github-trending-analyzer

Name: github-trending-analyzer
Author: Dianel555

64stars6forks

How to install github-trending-analyzer?

dianel555/dskills/github-trending-analyzer

$npx -y skills add Dianel555/DSkills --skill github-trending-analyzer

Installs into the current project.

Summary

Crawl GitHub trending repositories, analyze with LLM for Chinese insights, categorize by themes, compute diffs against history, and generate briefing plus detailed reports in Markdown. Supports incremental gap-filling and selective re-analysis with caching.

Files · 1

View on GitHub

SKILL.md

1	# GitHub Trending Analyzer
2
3	A workflow protocol for tracking GitHub trending repositories with LLM-powered analysis. Fetches trending projects, enriches each with structured Chinese insights (what/analogy/help/who), classifies by themes, compares against historical snapshots, and generates dual-format reports (briefing + detailed).
4
5	## Trigger Signals
6
7	- GitHub trending analysis
8	- Weekly tech trend report
9	- Repository discovery automation
10	- Incremental analysis refresh
11	- Theme-based repo categorization
12
13	## Preconditions
14
15	- HTTP access to github.com/trending (no auth required for public trending)
16	- LLM backend capable of JSON-structured output (for the 4-field analysis schema)
17	- File system access for memory cache and report output
18	- HTML parsing capability (regex or DOM parser)
19
20	## Strategy
21
22	Run the five-step pipeline in order.
23
24	### Step 1: Fetch trending HTML
25
26	Construct the URL with time range and optional language filter:
27	```
28	https://github.com/trending[/{language}]?since={daily\|weekly\|monthly}
29	```
30
31	Fetch with a browser User-Agent to avoid bot detection. Parse the HTML to extract:
32	- `name` (org/repo)
33	- `url` (full GitHub link)
34	- `desc` (one-line description from the page)
35	- `lang` (primary language)
36	- `stars` (total stargazers count)
37	- `today_stars` (increment for this period)
38
39	Regex patterns (reference from source):
40	- Project name: `<h2[^>]>.?<a href="/([^"]+)"`
41	- Description: `<p class="[^"]col-9[^"]"[^>]>\s(.?)\s</p>`
42	- Language: `<span itemprop="programmingLanguage">([^<]+)</span>`
43	- Stars: parse from `/stargazers` link text after stripping HTML tags
44	- Today increment: `([\d,]+)\sstars?\s(?:this\|today)` (case-insensitive)
45
46	### Step 2: Batch LLM analysis
47
48	For each batch of 5 projects (to avoid token limits), send this prompt to your LLM:
49
50	```
51	Analyze the following {N} GitHub Trending projects. Output strict JSON array.
52	Each project needs 4 fields:
53	- what: What it is (≤30 Chinese characters)
54	- analogy: Life analogy (one sentence)
55	- help: What it helps you do (2 items, each ≤40 chars, array)
56	- who: Who needs it (one sentence, ≤30 chars)
57
58	Project list:
59	1. org/repo (Language) — description...
