kim-decision

Name: kim-decision
Author: KimYx0207

151stars46forks

How to install kim-decision?

kimyx0207/kim_service/kim-decision

$npx -y skills add KimYx0207/Kim_Service --skill kim-decision

Installs into the current project.

Summary

Use when the user asks for KIM, Kim, laojin, 老金, 问问老金, 老金怎么看, asks for decision analysis, structured reasoning, product/business/content review, PRD, MVP, user path, growth, monetization, pricing, client delivery, revenue, cost, scope, strategy, retrospectives, or a concrete plan

Files · 1

View on GitHub

SKILL.md

1	# KIM Skill
2
3	## Operating target
4
5	Deliver a usable decision or artifact.
6
7	The method stays abstract.
8
9	The final answer may use concrete evidence.
10
11	Use concrete names, companies, tools, sources, dates, metrics, cases, commands, or file paths when they improve trust. Verify them or mark them as unconfirmed.
12
13	Do not use a named person as an internal role.
14
15	Do not write "think like this person."
16
17	Turn useful thinking patterns into abstract models.
18
19	## Core-problem gate
20
21	Before expanding the frame, name the core problem internally in one sentence:
22
23	- What decision, defect, design gap, offer, path, or artifact is the user actually asking for?
24	- What outcome would make the user consider the work successful?
25	- What evidence would change the answer?
26	- What is explicitly out of scope for this answer?
27	- What unknown, if any, blocks a safe or useful answer?
28	- What is the smallest useful output that moves the user forward?
29
30	If a step, model, heading, or explanation does not improve the core problem, evidence quality, execution clarity, or final review quality, compress it or cut it.
31
32	Do not let the method become the deliverable. KIM borrows governance discipline from Meta_Kim, but the visible result must still be a sharp decision, test, artifact, or next action.
33
34	## Path scale
35
36	Choose the smallest path that can responsibly close the core problem:
37
38	\| Path \| Use when \| Visible shape \|
39	\|---\|---\|---\|
40	\| Fast path \| Single focused question, local/read-only evidence, no high-stakes external claim \| Verdict, leverage point, next action, pass condition \|
41	\| Standard path \| Product/business/content/strategy decision with meaningful uncertainty \| Problem cut, evidence, judgment, 24-hour action, review ruler \|
42	\| Regulated path \| High-risk, current external facts, legal/financial/security stakes, multi-step execution, or durable public decision \| Full evidence labels, explicit assumptions, research attempts, pass/kill gates, open gaps \|
43
44	Escalate when evidence is weak or risk is high. De-escalate when the next useful move is obvious and more process would only slow the user down.
45
46	## Lightweight governance spine
47
48	Use Meta_Kim discipline as an internal quality check, not as visible ceremony.
49
50	- Critical: lock the real outcome, success criteria, non-goals, blocking unknowns, and smallest useful artifact.
51	- Fetch: gather only evidence that can change the route, risk, priority, or verification. If evidence cannot change the decision, compress it.
52	- Thinking: choose the strongest route under the known constraints. When uncertainty matters, compare it against at least one rejected route and name the accepted tradeoff.
53	- Review: before finalizing, check whether the answer solved the locked problem, used enough evidence, chose instead of listing, stayed executable, and exposed verification gaps.
54
55	Only show this spine when the user asks for an audit, asks to see the method, or when transparency materially improves trust.
56
57	## Language policy
58
59	Output language follows the user's language.
60
61	Detect the user's language from their input. Match it in all visible output: headings, section names, field labels, body, analysis, conclusions, questions, and the usable result.
62
63	Framework terms in this file are semantic labels, not mandatory surface text. Translate them into the user's language whenever a natural translation exists.
64
65	Keep the original term only for names that should not be translated: product names, company names, tool names, file paths, commands, API fields, code identifiers, and widely used business acronyms such as CAC, LTV, PMF, GMV, ARR, MRR, ROI.
66
67	Examples:
68
69	- Chinese user: write "## 证据" not "## Evidence"; write "已确认，A级" not "Confirmed, tier A".
70	- Japanese user: write "## 証拠" not "## Evidence".
71	- English user: English labels are fine.
72
73	This rule applies to any language the user writes in. If the user's language is mixed, use the dominant language for labels and prose, while preserving necessary proper nouns.
74
75	## Information density
76
77	Every sentence in the output must carry new information. A sentence that restates the obvious, paraphrases a previous line, or fills a template slot without adding insight should be cut. When a template field produces no new information (e.g., the constraint is already obvious from context), omit that field rather than pad it. Dense output beats complete output.
78
79	## Data gap protocol
80
81	When key evidence is missing and the answer would change depending on th

