEL: epistemic-mapping ∥ cognitive-bias-detection ∥ cynefin-framework → PARALLEL: scenario-planning ∥ probabilistic-thinking ∥ fermi-estimation → PARALLEL: inversion-premortem ∥ red-teaming ∥ second-order-thinking → SEQUENTIAL: game-theoretic-analysis → decision-synthesis
Incentives misaligned / need to design rules	SEQUENTIAL: game-theoretic-analysis → PARALLEL: second-order-thinking ∥ red-teaming → decision-synthesis
Synthesize evidence from multiple sources	SEQUENTIAL: evidence-synthesis → decision-synthesis

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.

Pattern	Skills	Use when
P1 — Adversarial	inversion-premortem ∥ red-teaming ∥ second-order-thinking	Validating a plan before commitment
P2 — Generative	lateral-thinking ∥ analogical-thinking ∥ first-principles-thinking	Stuck, need new options
P3 — Diagnostic	system-thinking ∥ theory-of-constraints	System failing, need to understand why
P4 — Uncertainty	scenario-planning ∥ probabilistic-thinking ∥ fermi-estimation	Decision needs quantification
P5 — Meta-cognitive	epistemic-mapping ∥ cognitive-bias-detection ∥ cynefin-framework	Clean the reasoning environment first
P6 — Strategic	game-theoretic-analysis ∥ second-order-thinking	Multiple agents with competing incentives

---

Post-Step Routing Reference

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

Completed skill	Finding	Adjust plan to include
epistemic-mapping	Dangerous assumptions found	first-principles-thinking (sequential, next)
cynefin-framework	Domain = Complex	lateral-thinking ∥ scenario-planning (parallel) instead of structured analysis
cynefin-framework	Domain = Chaotic	Act immediately; retrospective-counterfactual after stabilization
game-theoretic-analysis	Nash Equilibrium ≠ Pareto Optimum	Mechanism design — decision-synthesis with design constraints
game-theoretic-analysis	Information asymmetry identified	red-teaming on exploitability (sequential)
game-theoretic-analysis	Repeated game dynamics	second-order-thinking on reputation effects (sequential)
system-thinking	Bottleneck identified	theory-of-constraints (sequential)
five-whys-root-cause	Root cause is causal claim	evidence-synthesis (sequential)
five-whys-root-cause	Multiple root causes	decision-synthesis (sequential, to prioritize)
adversarial panel (P1)	High-severity risks	cognitive-bias-detection on the risk analysis (sequential)
generative panel (P2)	All options weak	epistemic-mapping — frame may be wrong (sequential, restart)
uncertainty panel (P4)	High uncertainty persists	inversion-premortem on worst-case scenario (sequential)
limit-thinking	Asymptotic ceiling found	theory-of-constraints to identify the constraint (sequential)
limit-thinking	Reversal / collapse found	first-principles-thinking — is this the right variable? (sequential)
limit-thinking	Optimal operating point identified	decision-synthesis (sequential)
second-order-thinking	Consequence chain suggests trajectory	limit-thinking to trace to the extreme (sequential)
decision-synthesis	Key assumption too uncertain	epistemic-mapping → validate before committing
evidence-synthesis	Evidence synthesized, decision needed	decision-synthesis (sequential)
retrospective-counterfactual	Systemic cause found	system-thinking ∥ five-whys-root-cause (parallel)

---

Skill Registry

Skill	File path	Parallelizes with
epistemic-mapping	skills/epistemic-mapping/SKILL.md	cynefin-framework, cognitive-bias-detection
cynefin-framework	skills/cynefin-framework/SKILL.md	epistemic-mapping, cognitive-bias-detection
system-thinking	skills/system-thinking/SKILL.md	theory-of-constraints
theory-of-constraints	skills/theory-of-constraints/SKILL.md	system-thinking
five-whys-root-cause	skills/five-whys-root-cause/SKILL.md	—
cognitive-bias-detection	skills/cognitive-bias-detection/SKILL.md	epistemic-mapping, cynefin-framework
inversion-premortem	skills/inversion-premortem/SKILL.md	red-teaming, second-order-thinking
red-teaming	skills/red-teaming/SKILL.md	inversion-premortem, second-order-thinking
second-order-thinking	skills/second-order-thinking/SKILL.md	inversion-premortem, red-teaming
probabilistic-thinking	skills/probabilistic-thinking/SKILL.md	scenario-planning, fermi-estimation
fermi-estimation	skills/fermi-estimation/SKILL.md	probabilistic-thinking, scenario-planning
scenario-planning	skills/scenario-planning/SKILL.md	probabilistic-thinking, fermi-estimation
game-theoretic-analysis	skills/game-theoretic-analysis/SKILL.md	second-order-thinking
limit-thinking	skills/limit-thinking/SKILL.md	second-order-thinking, scenario-planning
lateral-thinking	skills/lateral-thinking/SKILL.md	analogical-thinking, first-principles-thinking
analogical-thinking	skills/analogical-thinking/SKILL.md	lateral-thinking, first-principles-thinking
first-principles-thinking	skills/first-principles-thinking/SKILL.md	lateral-thinking, analogical-thinking
bisociative-creativity	skills/bisociative-creativity/SKILL.md	standalone
decision-synthesis	skills/decision-synthesis/SKILL.md	runs after all others
decision-intelligence	skills/decision-intelligence/SKILL.md	standalone (single-option evaluation)
retrospective-counterfactual	skills/retrospective-counterfactual/SKILL.md	five-whys-root-cause
evidence-synthesis	skills/evidence-synthesis/SKILL.md	—