council

Name: council
Author: softspark

161stars21forks

How to install council?

softspark/ai-toolkit/council

$npx -y skills add softspark/ai-toolkit --skill council

Installs into the current project.

Summary

4-perspective decision evaluation for architecture choices. Triggers: council, evaluate decision, pros cons, multi-angle, alternatives.

Files · 1

View on GitHub

SKILL.md

1	# Decision Council
2
3	$ARGUMENTS
4
5	Evaluate a decision from 4 distinct perspectives using parallel sub-agents, then synthesize a weighted recommendation.
6
7	## Usage
8
9	```
10	/council [decision question or proposal to evaluate]
11	```
12
13	## What This Command Does
14
15	1. Parses the decision question from user input
16	2. Gathers codebase context relevant to the decision
17	3. Spawns 4 parallel sub-agents — each analyzing from a different perspective
18	4. Synthesizes all perspectives into a structured recommendation with decision matrix
19
20	## MANDATORY: You MUST use the Agent tool
21
22	DO NOT analyze the decision yourself. Your job is to parse the question, spawn 4 sub-agents in parallel via the `Agent` tool, and synthesize their outputs. If you attempt to provide all perspectives inline, you have failed.
23
24	## Process
25
26	### 1. Parse the Decision
27
28	Extract from the user's input:
29
30	- The proposal — what is being considered
31	- The alternatives — what the options are (if not stated, infer the implicit alternative: status quo)
32	- The context — what project/codebase/situation this applies to
33
34	If the question is too vague to evaluate, ask ONE clarifying question before proceeding.
35
36	### 2. Gather Context
37
38	Before spawning agents, quickly scan the codebase for relevant context:
39
40	- Current tech stack, dependencies, patterns in use
41	- Existing code related to the decision area
42	- Configuration, infrastructure, or architectural choices already made
43
44	Include this context in each sub-agent prompt so perspectives are grounded in reality.
45
46	### 3. Spawn 4 Sub-Agents in Parallel (REQUIRED)
47
48	Call the `Agent` tool 4 times in a single response — all agents MUST launch in the same message to run in parallel.
49
50	\| Agent \| Role \| Directive \|
51	\|-------\|------\|-----------\|
52	\| Advocate \| Case FOR \| Present the strongest case FOR the proposal. Find evidence, benefits, success stories. Reference relevant code/patterns in the codebase. Be persuasive but honest. \|
53	\| Critic \| Case AGAINST \| Present the strongest case AGAINST. Find risks, hidden costs, failure modes, alternatives that might be better. Be thorough but fair. \|
54	\| Pragmatist \| Trade-offs \| Evaluate practical trade-offs: implementation cost, timeline, team capacity, maintenance burden, migration risk, operational complexity. Ground estimates in the actual codebase size and patterns. \|
55	\| User-Proxy \| User impact \| Consider end-user and customer impact: UX changes, downtime during migration, performance implications, breaking changes, adoption friction, documentation needs. \|
56
57	Each agent prompt MUST include:
58
59	1. The original decision question
60	2. The codebase context gathered in step 2
61	3. The specific perspective this agent owns
62	4. Instruction to search the codebase for supporting evidence
63	5. Constraint: 200-400 words, concrete evidence over abstract arguments
64
65	### 4. Synthesize
66
67	After all 4 agents complete, combine their outputs into the structured format below. Do NOT simply concatenate — identify agreements, contradictions, and conditional factors across perspectives.
68
69	## Output Format
70
71	```markdown
72	## Decision Council: [Question]
73
74	### Advocate (FOR)
75	[Summary of arguments for — key benefits and evidence]
76
77	### Critic (AGAINST)
78	[Summary of arguments against — key risks and alternatives]
79
80	### Pragmatist (TRADE-OFFS)
81	[Practical considerations — cost, timeline, complexity]
82
83	### User-Proxy (USER IMPACT)
84	[End-user perspective — UX, performance, breaking changes]
85
86	### Synthesis
87	Recommendation: [FOR / AGAINST / CONDITIONAL]
88	Confidence: [HIGH / MEDIUM / LOW]
89	Key condition: [Primary factor that would change the recommendation]
90
91	Where perspectives agree: [Common ground across agents]
92	Where perspectives conflict: [Key disagreements and why]
93
94	### Decision Matrix
95	\| Factor \| Weight \| FOR score (1-5) \| AGAINST score (1-5) \|
96	\|--------\|--------\|-----------------\|---------------------\|
97	\| Technical merit \| [H/M/L] \| [score] \| [score] \|
98	\| Risk \| [H/M/L] \| [score] \| [score] \|
99	\| Cost \| [H/M/L] \| [score] \| [score] \|
100	\| Timeline \| [H/M/L] \| [score] \| [score] \|
101	\| User impact \| [H/M/L] \| [score] \| [score] \|
102	\| Weighted total \| \| [total] \| [total] \|
103	```
104
105	## Rules
106
107	- Each sub-agent must search the codebase for relevant evidence — no purely abstract arguments
108	- Sub-agents must be honest within their role — the Advocate should acknowledge weaknesses, the Critic should acknowledge strengths
109	- Keep each perspective to 200-400 words — density over length
110	- The synthesis must add value beyond summarizing — identify the decisive factor
111	- If the decision is clearly one-sided after analysis, say so — don't manufacture false balance
112
113	## Anti

People who liked this also viewed

6 picks

Type

find-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skSkillsJul 20262.6M27k
grill-meA relentless interview to sharpen a plan or design.SkillsJul 2026633k182k
vercel-react-best-practicesVercel's official collection of agent skillsSkillsJul 2026573k29k
improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.SkillsJul 2026522k182k
setup-matt-pocock-skillsConfigure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.SkillsJul 2026454k182k
triageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.SkillsJul 2026424k182k

council

161stars21forks

View on GitHub

How to install council?

softspark/ai-toolkit/council

$npx -y skills add softspark/ai-toolkit --skill council

Installs into the current project.

