Agent skill · operations · aiskillstore
reasoning-causal
Execute evidence-based decision-making through 6-stage causal flow. Use for known processes, operational execution, and decisions with clear cause-effect chains.
Why this skill is useful
Provides a structured 6-stage causal reasoning framework for decision-making that the AI wouldn't generate on its own.
What it needs
About 5k tokens when loaded. Last updated 2026-08-07. 405 stars on the source repository.
What this skill does
Causal Reasoning Execute systematic cause-effect reasoning. The logic of process and action. Relationship to Goals Threads are the execution layer for goals. Goals define what to achieve; threads define how. Thread types: Goal-linked: Created from subgoals, has goalid in metadata Reactive: Created from signals (no goal), may spawn or link to goal Type Signature When to Use Process execution with known steps Decision with clear cause-effect chain Operational workflows (sales, marketing, engineering) Canvas hypothesis testing Action planning and execution Executing subgoals (goal-linked threads) Thread Types Type Location Use For ------ ---------- --------- Business threads/operations/{name}/ Strategic decisions, product changes Sales threads/sales/{name}/ Deal pipelines, prospects Marketing threads/marketing/{name}/ Campaigns, content launches Engineering threads/engineering/{name}/ Requirements → specifications Thread-specific details: See references/threads/{type}.md --- 6-Stage Flow Execute stages sequentially. Each stage produces a markdown file in the thread directory. Stage 1: Input File: 1-input.md Purpose: Capture factual observation that triggers the flow. Content: What happened? (fact, not opinion) When? Where? Who observed? Raw data/evidence links Context (what we believed before) Rules: Facts only, no interpretation No solutions or recommendations Link to evidence Detail: references/stages/input.md --- Stage 2: Hypothesis File: 2-hypothesis.md Purpose: Link observation to Canvas assumption being tested. Content: Which assumption does this challenge/validate? What do we believe will happen? What would prove us wrong? Testable prediction Rules: Must reference strategy/canvas/10.assumptions.md State falsifiable hypothesis Define success/failure criteria Detail: references/stages/hypothesis.md --- Stage 3: Implication File: 3-implication.md Purpose: Analyze business impact with numbers. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aiskillstore/reasoning-causal