60	2. ...
61
62	Output ONLY the JSON array, no other text. Example:
63	[{"name":"org/repo","what":"...","analogy":"...","help":["...","..."],"who":"..."}]
64	```
65
66	Parse the response:
67	1. Strip markdown code fences (` ```json ` / ` ``` `)
68	2. Clean trailing commas: `,\s*([\]}])` → `\1`
69	3. Extract the JSON array via regex: `\[.*\]` (DOTALL)
70	4. Decode with `json.loads()` or equivalent
71	5. Match results back to projects by name suffix (case-insensitive)
72
73	Fallback: If array parsing fails, extract individual objects via bracket-counting and parse one by one.
74
75	Deep mode (optional): Use longer limits (what ≤50 chars, help 3 items) for richer analysis.
76
77	### Step 3: Theme classification
78
79	Load the bundled `theme_rules.json`. For each project:
80	1. Concatenate `name + " " + desc` and lowercase
81	2. Iterate themes by priority order
82	3. Check if any keyword from the theme appears in the text
83	4. Assign to first matching theme
84	5. Default to "🌐 其他" if no match
85
86	Result: `{theme_name: [projects...]}` dictionary.
87
88	### Step 4: Compute diff (optional)
89
90	If you maintain a memory cache (JSON file storing past runs):
91	```json
92	[
93	{
94	"date": "2026-06-19",
95	"since": "weekly",
96	"lang": "python",
97	"repos": [{"name":"...", "url":"...", "desc":"...", "lang":"...", "stars":..., "today_stars":..., "analysis":{...}}]
98	}
99	]
100	```
101
102	Compare current repos against the latest entry with the same `since` value:
103	- new: projects in current but not in last
104	- hot: projects in both
105	- dropped: projects in last but not in current
106	- last_date: baseline timestamp
107
108	### Step 5: Generate reports
109
110	#### Briefing (compact, for quick scan)
111
112	Structure:
113	```markdown
114	# GitHub 热门趋势简报 - {date}
115
116	> 生成日期: {date}
117	> 来源: github.com/trending?since={since}
118	> 对比基准: {baseline_date}
119
120	## 🔥 新上榜
121	\| 排名 \| 项目 \| 语言 \| ⭐ Stars \| 📈 今日新增 \| 一句话说明 \|
122
123	## ⭐ 持续热门
124	\| 项目 \| 语言 \| ⭐ Stars \| 📈 今日新增 \| 为什么值得关注 \|
125
126	## 📉 掉出榜单
127	\| 项目 \| 可能意味着什么 \|
128
129	## 🎯 趋势主题
130	{theme} (N个): repo1(+stars), repo2(+stars), ...
131
132	## 💡 趋势解读
133	{LLM-generated trend insight based on all "what" summaries}
134	```
135
136	Trend insight prompt:
137	```
138	基于以下GitHub Trending项目摘要，用3-5句话分析当前最强技术趋势和驱动力：
139	{list of "name: what" for all projects}
140	```
141
142	#### Detailed (one section per project)
143
144	Structure:
145	```markdown
146	# GitHub 详细分析 - {date}
147
148	## {Project Name}
149
150	Stars: {total} (+{increment})
151	Language: {lang}
152	URL: {github_url}
153
154	### 这是什么
155	{analysis.what}
156
157	### 生活化类比
158	{analysis.analogy}
159
160	### 它能帮你做什么
161	1. {analysis.help[0]}
162	2. {analysis.help[1]}
163
164	### 谁需要它
165	{analysis.who}
166
167	---
168	```
169
170	Save both to files with date-stamped names (e.g. `tre

