best-in-world-research

Name: best-in-world-research
Author: stevembarclay

33stars2forks

How to install best-in-world-research?

stevembarclay/pencilplaybook/best-in-world-research

$npx -y skills add stevembarclay/pencilplaybook --skill best-in-world-research

Installs into the current project.

Summary

World-class practice research. This skill should be used when the user asks what the best in the world does about a specific problem, technique, or situation — covering product, engineering, design, marketing, compliance, operations, org design, and any other domain. Use when the

Files · 1

View on GitHub

SKILL.md

1	# Best-In-World Research
2
3	Surface what elite practitioners actually do. Concise by default. Rigorous always.
4
5	## The Question This Skill Answers
6
7	> "What does the best in the world do about [X]?"
8
9	This is a research question, not a strategy question. The output is an expert brief — not a decision framework. Use `best-in-world-strategy` when the goal is to choose between options with tradeoffs scored. Use this skill when the goal is: what does excellent look like here?
10
11	## Mode Selection
12
13	Determine mode before responding:
14
15	- Simple or directional question → Quick mode automatically. Do not ask.
16	- Open-ended or "I don't know where to start" question → Ask: "Quick answer or comprehensive breakdown?" before responding.
17	- User says "quick" / "fast" / "brief" → Quick mode.
18	- User says "deep" / "comprehensive" / "full" → Deep mode.
19
20	## Quick Mode (default for most questions)
21
22	Answer in expert voice. No headers. No bullet scaffolding unless the question naturally has a list answer. Conversational but authoritative — like you're quoting the person who spent 25 years solving exactly this problem.
23
24	Quick mode rules:
25	- Name who: the specific company, team, person, or practitioner archetype that owns this domain. Not "top SaaS companies." Specific.
26	- State what they do: observable behavior, not belief. "They do X" not "they believe in Y."
27	- Give the mechanism: one sentence on why it works.
28	- Flag confidence if inferred: note when a practice is attributed vs. confirmed by primary source.
29	- Length: 2–4 short paragraphs or 4–6 bullets. No longer.
30
31	Example quick answer tone:
32	> "If you asked the team that built Stripe's API, they'd tell you every error object returns four fields: `code`, `message`, `param`, and `doc_url`. The `doc_url` is the move most people skip — it turns a cryptic error into a solvable problem in one click. The pattern: errors are documentation. If a developer hits an error and can't fix it in two minutes, the error message failed, not the developer."
33
34	## Deep Mode (on request or open-ended questions)
35
36	For when the user doesn't know the landscape and needs the full picture. Still not a dissertation — disciplined and structured, but concise within structure.
37
38	Deep mode output:
39
40	```
41	## What the Best in the World Does: [Topic]
42
43	### Elite Practitioners
44	- [Name/Company]: [what makes them credible here — specific signal, not reputation]
45	- [Name/Company]: ...
46	- [Name/Company]: ...
47
48	### What They Actually Do
49	[For each practitioner: 2–3 concrete practices. Specific and observable. Note confidence: confirmed / inferred / attributed.]
50
51	### The Pattern
52	[2–3 cross-cutting behaviors that appear across the best. Name each. One sentence on the mechanism.]
53
54	### What Mediocre Looks Like
55	[The common approach most people take, and why it fails — include the failure mechanism, not just the label.]
56
57	### Starting Point
58	[Minimum viable world-class for this problem. What you can do this week. The single thing that separates good from elite.]
59	```
60
61	Target length for deep mode: 400–600 words. If it's longer, cut.
62
63	## Quality Bar (both modes)
64
65	- Never say "top companies" or "industry leaders" — name them specifically.
66	- Distinguish what practitioners do from what they say. Published principles often lag private practice.
67	- Concrete = "Netflix uses chaos engineering tools that randomly kill production services during business hours." Not concrete = "Netflix prioritizes resilience."
68	- Anti-patterns require the failure mechanism — why the bad approach still gets chosen, not just that it's bad.
69	- Flag inferences. Don't present second-hand attribution as confirmed practice.
70	- No padding. If you don't know specific practitioners for a niche domain, say so and give the best inference you have with a confidence note.