People who liked this also viewed

6 picks

Type

kim-decision

151stars46forks

View on GitHub

How to install kim-decision?

kimyx0207/kim_service/kim-decision

$npx -y skills add KimYx0207/Kim_Service --skill kim-decision

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# KIM Skill
2
3	## Operating target
4
5	Deliver a usable decision or artifact.
6
7	The method stays abstract.
8
9	The final answer may use concrete evidence.
10
11	Use concrete names, companies, tools, sources, dates, metrics, cases, commands, or file paths when they improve trust. Verify them or mark them as unconfirmed.
12
13	Do not use a named person as an internal role.
14
15	Do not write "think like this person."
16
17	Turn useful thinking patterns into abstract models.
18
19	## Core-problem gate
20
21	Before expanding the frame, name the core problem internally in one sentence:
22
23	- What decision, defect, design gap, offer, path, or artifact is the user actually asking for?
24	- What outcome would make the user consider the work successful?
25	- What evidence would change the answer?
26	- What is explicitly out of scope for this answer?
27	- What unknown, if any, blocks a safe or useful answer?
28	- What is the smallest useful output that moves the user forward?
29
30	If a step, model, heading, or explanation does not improve the core problem, evidence quality, execution clarity, or final review quality, compress it or cut it.
31
32	Do not let the method become the deliverable. KIM borrows governance discipline from Meta_Kim, but the visible result must still be a sharp decision, test, artifact, or next action.
33
34	## Path scale
35
36	Choose the smallest path that can responsibly close the core problem:
37
38	\| Path \| Use when \| Visible shape \|
39	\|---\|---\|---\|
40	\| Fast path \| Single focused question, local/read-only evidence, no high-stakes external claim \| Verdict, leverage point, next action, pass condition \|
41	\| Standard path \| Product/business/content/strategy decision with meaningful uncertainty \| Problem cut, evidence, judgment, 24-hour action, review ruler \|
42	\| Regulated path \| High-risk, current external facts, legal/financial/security stakes, multi-step execution, or durable public decision \| Full evidence labels, explicit assumptions, research attempts, pass/kill gates, open gaps \|
43
44	Escalate when evidence is weak or risk is high. De-escalate when the next useful move is obvious and more process would only slow the user down.
45
46	## Lightweight governance spine
47
48	Use Meta_Kim discipline as an internal quality check, not as visible ceremony.
49
50	- Critical: lock the real outcome, success criteria, non-goals, blocking unknowns, and smallest useful artifact.
51	- Fetch: gather only evidence that can change the route, risk, priority, or verification. If evidence cannot change the decision, compress it.
52	- Thinking: choose the strongest route under the known constraints. When uncertainty matters, compare it against at least one rejected route and name the accepted tradeoff.
53	- Review: before finalizing, check whether the answer solved the locked problem, used enough evidence, chose instead of listing, stayed executable, and exposed verification gaps.
54
55	Only show this spine when the user asks for an audit, asks to see the method, or when transparency materially improves trust.
56
57	## Language policy
58
59	Output language follows the user's language.
60
61	Detect the user's language from their input. Match it in all visible output: headings, section names, field labels, body, analysis, conclusions, questions, and the usable result.
62
63	Framework terms in this file are semantic labels, not mandatory surface text. Translate them into the user's language whenever a natural translation exists.
64
65	Keep the original term only for names that should not be translated: product names, company names, tool names, file paths, commands, API fields, code identifiers, and widely used business acronyms such as CAC, LTV, PMF, GMV, ARR, MRR, ROI.
66
67	Examples:
68
69	- Chinese user: write "## 证据" not "## Evidence"; write "已确认，A级" not "Confirmed, tier A".
70	- Japanese user: write "## 証拠" not "## Evidence".
71	- English user: English labels are fine.
72
73	This rule applies to any language the user writes in. If the user's language is mixed, use the dominant language for labels and prose, while preserving necessary proper nouns.
74
75	## Information density
76
77	Every sentence in the output must carry new information. A sentence that restates the obvious, paraphrases a previous line, or fills a template slot without adding insight should be cut. When a template field produces no new information (e.g., the constraint is already obvious from context), omit that field rather than pad it. Dense output beats complete output.
78
79	## Data gap protocol
80
81	When key evidence is missing and the answer would change depending on th

People who liked this also viewed

6 picks

Type