hn-digest
Skill17 starsChanged 3 months agoApache-2.0View on GitHub
Generate HN digests in org-mode format. Use when curating Hacker News stories, creating digests, or converting between JSON/org/HTML formats.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- tomy0000000/skillstheir own version, first seen Mar 2, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- tomy0000000/skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
Files
HN Digest Skill
Curate Hacker News stories into structured org-mode files with translations.
Workflow
HN API (JSON) → Claude (curate) → .org file → HTML thread
↑ ↓
└──────── reversible ──────────┘Quick Start
Curate new digest
# 1. Fetch stories (workflow does this)
# 2. Claude reads /tmp/hn/stories.json, writes digest
# 3. Convert to org. In the workflow, DIGEST_DATE and DIGEST_PATH are set
# and override the JSON date and the path argument (see json2org.py).
python3 scripts/json2org.py /tmp/digest.json digests/2025/12/15-1100.org
# 4. Build the site (all editions; only changed files are written)
python3 scripts/org2html.py digests/*/*/*.orgValidate round-trip
python3 scripts/org2json.py digests/2025/12/15-1100.org /tmp/check.json
# Should match originalOrg Format
#+TITLE: HN Digest 2025-12-15 11:00 UTC
#+DATE: 2025-12-15T11:00:00Z
* Vibe
Roomba dies, Arduino goes corporate...
* Stories
** Robot vacuum Roomba maker files for bankruptcy :robotics:hardware:
:PROPERTIES:
:ID: 46268854
:URL: https://news.bloomberglaw.com/...
:HN_URL: https://news.ycombinator.com/item?id=46268854
:POINTS: 191
:COMMENTS: 182
:END:
*** TLDR
iRobot filed Chapter 11 bankruptcy...
*** Take
Roborock ate their lunch...
*** Comments
**** simonjgreen
This is the cost of complacency.
*** i18n :i18n:
**** zh
***** TLDR
iRobot申请了第11章破产...Scripts
| Script | Purpose |
json2org.py | Convert curated JSON → org file |
org2json.py | Parse org → JSON (validation) |
org2html.py | Render all org files → the static site (index, archive, e/, editions.json) |
llms-gen.py | Generate llms.txt index |
Properties Reference
Story properties in :PROPERTIES: drawer:
| Property | Description |
:ID: | HN story ID (required) |
:URL: | Article URL |
:HN_URL: | HN discussion URL |
:POINTS: | Score at fetch time |
:COMMENTS: | Comment count |
:BY: | Submitter username |
:TIME: | Submission time (ISO) |
i18n Structure
Translations as subheadings under *** i18n:
*** i18n :i18n:
**** zh
:PROPERTIES:
:LANG: zh
:END:
***** TLDR
Chinese translation...
***** Take
Chinese opinion...
**** ja
:PROPERTIES:
:LANG: ja
:END:
***** TLDR
Japanese translation...Supported languages: zh, ja, ko, es, de
See Also
- ARCHITECTURE.md - Full design doc
- REFERENCE.md - API reference for scripts
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