People who liked this also viewed

6 picks

Type

best-in-world-research

33stars2forks

View on GitHub

How to install best-in-world-research?

stevembarclay/pencilplaybook/best-in-world-research

$npx -y skills add stevembarclay/pencilplaybook --skill best-in-world-research

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Best-In-World Research
2
3	Surface what elite practitioners actually do. Concise by default. Rigorous always.
4
5	## The Question This Skill Answers
6
7	> "What does the best in the world do about [X]?"
8
9	This is a research question, not a strategy question. The output is an expert brief — not a decision framework. Use `best-in-world-strategy` when the goal is to choose between options with tradeoffs scored. Use this skill when the goal is: what does excellent look like here?
10
11	## Mode Selection
12
13	Determine mode before responding:
14
15	- Simple or directional question → Quick mode automatically. Do not ask.
16	- Open-ended or "I don't know where to start" question → Ask: "Quick answer or comprehensive breakdown?" before responding.
17	- User says "quick" / "fast" / "brief" → Quick mode.
18	- User says "deep" / "comprehensive" / "full" → Deep mode.
19
20	## Quick Mode (default for most questions)
21
22	Answer in expert voice. No headers. No bullet scaffolding unless the question naturally has a list answer. Conversational but authoritative — like you're quoting the person who spent 25 years solving exactly this problem.
23
24	Quick mode rules:
25	- Name who: the specific company, team, person, or practitioner archetype that owns this domain. Not "top SaaS companies." Specific.
26	- State what they do: observable behavior, not belief. "They do X" not "they believe in Y."
27	- Give the mechanism: one sentence on why it works.
28	- Flag confidence if inferred: note when a practice is attributed vs. confirmed by primary source.
29	- Length: 2–4 short paragraphs or 4–6 bullets. No longer.
30
31	Example quick answer tone:
32	> "If you asked the team that built Stripe's API, they'd tell you every error object returns four fields: `code`, `message`, `param`, and `doc_url`. The `doc_url` is the move most people skip — it turns a cryptic error into a solvable problem in one click. The pattern: errors are documentation. If a developer hits an error and can't fix it in two minutes, the error message failed, not the developer."
33
34	## Deep Mode (on request or open-ended questions)
35
36	For when the user doesn't know the landscape and needs the full picture. Still not a dissertation — disciplined and structured, but concise within structure.
37
38	Deep mode output:
39
40	```
41	## What the Best in the World Does: [Topic]
42
43	### Elite Practitioners
44	- [Name/Company]: [what makes them credible here — specific signal, not reputation]
45	- [Name/Company]: ...
46	- [Name/Company]: ...
47
48	### What They Actually Do
49	[For each practitioner: 2–3 concrete practices. Specific and observable. Note confidence: confirmed / inferred / attributed.]
50
51	### The Pattern
52	[2–3 cross-cutting behaviors that appear across the best. Name each. One sentence on the mechanism.]
53
54	### What Mediocre Looks Like
55	[The common approach most people take, and why it fails — include the failure mechanism, not just the label.]
56
57	### Starting Point
58	[Minimum viable world-class for this problem. What you can do this week. The single thing that separates good from elite.]
59	```
60
61	Target length for deep mode: 400–600 words. If it's longer, cut.
62
63	## Quality Bar (both modes)
64
65	- Never say "top companies" or "industry leaders" — name them specifically.
66	- Distinguish what practitioners do from what they say. Published principles often lag private practice.
67	- Concrete = "Netflix uses chaos engineering tools that randomly kill production services during business hours." Not concrete = "Netflix prioritizes resilience."
68	- Anti-patterns require the failure mechanism — why the bad approach still gets chosen, not just that it's bad.
69	- Flag inferences. Don't present second-hand attribution as confirmed practice.
70	- No padding. If you don't know specific practitioners for a niche domain, say so and give the best inference you have with a confidence note.

People who liked this also viewed

6 picks

Type