explain

Name: explain
Author: kv0906

2installs33forks

How to install explain?

kv0906/pm-kit/explain

$npx -y skills add kv0906/pm-kit --skill explain

Installs into the current project.

Summary

Break down complex concepts (math, models, systems, terminology) into first-principles explanations. Use when user says "explain", "break this down", "first principles", "ELI5", or pastes a formula/model/system to understand.

Files · 1

View on GitHub

SKILL.md

1	# Explain — First Principles Concept Breaker
2
3	Reverse-engineer complex concepts into natural language. No jargon. Start from the end result and work backwards to raw inputs.
4
5	Input format: `/explain [concept, formula, model, or paste]`
6
7	## What You Do
8
9	Take any complex input — math formula, scoring model, system design, methodology, technical concept — and explain it so a beginner can explain it back.
10
11	## Input
12
13	User provides:
14	- A math problem, equation, methodology, scoring system, model, or abstract concept
15	- Optional: context of what it's used for (finance, physics, prediction markets, etc.)
16
17	## Reasoning Process (follow in order)
18
19	Work through these steps internally before writing the explanation:
20
21	A. Find the End Goal — What is the final output? Translate it to a real-world result (money, score, probability, decision, ranking).
22
23	B. Find the Inputs — What raw information goes in? Translate each to real-world meaning.
24
25	C. Find How Value Is Earned — What actions/factors increase the result? What decreases it?
26
27	D. Find Comparisons — Does the model compare things? (person vs person, side vs side, time vs time). Explain as "share of total" or "relative contribution".
28
29	E. Find Rules and Boundaries — Minimums, maximums, penalties, special cases. Explain why each exists.
30
31	F. Find Time/Repetition — If the model samples repeatedly, explain as "measured many times and added up over time."
32
33	G. Find What Breaks Without Each Piece — For each major component, ask: what goes wrong if we remove this? This reveals WHY it exists.
34
35	## Output Structure
36
37	Write these sections in order:
38
39	### 1. What This Produces
40
41	One sentence: what the final output represents in real life.
42
43	### 2. What Controls It
44
45	List the real-world factors that push the result up or down. No symbols.
46
47	### 3. Reverse Walkthrough (End → Beginning)
48
49	Start from the final result. Walk backwards through each layer until reaching raw inputs. Each step should answer: "where does THIS come from?"
50
51	### 4. What Each Part Measures (and Why)
52
53	For each component:
54	- What it measures in plain language
55	- Why it exists (what breaks without it)
56	- What behavior it rewards or punishes
57
58	### 5. Rules of the Game
59
60	Rewrite the entire model as a rulebook using "If you do X, then Y happens" statements. No math.
61
62	### 6. Concrete Example
63
64	Small example with simple numbers. Show how changing one input changes the outcome.
65
66	### 7. One-Paragraph Summary
67
68	Compress everything into one short paragraph a beginner could repeat back.
69
70	## Style Rules
71
72	- Short sentences. Natural wording.
73	- No symbols unless user insists.
74	- No jargon: avoid "quadratic", "normalization", "distribution", "convex", "derivative", "expectation", "linear regression" etc.
75	- When jargon is unavoidable, immediately follow with a plain restatement: "normalization — meaning we shrink everything to fit on the same scale"
76	- Use everyday metaphors: sharing a pie, scoring a game, competition ranking, filling a bucket.
77	- Prioritize meaning over calculation.
78	- Write to a file in `docs/` when output exceeds 20 lines (per vault conventions).
79
80	## Fail-Safes
81
82	If the input is ambiguous or missing definitions:
83	- Make the best interpretation
84	- State assumptions explicitly
85	- Still explain the likely intent
86
87	## Success Criteria
88
89	Your explanation succeeds if:
90	- A beginner can explain the system back to you
91	- The user knows what actions increase/decrease results
92	- The user understands why each major piece exists (not just what it does)