People who liked this also viewed

6 picks

Type

github-trending-analyzer

64stars6forks

View on GitHub

How to install github-trending-analyzer?

dianel555/dskills/github-trending-analyzer

$npx -y skills add Dianel555/DSkills --skill github-trending-analyzer

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# GitHub Trending Analyzer
2
3	A workflow protocol for tracking GitHub trending repositories with LLM-powered analysis. Fetches trending projects, enriches each with structured Chinese insights (what/analogy/help/who), classifies by themes, compares against historical snapshots, and generates dual-format reports (briefing + detailed).
4
5	## Trigger Signals
6
7	- GitHub trending analysis
8	- Weekly tech trend report
9	- Repository discovery automation
10	- Incremental analysis refresh
11	- Theme-based repo categorization
12
13	## Preconditions
14
15	- HTTP access to github.com/trending (no auth required for public trending)
16	- LLM backend capable of JSON-structured output (for the 4-field analysis schema)
17	- File system access for memory cache and report output
18	- HTML parsing capability (regex or DOM parser)
19
20	## Strategy
21
22	Run the five-step pipeline in order.
23
24	### Step 1: Fetch trending HTML
25
26	Construct the URL with time range and optional language filter:
27	```
28	https://github.com/trending[/{language}]?since={daily\|weekly\|monthly}
29	```
30
31	Fetch with a browser User-Agent to avoid bot detection. Parse the HTML to extract:
32	- `name` (org/repo)
33	- `url` (full GitHub link)
34	- `desc` (one-line description from the page)
35	- `lang` (primary language)
36	- `stars` (total stargazers count)
37	- `today_stars` (increment for this period)
38
39	Regex patterns (reference from source):
40	- Project name: `<h2[^>]>.?<a href="/([^"]+)"`
41	- Description: `<p class="[^"]col-9[^"]"[^>]>\s(.?)\s</p>`
42	- Language: `<span itemprop="programmingLanguage">([^<]+)</span>`
43	- Stars: parse from `/stargazers` link text after stripping HTML tags
44	- Today increment: `([\d,]+)\sstars?\s(?:this\|today)` (case-insensitive)
45
46	### Step 2: Batch LLM analysis
47
48	For each batch of 5 projects (to avoid token limits), send this prompt to your LLM:
49
50	```
51	Analyze the following {N} GitHub Trending projects. Output strict JSON array.
52	Each project needs 4 fields:
53	- what: What it is (≤30 Chinese characters)
54	- analogy: Life analogy (one sentence)
55	- help: What it helps you do (2 items, each ≤40 chars, array)
56	- who: Who needs it (one sentence, ≤30 chars)
57
58	Project list:
59	1. org/repo (Language) — description...
60	2. ...
61
62	Output ONLY the JSON array, no other text. Example:
63	[{"name":"org/repo","what":"...","analogy":"...","help":["...","..."],"who":"..."}]
64	```
65
66	Parse the response:
67	1. Strip markdown code fences (` ```json ` / ` ``` `)
68	2. Clean trailing commas: `,\s*([\]}])` → `\1`
69	3. Extract the JSON array via regex: `\[.*\]` (DOTALL)
70	4. Decode with `json.loads()` or equivalent
71	5. Match results back to projects by name suffix (case-insensitive)
72
73	Fallback: If array parsing fails, extract individual objects via bracket-counting and parse one by one.
74
75	Deep mode (optional): Use longer limits (what ≤50 chars, help 3 items) for richer analysis.
76
77	### Step 3: Theme classification
78
79	Load the bundled `theme_rules.json`. For each project:
80	1. Concatenate `name + " " + desc` and lowercase
81	2. Iterate themes by priority order
82	3. Check if any keyword from the theme appears in the text
83	4. Assign to first matching theme
84	5. Default to "🌐 其他" if no match
85
86	Result: `{theme_name: [projects...]}` dictionary.
87
88	### Step 4: Compute diff (optional)
89
90	If you maintain a memory cache (JSON file storing past runs):
91	```json
92	[
93	{
94	"date": "2026-06-19",
95	"since": "weekly",
96	"lang": "python",
97	"repos": [{"name":"...", "url":"...", "desc":"...", "lang":"...", "stars":..., "today_stars":..., "analysis":{...}}]
98	}
99	]
100	```
101
102	Compare current repos against the latest entry with the same `since` value:
103	- new: projects in current but not in last
104	- hot: projects in both
105	- dropped: projects in last but not in current
106	- last_date: baseline timestamp
107
108	### Step 5: Generate reports
109
110	#### Briefing (compact, for quick scan)
111
112	Structure:
113	```markdown
114	# GitHub 热门趋势简报 - {date}
115
116	> 生成日期: {date}
117	> 来源: github.com/trending?since={since}
118	> 对比基准: {baseline_date}
119
120	## 🔥 新上榜
121	\| 排名 \| 项目 \| 语言 \| ⭐ Stars \| 📈 今日新增 \| 一句话说明 \|
122
123	## ⭐ 持续热门
124	\| 项目 \| 语言 \| ⭐ Stars \| 📈 今日新增 \| 为什么值得关注 \|
125
126	## 📉 掉出榜单
127	\| 项目 \| 可能意味着什么 \|
128
129	## 🎯 趋势主题
130	{theme} (N个): repo1(+stars), repo2(+stars), ...
131
132	## 💡 趋势解读
133	{LLM-generated trend insight based on all "what" summaries}
134	```
135
136	Trend insight prompt:
137	```
138	基于以下GitHub Trending项目摘要，用3-5句话分析当前最强技术趋势和驱动力：
139	{list of "name: what" for all projects}
140	```
141
142	#### Detailed (one section per project)
143
144	Structure:
145	```markdown
146	# GitHub 详细分析 - {date}
147
148	## {Project Name}
149
150	Stars: {total} (+{increment})
151	Language: {lang}
152	URL: {github_url}
153
154	### 这是什么
155	{analysis.what}
156
157	### 生活化类比
158	{analysis.analogy}
159
160	### 它能帮你做什么
161	1. {analysis.help[0]}
162	2. {analysis.help[1]}
163
164	### 谁需要它
165	{analysis.who}
166
167	---
168	```
169
170	Save both to files with date-stamped names (e.g. `tre

People who liked this also viewed

6 picks

Type