daily-brief

Name: daily-brief
Author: leiting-eric

298stars159forks

How to install daily-brief?

leiting-eric/dailybrief/daily-brief

$npx -y skills add leiting-eric/DailyBrief --skill daily-brief

Installs into the current project.

Summary

Operational knowledge for the daily-brief digest pipeline (this project). RSS/API fetchers, pluggable LLM enrichment (default claude CLI on Max; also anthropic/openai/deepseek/minimax API), trading section, HTML rendering, cross-platform scheduler integration (Windows Task Schedu

Files · 1

View on GitHub

SKILL.md

1	# daily-brief — Operational Skill
2
3	This project generates a single-page HTML daily digest covering tech / finance / politics / market data / community discussion. The pipeline runs locally via the OS scheduler (Windows Task Scheduler / macOS launchd / Linux cron, default 08:00 local time) and emits `daily_reports/<YYYY-MM-DD>/<YYYY-MM-DD>.html` + sidecar files (each date gets its own subdir). The date label uses the system local timezone by default — set `REPORT_TZ` (e.g. `Asia/Shanghai`, `UTC`) in `.env.local` to override.
4
5	Detailed architecture lives in code; this skill is a cheat sheet for operating and diagnosing, not a re-explanation of the system.
6
7	## Project root assumption
8
9	All paths in this skill are relative to the project root (the directory that contains `package.json`, `lib/`, `scripts/`).
10
11	Before any command, ensure the working directory is the project root. Two cases:
12
13	1. Claude Code session opened inside the project — already there, no action needed
14	2. Session opened elsewhere — read the config file and `cd`:
15
16	```bash
17	# Cross-platform Node one-liner (prints the project root path):
18	node -e "const fs=require('fs'),os=require('os'),path=require('path');const cfg=path.join(os.homedir(),'.daily-brief-config');if(fs.existsSync(cfg))console.log(fs.readFileSync(cfg,'utf8').trim());else process.exit(1)"
19	```
20
21	Use the printed path: `cd "$(...)"` on bash / `Set-Location (...)` in PowerShell.
22
23	The config file is written by `node scripts/install.mjs --global`. If it's missing the user hasn't done a global install — tell them to run it.
24
25	## Quick command reference
26
27	\| Need \| Command \| Cost \|
28	\|---\|---\|---\|
29	\| Full pipeline \| `npm run daily` \| ~5-8 min, ~6 Sonnet calls \|
30	\| Fetch sanity only (no LLM) \| `npm run dry-run` \| ~30s \|
31	\| Re-render existing sidecar \| `npm run render [date]` \| <1s \|
32	\| Re-run trading section \| `npm run regen-trading [date]` \| ~2 min, 1 LLM call \|
33	\| Top-up missing summary \| `npm run regen-enrich <cat:sub> [date]` \| ~20-40s, 1 LLM call \|
34	\| Open today's report in Chrome \| `npm run open` \| instant \|
35	\| Sonnet quota + call history \| `npm run quota-report` \| instant \|
36
37	`[date]` defaults to today's date in the report timezone (system local, or `REPORT_TZ` if set). The pipeline and the OS scheduler both run in local time, so the report's date label = the date when the trigger fired in the report timezone. A user with `REPORT_TZ=Asia/Shanghai` whose machine fires the trigger at 23:00 UTC-8 will get a "next-day Shanghai" file, e.g. `daily_reports/2026-05-17/2026-05-17.html`.
38
39	`<cat:sub>` accepted by `regen-enrich`: `finance:news`, `politics:world`, `tech:ai-news`. Single-source X 推文 (`tech:x-viral`) is enriched as part of `daily` only — no top-up path.
40
41	## File map — where to change what
42
43	\| Task \| File \|
44	\|---\|---\|
45	\| Add / disable / re-categorize a source \| `sources.config.json` (project root — single source of truth; `lib/sources/registry.ts` is just a loader) \|
46	\| Rename L1 tab labels \| `lib/output/render.ts` `CATEGORY_LABELS` \|
47	\| Reorder / rename L2 subcategories \| `SUBCATEGORY_ORDER` + `SUBCATEGORY_LABELS` in same file \|
48	\| Change per-source item cap \| `SOURCE_DISPLAY_LIMITS` \|
49	\| Change merged-timeline cap \| `MERGED_SUBGROUP_LIMITS` \|
50	\| Add a Sonnet enrichment prompt \| `lib/ai/enrich.ts` — copy `XVIRAL_SYSTEM_PROMPT` pattern \|
51	\| Wire an enrichment into pipeline \| `scripts/daily.ts` — `await enrichXxx(articles)` in `main()` \|
52	\| Add a new fetcher type \| New file in `lib/sources/` + branch in `lib/sources/dispatch.ts` \|
53	\| Adjust HTML styling \| inline `<style>` block in `renderHtml()` in `lib/output/render.ts` \|
54	\| Change scheduler trigger time \| `node scripts/install.mjs --at HH:MM` (re-registers) \|
55	\| Wrapper script the scheduler invokes \| `scripts/run-daily.mjs` \|
56
57	## How LLM enrichment works (mental model)
58
59	- Each merged L2 subcategory gets a Sonnet pass: GH-trending (per-source), finance:news, politics:world, tech:ai-news, tech:x-viral.
60	- Each pass = one batched Sonnet call for all items in that subgroup. Don't iterate per-item.
61	- Sources with `lang: "zh"` in registry skip enrichment (already Chinese).
62	- Failures are non-fatal: skipped articles just render without `summary`.
63
64	## Diagnostic flow
65
66	Order matters — top-to-botto

