show-hn-writer

Name: show-hn-writer
Author: Varnan-Tech

20installs59forks

How to install show-hn-writer?

varnan-tech/opendirectory/show-hn-writer

$npx -y skills add Varnan-Tech/opendirectory --skill show-hn-writer

Installs into the current project.

Summary

Draft a Show HN post backed by real HN performance data. Uses observed patterns from 250 top HN posts to maximise score.

Files · 1

View on GitHub

SKILL.md

1	# Show HN Writer — Data-Backed Edition
2
3	This skill drafts HN posts using patterns extracted from 250 real top-ranking posts.
4	Every rule below comes from observed data, not convention.
5
6	---
7
8	## What the data says (internalize this before writing anything)
9
10	These are the findings from 250 top HN posts scraped April 18 2026. They override
11	any received wisdom about HN writing.
12
13	Title length is the single strongest predictor of score.
14	- Under 40 chars: avg 248 pts (n=82)
15	- 40–59 chars: avg 192 pts (n=68)
16	- 60–79 chars: avg 150 pts (n=91)
17	- 80+ chars: avg 131 pts (n=9)
18	Default target: under 40 characters. Hard ceiling: 60.
19
20	Body text does not affect score.
21	90% of posts had no body. With-body avg: 189. Without-body avg: 193. Statistically
22	identical. A body is only worth writing if you have genuinely interesting technical
23	detail that won't fit in a title. Never write a body to pad credibility.
24
25	Show HN prefix suppresses score.
26	Show HN posts averaged 94 pts vs 186+ for plain statements. The label signals
27	"I want feedback on my thing" which triggers a more skeptical read. Only use "Show HN:"
28	when the project is genuinely novel. Always offer a plain-title alternative.
29
30	First-person titles outperform anonymous statements.
31	First-person ("I…", "My…", "We…"): avg 291 pts (n=9).
32	Plain statement: avg 186 pts (n=126).
33	If the builder's perspective is part of the story, lead with it.
34
35	Questions generate comments more than upvotes.
36	Question titles avg ratio of comments-to-score above 1.0×. Best for discussions,
37	not for raw score. Ask the user which they're optimising for before writing.
38
39	Themes that consistently outperform:
40	- Security / backdoor / breach stories: avg 308 pts
41	- Privacy / surveillance / data stories: avg 282 pts
42	- AI / LLM releases: avg 266 pts (42 posts — largest category)
43	- Open source releases: avg 485 pts (small n, but strong signal)
44
45	The highest-scoring titles share one trait: they are stories, not topics.
46	"Someone bought 30 WordPress plugins and planted a backdoor in all of them" — 1192 pts.
47	"Google broke its promise to me – now ICE has my data" — 1688 pts.
48	A topic is "WordPress plugin security". A story has an actor, an action, and stakes.
49
50	---
51
52	## Step 1: Ask the user one question before anything else
53
54	Before drafting, ask:
55
56	"Two quick questions:
57	1. Are you optimising for score (reach) or comments (discussion)?
58	2. What does the project do — one sentence, technical, no adjectives?"
59
60	Do not proceed until you have both answers.
61
62	---
63
64	## Step 2: Determine the right post type
65
66	Based on the project and goal, decide which format to use:
67
68	Plain title (recommended default)
69	No prefix. Just what it is or what happened. Highest avg score.
70	Use when: sharing a release, article, tool, or event.
71
72	Show HN: prefix (use sparingly)
73	Use only when: the project is a working demo, the builder is present to answer
74	questions, and the technical implementation is the interesting part.
75	Avg score is low (94), but it signals authenticity when the project is genuinely novel.
76	Always also draft a plain-title alternative for comparison.
77
78	Ask HN: prefix
79	Use when: the goal is discussion, not promotion. Avg engagement ratio > 1.0×.
80	Best for "who is using X?" or "should I do Y?" posts.
81
82	Tell HN: prefix
83	Whistleblowing, accountability, or disclosure. One data point at 819 pts.
84	Only use if the post is factual, verifiable, and the builder is named.
85
86	---
87
88	## Step 3: Draft the title
89
90	The title is the entire post. Treat the body as optional.
91
92	Rules derived from data:
93	- Target under 40 characters. Every 20 chars over that costs roughly 30 avg points.
94	- Write a story, not a category. Actor + action + stakes beats noun phrases.
95	- First person ("I…") adds ~100 pts avg vs plain statement when builder perspective matters.
96	- No marketing adjectives. Not "fast", "simple", "powerful", "lightweight" unless
97	it is a literal spec (e.g. "35B-A3B" is a spec, "powerful" is not).
98	- Specificity beats generality. "30 WordPress plugins" beats "popular CMS plugins".
99	- Year in brackets signals classic worth reading: (2008), (1956). Use when linking
100	older content that has aged well.
101	- En dash (–) for subtitle format: "Product Name – what it does". Not a hyphen (-).
102
103	Draft three variants:
104	1. Shortest possible (aim for under 35 chars) — strip everything non-essential
105	2. Story angle — actor + action + stakes
106	3. Technical angle — lead with the interesting engineering decision
107
108	Then apply the length test: count chars on each. Flag any over 60.
109
110	---
111
112	## Step 4: Decide whether to write a body
113
114	Ask yourself: does the technical implementation have a detail that cannot fit in
115	the title and that HN en