Summary

4-perspective decision evaluation for architecture choices. Triggers: council, evaluate decision, pros cons, multi-angle, alternatives.

Files · 1

View on GitHub

SKILL.md

1	# Decision Council
2
3	$ARGUMENTS
4
5	Evaluate a decision from 4 distinct perspectives using parallel sub-agents, then synthesize a weighted recommendation.
6
7	## Usage
8
9	```
10	/council [decision question or proposal to evaluate]
11	```
12
13	## What This Command Does
14
15	1. Parses the decision question from user input
16	2. Gathers codebase context relevant to the decision
17	3. Spawns 4 parallel sub-agents — each analyzing from a different perspective
18	4. Synthesizes all perspectives into a structured recommendation with decision matrix
19
20	## MANDATORY: You MUST use the Agent tool
21
22	DO NOT analyze the decision yourself. Your job is to parse the question, spawn 4 sub-agents in parallel via the `Agent` tool, and synthesize their outputs. If you attempt to provide all perspectives inline, you have failed.
23
24	## Process
25
26	### 1. Parse the Decision
27
28	Extract from the user's input:
29
30	- The proposal — what is being considered
31	- The alternatives — what the options are (if not stated, infer the implicit alternative: status quo)
32	- The context — what project/codebase/situation this applies to
33
34	If the question is too vague to evaluate, ask ONE clarifying question before proceeding.
35
36	### 2. Gather Context
37
38	Before spawning agents, quickly scan the codebase for relevant context:
39
40	- Current tech stack, dependencies, patterns in use
41	- Existing code related to the decision area
42	- Configuration, infrastructure, or architectural choices already made
43
44	Include this context in each sub-agent prompt so perspectives are grounded in reality.
45
46	### 3. Spawn 4 Sub-Agents in Parallel (REQUIRED)
47
48	Call the `Agent` tool 4 times in a single response — all agents MUST launch in the same message to run in parallel.
49
50	\| Agent \| Role \| Directive \|
51	\|-------\|------\|-----------\|
52	\| Advocate \| Case FOR \| Present the strongest case FOR the proposal. Find evidence, benefits, success stories. Reference relevant code/patterns in the codebase. Be persuasive but honest. \|
53	\| Critic \| Case AGAINST \| Present the strongest case AGAINST. Find risks, hidden costs, failure modes, alternatives that might be better. Be thorough but fair. \|
54	\| Pragmatist \| Trade-offs \| Evaluate practical trade-offs: implementation cost, timeline, team capacity, maintenance burden, migration risk, operational complexity. Ground estimates in the actual codebase size and patterns. \|
55	\| User-Proxy \| User impact \| Consider end-user and customer impact: UX changes, downtime during migration, performance implications, breaking changes, adoption friction, documentation needs. \|
56
57	Each agent prompt MUST include:
58
59	1. The original decision question
60	2. The codebase context gathered in step 2
61	3. The specific perspective this agent owns
62	4. Instruction to search the codebase for supporting evidence
63	5. Constraint: 200-400 words, concrete evidence over abstract arguments
64
65	### 4. Synthesize
66
67	After all 4 agents complete, combine their outputs into the structured format below. Do NOT simply concatenate — identify agreements, contradictions, and conditional factors across perspectives.
68
69	## Output Format
70
71	```markdown
72	## Decision Council: [Question]
73
74	### Advocate (FOR)
75	[Summary of arguments for — key benefits and evidence]
76
77	### Critic (AGAINST)
78	[Summary of arguments against — key risks and alternatives]
79
80	### Pragmatist (TRADE-OFFS)
81	[Practical considerations — cost, timeline, complexity]
82
83	### User-Proxy (USER IMPACT)
84	[End-user perspective — UX, performance, breaking changes]
85
86	### Synthesis
87	Recommendation: [FOR / AGAINST / CONDITIONAL]
88	Confidence: [HIGH / MEDIUM / LOW]
89	Key condition: [Primary factor that would change the recommendation]
90
91	Where perspectives agree: [Common ground across agents]
92	Where perspectives conflict: [Key disagreements and why]
93
94	### Decision Matrix
95	\| Factor \| Weight \| FOR score (1-5) \| AGAINST score (1-5) \|
96	\|--------\|--------\|-----------------\|---------------------\|
97	\| Technical merit \| [H/M/L] \| [score] \| [score] \|
98	\| Risk \| [H/M/L] \| [score] \| [score] \|
99	\| Cost \| [H/M/L] \| [score] \| [score] \|
100	\| Timeline \| [H/M/L] \| [score] \| [score] \|
101	\| User impact \| [H/M/L] \| [score] \| [score] \|
102	\| Weighted total \| \| [total] \| [total] \|
103	```
104
105	## Rules
106
107	- Each sub-agent must search the codebase for relevant evidence — no purely abstract arguments
108	- Sub-agents must be honest within their role — the Advocate should acknowledge weaknesses, the Critic should acknowledge strengths
109	- Keep each perspective to 200-400 words — density over length
110	- The synthesis must add value beyond summarizing — identify the decisive factor
111	- If the decision is clearly one-sided after analysis, say so — don't manufacture false balance
112
113	## Anti

People who liked this also viewed

6 picks

Type