sequential-thinking

Name: sequential-thinking
Author: Rune-kit

80stars21forks

How to install sequential-thinking?

rune-kit/rune/sequential-thinking

$npx -y skills add Rune-kit/rune --skill sequential-thinking

Installs into the current project.

Summary

Step-by-step complex reasoning for multi-variable problems. Breaks interconnected decisions into ordered logical steps with bias detection, reversibility classification, and second-order effect tracking.

Files · 1

View on GitHub

SKILL.md

1	# sequential-thinking
2
3	## Purpose
4
5	Multi-variable analysis utility for decisions where factors are interdependent and order of reasoning matters. Receives a decision problem, classifies reversibility, detects cognitive biases, maps variable dependencies, processes them in dependency order, checks for second-order effects, and returns a structured decision tree with final recommendation. Stateless — no memory between calls.
6
7	## Calls (outbound)
8
9	None — pure L3 reasoning utility.
10
11	## Called By (inbound)
12
13	- `debug` (L2): multi-factor bugs with interacting causes
14	- `plan` (L2): complex architecture with many trade-offs
15	- `brainstorm` (L2): evaluating approaches with many variables
16
17	## When to Use
18
19	Invoke this skill when:
20	- The decision has more than 3 interacting variables
21	- Choosing option A changes what options are valid for B and C
22	- Architecture decisions have cascading downstream effects
23	- Trade-off analysis where constraints eliminate entire solution branches
24
25	Do NOT use for simple linear analysis — `problem-solver` is more efficient for single-dimension reasoning.
26
27	## Execution
28
29	### Input
30
31	```
32	decision: string — the decision or problem to analyze
33	variables: string[] — (optional) pre-identified factors; if omitted, skill identifies them
34	constraints: string[] — (optional) hard limits that eliminate options
35	goal: string — (optional) success criteria or desired outcome
36	```
37
38	### Step 0 — Reversibility Classification
39
40	Before investing analytical effort, classify the decision:
41
42	\| Type \| Definition \| Analytical Effort \|
43	\|------\|-----------\|-------------------\|
44	\| Two-way door \| Reversible, can iterate, low switching cost \| Decide quickly, set review date. Light analysis. \|
45	\| One-way door \| Irreversible, high stakes, costly to reverse \| Full sequential analysis. Deep reasoning. \|
46	\| Partially reversible \| Some aspects reversible, some not \| Full analysis on irreversible aspects, light on reversible. \|
47
48	If two-way door → streamline: skip Step 4 (second-order) and Step 5 (bias cross-check). State reasoning.
49
50	### Step 1 — Identify All Variables
51
52	List every factor that affects the decision. For each variable, record:
53	- Name and description
54	- Possible values or range
55	- Whether it is controllable (we can choose) or fixed (constraint from environment)
56
57	If the caller provided `variables`, validate and expand the list. If omitted, derive from the decision statement.
58
59	### Step 2 — Map Dependencies
60
61	For each pair of variables, determine if a dependency exists:
62	- `[A] constrains [B]`: choosing a value for A limits valid values for B
63	- `[A] influences [B]`: A affects the cost/benefit calculation for B but does not eliminate options
64	- `[A] independent of [B]`: no relationship
65
66	Document dependencies as: `[Variable A] → [Variable B]: [type and reason]`
67
68	Identify which variables have the most outbound dependencies — those must be resolved first.
69
70	### Step 3 — Evaluate in Dependency Order
71
72	Sort variables from most-constrained (fixed / most depended upon) to least-constrained (free / most flexible). Process in that order:
73
74	For each variable in sequence:
75	- State current known state of all previously resolved variables
76	- Evaluate valid options given those constraints
77	- Select the best option with explicit reasoning
78	- Record the conclusion and how it affects downstream variables
79
80	Do not jump ahead — each step must reference the conclusions of prior steps.
81
82	Running state block at each step:
83
84	```
85	State after Step N:
86	- [Variable A]: resolved to [value] because [reason]
87	- [Variable B]: resolved to [value] because [reason]
88	- Remaining: [Variable C], [Variable D]
89	```
90
91	### Step 4 — Second-Order Effects Check
92
93	After all variables are resolved, apply second-order thinking:
94
95	For each resolved variable, ask: "And then what?"
96
97	\| Variable \| First-Order Effect \| Second-Order Effect \| Risk Level \|
98	\|----------\|-------------------\|--------------------\|-\|
99	\| [A = value] \| [immediate consequence] \| [consequence of consequence] \| low/medium/high \|
100
101	Flag any second-order effect that:
102	- Contradicts the goal stated in the input
103	- Creates a feedback loop (reinforcing or balancing)
104	- Affects stakeholders not considered in the analysis
105	- Would flip a previous variable's optimal value
106
107	If a dangerous second-order effect is found → revisit the affected variable with this new information.
108
109	### Step 5 — Bias Cross-Check
110
111	Check the analysis for the 3 biases most dangerous to multi-variable decisions:
112
113	\| Bias \| Detection Question \| If Detected \|
114	\|------\|-------------------\|-------------\|
115	\| Anchoring \| Did the first variable we resolved disproportionatel