People who liked this also viewed

6 picks

Type

grill-with-docsA relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.SkillsJul 2026537k182k
lark-minutes飞书妙记：搜索妙记、查看妙记基础信息、下载/上传音视频、读取或编辑妙记的产物内容、改标题、替换说话人/关键词、申请妙记查看/编辑权限。当给出minute_token、本地音视频文件，要查/改/转妙记产物，或用户明确要主动申请妙记权限时使用；本地音视频转纪要/逐字稿优先走本 skill，不要用 ffmpeg/whisper 本地转写。不负责：获取会议关联妙记，或仅按自然语言标题定位纪要SkillsJul 2026379k16k
lark-markdown飞书 Markdown：查看、创建、上传、编辑和比较 Markdown 文件。当用户需要创建或编辑 Markdown 文件、读取、修改、局部 patch 或比较差异时使用。不负责将 Markdown 导入为飞书在线文档，也不负责文件搜索、权限、评论、移动、删除等云空间管理操作。SkillsJul 2026295k16k
docxUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', SkillsJul 2026157k163k
edit-articleSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026154k181k
lark-note飞书会议纪要（Note）直查：已知 note_id 时查询纪要详情、展示类型、关联文档 token，并读取 unified 原始逐字记录。当用户已持有 note_id，或从文档显式 vc-node-id 获得 note_id 时使用。不负责会议/日程/妙记定位、文档标题搜索或 Docx 正文读取。SkillsJul 2026154k16k

explain

2installs33forks

View on GitHub

How to install explain?

kv0906/pm-kit/explain

$npx -y skills add kv0906/pm-kit --skill explain

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Explain — First Principles Concept Breaker
2
3	Reverse-engineer complex concepts into natural language. No jargon. Start from the end result and work backwards to raw inputs.
4
5	Input format: `/explain [concept, formula, model, or paste]`
6
7	## What You Do
8
9	Take any complex input — math formula, scoring model, system design, methodology, technical concept — and explain it so a beginner can explain it back.
10
11	## Input
12
13	User provides:
14	- A math problem, equation, methodology, scoring system, model, or abstract concept
15	- Optional: context of what it's used for (finance, physics, prediction markets, etc.)
16
17	## Reasoning Process (follow in order)
18
19	Work through these steps internally before writing the explanation:
20
21	A. Find the End Goal — What is the final output? Translate it to a real-world result (money, score, probability, decision, ranking).
22
23	B. Find the Inputs — What raw information goes in? Translate each to real-world meaning.
24
25	C. Find How Value Is Earned — What actions/factors increase the result? What decreases it?
26
27	D. Find Comparisons — Does the model compare things? (person vs person, side vs side, time vs time). Explain as "share of total" or "relative contribution".
28
29	E. Find Rules and Boundaries — Minimums, maximums, penalties, special cases. Explain why each exists.
30
31	F. Find Time/Repetition — If the model samples repeatedly, explain as "measured many times and added up over time."
32
33	G. Find What Breaks Without Each Piece — For each major component, ask: what goes wrong if we remove this? This reveals WHY it exists.
34
35	## Output Structure
36
37	Write these sections in order:
38
39	### 1. What This Produces
40
41	One sentence: what the final output represents in real life.
42
43	### 2. What Controls It
44
45	List the real-world factors that push the result up or down. No symbols.
46
47	### 3. Reverse Walkthrough (End → Beginning)
48
49	Start from the final result. Walk backwards through each layer until reaching raw inputs. Each step should answer: "where does THIS come from?"
50
51	### 4. What Each Part Measures (and Why)
52
53	For each component:
54	- What it measures in plain language
55	- Why it exists (what breaks without it)
56	- What behavior it rewards or punishes
57
58	### 5. Rules of the Game
59
60	Rewrite the entire model as a rulebook using "If you do X, then Y happens" statements. No math.
61
62	### 6. Concrete Example
63
64	Small example with simple numbers. Show how changing one input changes the outcome.
65
66	### 7. One-Paragraph Summary
67
68	Compress everything into one short paragraph a beginner could repeat back.
69
70	## Style Rules
71
72	- Short sentences. Natural wording.
73	- No symbols unless user insists.
74	- No jargon: avoid "quadratic", "normalization", "distribution", "convex", "derivative", "expectation", "linear regression" etc.
75	- When jargon is unavoidable, immediately follow with a plain restatement: "normalization — meaning we shrink everything to fit on the same scale"
76	- Use everyday metaphors: sharing a pie, scoring a game, competition ranking, filling a bucket.
77	- Prioritize meaning over calculation.
78	- Write to a file in `docs/` when output exceeds 20 lines (per vault conventions).
79
80	## Fail-Safes
81
82	If the input is ambiguous or missing definitions:
83	- Make the best interpretation
84	- State assumptions explicitly
85	- Still explain the likely intent
86
87	## Success Criteria
88
89	Your explanation succeeds if:
90	- A beginner can explain the system back to you
91	- The user knows what actions increase/decrease results
92	- The user understands why each major piece exists (not just what it does)

People who liked this also viewed

6 picks

Type