People who liked this also viewed

6 picks

Type

daily-brief

298stars159forks

View on GitHub

How to install daily-brief?

leiting-eric/dailybrief/daily-brief

$npx -y skills add leiting-eric/DailyBrief --skill daily-brief

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# daily-brief — Operational Skill
2
3	This project generates a single-page HTML daily digest covering tech / finance / politics / market data / community discussion. The pipeline runs locally via the OS scheduler (Windows Task Scheduler / macOS launchd / Linux cron, default 08:00 local time) and emits `daily_reports/<YYYY-MM-DD>/<YYYY-MM-DD>.html` + sidecar files (each date gets its own subdir). The date label uses the system local timezone by default — set `REPORT_TZ` (e.g. `Asia/Shanghai`, `UTC`) in `.env.local` to override.
4
5	Detailed architecture lives in code; this skill is a cheat sheet for operating and diagnosing, not a re-explanation of the system.
6
7	## Project root assumption
8
9	All paths in this skill are relative to the project root (the directory that contains `package.json`, `lib/`, `scripts/`).
10
11	Before any command, ensure the working directory is the project root. Two cases:
12
13	1. Claude Code session opened inside the project — already there, no action needed
14	2. Session opened elsewhere — read the config file and `cd`:
15
16	```bash
17	# Cross-platform Node one-liner (prints the project root path):
18	node -e "const fs=require('fs'),os=require('os'),path=require('path');const cfg=path.join(os.homedir(),'.daily-brief-config');if(fs.existsSync(cfg))console.log(fs.readFileSync(cfg,'utf8').trim());else process.exit(1)"
19	```
20
21	Use the printed path: `cd "$(...)"` on bash / `Set-Location (...)` in PowerShell.
22
23	The config file is written by `node scripts/install.mjs --global`. If it's missing the user hasn't done a global install — tell them to run it.
24
25	## Quick command reference
26
27	\| Need \| Command \| Cost \|
28	\|---\|---\|---\|
29	\| Full pipeline \| `npm run daily` \| ~5-8 min, ~6 Sonnet calls \|
30	\| Fetch sanity only (no LLM) \| `npm run dry-run` \| ~30s \|
31	\| Re-render existing sidecar \| `npm run render [date]` \| <1s \|
32	\| Re-run trading section \| `npm run regen-trading [date]` \| ~2 min, 1 LLM call \|
33	\| Top-up missing summary \| `npm run regen-enrich <cat:sub> [date]` \| ~20-40s, 1 LLM call \|
34	\| Open today's report in Chrome \| `npm run open` \| instant \|
35	\| Sonnet quota + call history \| `npm run quota-report` \| instant \|
36
37	`[date]` defaults to today's date in the report timezone (system local, or `REPORT_TZ` if set). The pipeline and the OS scheduler both run in local time, so the report's date label = the date when the trigger fired in the report timezone. A user with `REPORT_TZ=Asia/Shanghai` whose machine fires the trigger at 23:00 UTC-8 will get a "next-day Shanghai" file, e.g. `daily_reports/2026-05-17/2026-05-17.html`.
38
39	`<cat:sub>` accepted by `regen-enrich`: `finance:news`, `politics:world`, `tech:ai-news`. Single-source X 推文 (`tech:x-viral`) is enriched as part of `daily` only — no top-up path.
40
41	## File map — where to change what
42
43	\| Task \| File \|
44	\|---\|---\|
45	\| Add / disable / re-categorize a source \| `sources.config.json` (project root — single source of truth; `lib/sources/registry.ts` is just a loader) \|
46	\| Rename L1 tab labels \| `lib/output/render.ts` `CATEGORY_LABELS` \|
47	\| Reorder / rename L2 subcategories \| `SUBCATEGORY_ORDER` + `SUBCATEGORY_LABELS` in same file \|
48	\| Change per-source item cap \| `SOURCE_DISPLAY_LIMITS` \|
49	\| Change merged-timeline cap \| `MERGED_SUBGROUP_LIMITS` \|
50	\| Add a Sonnet enrichment prompt \| `lib/ai/enrich.ts` — copy `XVIRAL_SYSTEM_PROMPT` pattern \|
51	\| Wire an enrichment into pipeline \| `scripts/daily.ts` — `await enrichXxx(articles)` in `main()` \|
52	\| Add a new fetcher type \| New file in `lib/sources/` + branch in `lib/sources/dispatch.ts` \|
53	\| Adjust HTML styling \| inline `<style>` block in `renderHtml()` in `lib/output/render.ts` \|
54	\| Change scheduler trigger time \| `node scripts/install.mjs --at HH:MM` (re-registers) \|
55	\| Wrapper script the scheduler invokes \| `scripts/run-daily.mjs` \|
56
57	## How LLM enrichment works (mental model)
58
59	- Each merged L2 subcategory gets a Sonnet pass: GH-trending (per-source), finance:news, politics:world, tech:ai-news, tech:x-viral.
60	- Each pass = one batched Sonnet call for all items in that subgroup. Don't iterate per-item.
61	- Sources with `lang: "zh"` in registry skip enrichment (already Chinese).
62	- Failures are non-fatal: skipped articles just render without `summary`.
63
64	## Diagnostic flow
65
66	Order matters — top-to-botto

People who liked this also viewed

6 picks

Type