agents2agentsai/hn-discoverer
codex-rs/skills/src/assets/research/hn-discoverer/SKILL.md
INTERNAL SUBAGENT SKILL — never invoke directly. This is called automatically by $hn-synthesis to discover relevant HN threads. If a user asks about HN discussions, use $hn-synthesis instead.
$ install --global
skillsauthnpx skillsauth add agents2agentsai/ata hn-discovererInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
70%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 7, 2026, 1:24 PM212.1s1 file scanned
SKILL.md
- name:
- hn-discoverer
- description:
- INTERNAL SUBAGENT SKILL — never invoke directly. This is called automatically by $hn-synthesis to discover relevant HN threads. If a user asks about HN discussions, use $hn-synthesis instead.
- short-description:
- [Internal] Subagent skill for hn-synthesis discovery
- allow_implicit_invocation:
- false
HN Discoverer
Search Hacker News for threads relevant to the given topic, deduplicate, rank, and return top thread IDs.
Instructions
- Run multiple
hn_searchcalls in parallel to maximize coverage — varysort_by(relevance, date),min_points(5, 50), andcontent_type(story, comment). - Use synonyms and related terms for broad topics (e.g., "AI agent" / "LLM agent" / "agentic").
- Use
date_from/date_to(YYYY-MM-DD) when user specifies a timeframe. - Deduplicate by
object_id. Appearing in multiple searches = positive signal, weight higher. - Rank by: relevance, points, comment count (prefer 10+ comments over high-point low-comment), recency.
- Return top 3-7 threads.
Do NOT call spawn_agent, present_reading_view, hn_get_thread, or any file tools. Your only tool is hn_search.
Return Format
THREAD <story_id> | <points> pts | <num_comments> comments | <title> | <hn_url> | <linked_url>
<linked_url>: the article/blog/paper URL, or (self) for Ask HN / text posts. Include 1-sentence topic context per thread.
Related Skills
agents2agentsai/workspace
testing
VerifiedTrustedCommunity
Multi-repo workspace management: clone repos, create execution runs, track papers/datasets/artifacts, manage snapshots, and review audit logs. Use when the user wants to organize multi-repo work, run experiments in sandboxes, or track research resources.
69SKILL.mdUpdated Mar 26, 2026
agents2agentsai/spreadsheets
tools
VerifiedTrustedCommunity
Build, edit, recalculate, import, and export spreadsheet workbooks with the preloaded @oai/artifact-tool JavaScript surface through the artifacts tool.
69SKILL.mdUpdated Mar 26, 2026
agents2agentsai/slides
tools
VerifiedTrustedCommunity
Build, edit, render, import, and export presentation decks with the preloaded @oai/artifact-tool JavaScript surface through the artifacts tool.
69SKILL.mdUpdated Mar 26, 2026
agents2agentsai/skill-installer
development
VerifiedTrustedCommunity
Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).
69SKILL.mdUpdated Mar 26, 2026