People who liked this also viewed

6 picks

Type

seo-auditWhen the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tagSkillsJul 2026168k41k
copywritingWhen the user wants to write, rewrite, or improve marketing copy for any page — including homepage, landing pages, pricing pages, feature pages, about pages, or product pages. Also use when the user sSkillsJul 2026159k41k
marketing-psychologyWhen the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'mental models,' 'cognitive bias,' 'persuasion,'SkillsJul 2026116k41k
content-strategyWhen the user wants to plan a content strategy, decide what content to create, or figure out what topics to cover. Also use when the user mentions "content strategy," "what should I write about," "conSkillsJul 2026111k41k
programmatic-seoWhen the user wants to create SEO-driven pages at scale using templates and data. Also use when the user mentions "programmatic SEO," "template pages," "pages at scale," "directory pages," "location pSkillsJul 2026107k41k
marketing-ideasWhen the user needs marketing ideas, inspiration, or strategies for their SaaS or software product. Also use when the user asks for 'marketing ideas,' 'growth ideas,' 'how to market,' 'marketing stratSkillsJul 2026104k41k

show-hn-writer

20installs59forks

View on GitHub

How to install show-hn-writer?

varnan-tech/opendirectory/show-hn-writer

$npx -y skills add Varnan-Tech/opendirectory --skill show-hn-writer

Installs into the current project.

Summary

Draft a Show HN post backed by real HN performance data. Uses observed patterns from 250 top HN posts to maximise score.