People who liked this also viewed

6 picks

Type

sequential-thinking

80stars21forks

View on GitHub

How to install sequential-thinking?

rune-kit/rune/sequential-thinking

$npx -y skills add Rune-kit/rune --skill sequential-thinking

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# sequential-thinking
2
3	## Purpose
4
5	Multi-variable analysis utility for decisions where factors are interdependent and order of reasoning matters. Receives a decision problem, classifies reversibility, detects cognitive biases, maps variable dependencies, processes them in dependency order, checks for second-order effects, and returns a structured decision tree with final recommendation. Stateless — no memory between calls.
6
7	## Calls (outbound)
8
9	None — pure L3 reasoning utility.
10
11	## Called By (inbound)
12
13	- `debug` (L2): multi-factor bugs with interacting causes
14	- `plan` (L2): complex architecture with many trade-offs
15	- `brainstorm` (L2): evaluating approaches with many variables
16
17	## When to Use
18
19	Invoke this skill when:
20	- The decision has more than 3 interacting variables
21	- Choosing option A changes what options are valid for B and C
22	- Architecture decisions have cascading downstream effects
23	- Trade-off analysis where constraints eliminate entire solution branches
24
25	Do NOT use for simple linear analysis — `problem-solver` is more efficient for single-dimension reasoning.
26
27	## Execution
28
29	### Input
30
31	```
32	decision: string — the decision or problem to analyze
33	variables: string[] — (optional) pre-identified factors; if omitted, skill identifies them
34	constraints: string[] — (optional) hard limits that eliminate options
35	goal: string — (optional) success criteria or desired outcome
36	```
37
38	### Step 0 — Reversibility Classification
39
40	Before investing analytical effort, classify the decision:
41
42	\| Type \| Definition \| Analytical Effort \|
43	\|------\|-----------\|-------------------\|
44	\| Two-way door \| Reversible, can iterate, low switching cost \| Decide quickly, set review date. Light analysis. \|
45	\| One-way door \| Irreversible, high stakes, costly to reverse \| Full sequential analysis. Deep reasoning. \|
46	\| Partially reversible \| Some aspects reversible, some not \| Full analysis on irreversible aspects, light on reversible. \|
47
48	If two-way door → streamline: skip Step 4 (second-order) and Step 5 (bias cross-check). State reasoning.
49
50	### Step 1 — Identify All Variables
51
52	List every factor that affects the decision. For each variable, record:
53	- Name and description
54	- Possible values or range
55	- Whether it is controllable (we can choose) or fixed (constraint from environment)
56
57	If the caller provided `variables`, validate and expand the list. If omitted, derive from the decision statement.
58
59	### Step 2 — Map Dependencies
60
61	For each pair of variables, determine if a dependency exists:
62	- `[A] constrains [B]`: choosing a value for A limits valid values for B
63	- `[A] influences [B]`: A affects the cost/benefit calculation for B but does not eliminate options
64	- `[A] independent of [B]`: no relationship
65
66	Document dependencies as: `[Variable A] → [Variable B]: [type and reason]`
67
68	Identify which variables have the most outbound dependencies — those must be resolved first.
69
70	### Step 3 — Evaluate in Dependency Order
71
72	Sort variables from most-constrained (fixed / most depended upon) to least-constrained (free / most flexible). Process in that order:
73
74	For each variable in sequence:
75	- State current known state of all previously resolved variables
76	- Evaluate valid options given those constraints
77	- Select the best option with explicit reasoning
78	- Record the conclusion and how it affects downstream variables
79
80	Do not jump ahead — each step must reference the conclusions of prior steps.
81
82	Running state block at each step:
83
84	```
85	State after Step N:
86	- [Variable A]: resolved to [value] because [reason]
87	- [Variable B]: resolved to [value] because [reason]
88	- Remaining: [Variable C], [Variable D]
89	```
90
91	### Step 4 — Second-Order Effects Check
92
93	After all variables are resolved, apply second-order thinking:
94
95	For each resolved variable, ask: "And then what?"
96
97	\| Variable \| First-Order Effect \| Second-Order Effect \| Risk Level \|
98	\|----------\|-------------------\|--------------------\|-\|
99	\| [A = value] \| [immediate consequence] \| [consequence of consequence] \| low/medium/high \|
100
101	Flag any second-order effect that:
102	- Contradicts the goal stated in the input
103	- Creates a feedback loop (reinforcing or balancing)
104	- Affects stakeholders not considered in the analysis
105	- Would flip a previous variable's optimal value
106
107	If a dangerous second-order effect is found → revisit the affected variable with this new information.
108
109	### Step 5 — Bias Cross-Check
110
111	Check the analysis for the 3 biases most dangerous to multi-variable decisions:
112
113	\| Bias \| Detection Question \| If Detected \|
114	\|------\|-------------------\|-------------\|
115	\| Anchoring \| Did the first variable we resolved disproportionatel

People who liked this also viewed

6 picks

Type