Files · 1

View on GitHub

SKILL.md

1	# Show HN Writer — Data-Backed Edition
2
3	This skill drafts HN posts using patterns extracted from 250 real top-ranking posts.
4	Every rule below comes from observed data, not convention.
5
6	---
7
8	## What the data says (internalize this before writing anything)
9
10	These are the findings from 250 top HN posts scraped April 18 2026. They override
11	any received wisdom about HN writing.
12
13	Title length is the single strongest predictor of score.
14	- Under 40 chars: avg 248 pts (n=82)
15	- 40–59 chars: avg 192 pts (n=68)
16	- 60–79 chars: avg 150 pts (n=91)
17	- 80+ chars: avg 131 pts (n=9)
18	Default target: under 40 characters. Hard ceiling: 60.
19
20	Body text does not affect score.
21	90% of posts had no body. With-body avg: 189. Without-body avg: 193. Statistically
22	identical. A body is only worth writing if you have genuinely interesting technical
23	detail that won't fit in a title. Never write a body to pad credibility.
24
25	Show HN prefix suppresses score.
26	Show HN posts averaged 94 pts vs 186+ for plain statements. The label signals
27	"I want feedback on my thing" which triggers a more skeptical read. Only use "Show HN:"
28	when the project is genuinely novel. Always offer a plain-title alternative.
29
30	First-person titles outperform anonymous statements.
31	First-person ("I…", "My…", "We…"): avg 291 pts (n=9).
32	Plain statement: avg 186 pts (n=126).
33	If the builder's perspective is part of the story, lead with it.
34
35	Questions generate comments more than upvotes.
36	Question titles avg ratio of comments-to-score above 1.0×. Best for discussions,
37	not for raw score. Ask the user which they're optimising for before writing.
38
39	Themes that consistently outperform:
40	- Security / backdoor / breach stories: avg 308 pts
41	- Privacy / surveillance / data stories: avg 282 pts
42	- AI / LLM releases: avg 266 pts (42 posts — largest category)
43	- Open source releases: avg 485 pts (small n, but strong signal)
44
45	The highest-scoring titles share one trait: they are stories, not topics.
46	"Someone bought 30 WordPress plugins and planted a backdoor in all of them" — 1192 pts.
47	"Google broke its promise to me – now ICE has my data" — 1688 pts.
48	A topic is "WordPress plugin security". A story has an actor, an action, and stakes.
49
50	---
51
52	## Step 1: Ask the user one question before anything else
53
54	Before drafting, ask:
55
56	"Two quick questions:
57	1. Are you optimising for score (reach) or comments (discussion)?
58	2. What does the project do — one sentence, technical, no adjectives?"
59
60	Do not proceed until you have both answers.
61
62	---
63
64	## Step 2: Determine the right post type
65
66	Based on the project and goal, decide which format to use:
67
68	Plain title (recommended default)
69	No prefix. Just what it is or what happened. Highest avg score.
70	Use when: sharing a release, article, tool, or event.
71
72	Show HN: prefix (use sparingly)
73	Use only when: the project is a working demo, the builder is present to answer
74	questions, and the technical implementation is the interesting part.
75	Avg score is low (94), but it signals authenticity when the project is genuinely novel.
76	Always also draft a plain-title alternative for comparison.
77
78	Ask HN: prefix
79	Use when: the goal is discussion, not promotion. Avg engagement ratio > 1.0×.
80	Best for "who is using X?" or "should I do Y?" posts.
81
82	Tell HN: prefix
83	Whistleblowing, accountability, or disclosure. One data point at 819 pts.
84	Only use if the post is factual, verifiable, and the builder is named.
85
86	---
87
88	## Step 3: Draft the title
89
90	The title is the entire post. Treat the body as optional.
91
92	Rules derived from data:
93	- Target under 40 characters. Every 20 chars over that costs roughly 30 avg points.
94	- Write a story, not a category. Actor + action + stakes beats noun phrases.
95	- First person ("I…") adds ~100 pts avg vs plain statement when builder perspective matters.
96	- No marketing adjectives. Not "fast", "simple", "powerful", "lightweight" unless
97	it is a literal spec (e.g. "35B-A3B" is a spec, "powerful" is not).
98	- Specificity beats generality. "30 WordPress plugins" beats "popular CMS plugins".
99	- Year in brackets signals classic worth reading: (2008), (1956). Use when linking
100	older content that has aged well.
101	- En dash (–) for subtitle format: "Product Name – what it does". Not a hyphen (-).
102
103	Draft three variants:
104	1. Shortest possible (aim for under 35 chars) — strip everything non-essential
105	2. Story angle — actor + action + stakes
106	3. Technical angle — lead with the interesting engineering decision
107
108	Then apply the length test: count chars on each. Flag any over 60.
109
110	---
111
112	## Step 4: Decide whether to write a body
113
114	Ask yourself: does the technical implementation have a detail that cannot fit in
115	the title and that HN en

People who liked this also viewed

6 picks

Type