← Back to Skills Marketplace
edmonddantesj

AOI Hackathon Scout (Lite)

by edmonddantesj · GitHub ↗ · v0.1.6
cross-platform ✓ Security Clean
930
Downloads
0
Stars
0
Active Installs
7
Versions
Install in OpenClaw
/install aoi-hackathon-scout-lite
Description
Public-safe hackathon source registry + filtering output (no crawling, no submissions).
README (SKILL.md)

AOI Hackathon Scout (Lite)

S-DNA: AOI-2026-0215-SDNA-HACK01

Quick Start (copy/paste)

# 1) install
clawhub install aoi-hackathon-scout-lite

# 2) shortlist view / best-effort recommendations
# (reads context/HACKATHON_SHORTLIST.md)
aoi-hackathon recommend --n 5

# 3) browse sources (no API keys)
aoi-hackathon sources
openclaw browser start
openclaw browser open https://devpost.com/c/artificial-intelligence
openclaw browser snapshot --efficient

Scope (public-safe)

  • ✅ Outputs curated source list for hackathons / builder programs / grants
  • ✅ Provides a filtering view: online-only preference, type tags
  • ✅ Provides a paste-ready summary template for the user
  • ❌ No crawling, no login, no form-fill, no submission automation
  • ❌ No Notion API usage in the public skill (paste template only)

Data source

  • Uses the local registry file:
    • context/HACKATHON_SOURCES_REGISTRY.md

Commands

Show sources

aoi-hackathon sources

Filter (best-effort)

# show only likely-online sources
# (filters Online-only fit = ✅ or ⚠️)
aoi-hackathon sources --online ok

# show only web3 sources
aoi-hackathon sources --type web3

Recommend from shortlist (best-effort)

# reads context/HACKATHON_SHORTLIST.md and prints top N online-eligible items
# (excludes rejected; prioritizes 🔥 markers and 'applying/watching')
aoi-hackathon recommend --n 5

Print Notion paste template (text only)

aoi-hackathon template

Setup (early users)

This skill is public-safe and does not require API keys by default.

Recommended default: Browser/web_fetch (no keys)

  • Use OpenClaw Browser to open sources and inspect deadlines/details.
  • Quick start: 
    openclaw browser start
openclaw browser open https://devpost.com/c/artificial-intelligence
openclaw browser snapshot --efficient

Optional: Brave Search API (fast keyword search)

If you want ultra-fast keyword search, you can enable Brave Search for web_search.

  • Get key: https://brave.com/search/api/ (choose Data for Search plan)
  • Configure (example): 
    openclaw config set tools.web.search.provider brave
openclaw config set tools.web.search.apiKey "BRAVE_API_KEY_HERE"
openclaw config set tools.web.search.enabled true
  • Disable again: 
    openclaw config set tools.web.search.enabled false

(Full setup guide in repo SSOT: context/HACKATHON_SEARCH_SETUP_GUIDE_V0_1.md)

Support

Provenance / originality

  • AOI implementation is original code.
  • Registry content is a curated link list.
Usage Guidance
This skill is coherent and appears to only read local markdown files in context/ and print filtered JSON. Before installing, (1) inspect your workspace's context/HACKATHON_SOURCES_REGISTRY.md and context/HACKATHON_SHORTLIST.md for any sensitive data (the skill will read those files), (2) avoid setting WORKSPACE to a directory containing secrets because the script uses that env var to find files, and (3) if you want to be extra cautious, review the included skill.js file yourself (it is short and readable). The optional Brave Search instructions in SKILL.md are informational only and do not grant the skill network access unless you configure OpenClaw tools separately.
Capability Analysis
Type: OpenClaw Skill Name: aoi-hackathon-scout-lite Version: 0.1.6 The skill is classified as benign. The `SKILL.md` explicitly states a 'public-safe' scope, disclaiming crawling, submissions, or Notion API usage, which the `skill.js` code adheres to. The JavaScript code performs only local file reads within the skill's workspace (`context/HACKATHON_SOURCES_REGISTRY.md`, `context/HACKATHON_SHORTLIST.md`, `context/HACKATHON_NOTION_PASTE_TEMPLATE.md`) and processes this data. There are no network calls, external command executions, or attempts to access sensitive system resources or environment variables beyond `WORKSPACE`. Instructions in `SKILL.md` for the agent to use `openclaw browser` or `openclaw config set` are for legitimate tool usage and optional setup (e.g., setting a placeholder API key), not for malicious prompt injection or unauthorized actions. No evidence of data exfiltration, persistence, or obfuscation was found.
Capability Assessment
✓ Purpose & Capability
Name/description match implementation: the skill reads local markdown registry/shortlist files, filters and ranks entries, and prints JSON; no crawling, form submission, or external credentials are required.
✓ Instruction Scope
SKILL.md and the CLI implementation only instruct the agent to read files under context/ (HACKATHON_SOURCES_REGISTRY.md, HACKATHON_SHORTLIST.md, optional template) and to use the OpenClaw browser for manual inspection. The README's optional Brave Search advice is informational and not required by the code.
✓ Install Mechanism
This is an instruction-only / lightweight node script with no install spec and no dependencies; nothing is downloaded or extracted at install time.
ℹ Credentials
No credentials or config paths are declared, which is appropriate. The code reads process.env.WORKSPACE (fallback to cwd) to locate context/ files — WORKSPACE is not documented in SKILL.md as a required env var; this is low-risk but means the skill will read files relative to whichever workspace root is used, so a maliciously-set WORKSPACE could point it at unexpected locations.
✓ Persistence & Privilege
always is false and the skill does not modify other skills or system settings; it only reads local files and prints output.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install aoi-hackathon-scout-lite
  3. After installation, invoke the skill by name or use /aoi-hackathon-scout-lite
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.6
docs: include recommend --n 5 in Quick Start
v0.1.5
docs: add copy/paste quick start
v0.1.4
docs: add early-user setup (OpenClaw Browser + optional Brave Search API)
v0.1.3
Deadline hygiene: parse ISO+TZ when available, exclude expired when parseable, safer regex, improved recommendation sorting.
v0.1.2
Docs: add GitHub Issues support link (aoi-skills).
v0.1.1
Add recommend command (reads shortlist). Expand source registry (lablab.ai, hackathons.dev).
v0.1.0
Initial release: public-safe hackathon source registry + filters + paste template (no crawling, no submissions). MIT.
Metadata
Slug aoi-hackathon-scout-lite
Version 0.1.6
License —
All-time Installs 0
Active Installs 0
Total Versions 7
Frequently Asked Questions

What is AOI Hackathon Scout (Lite)?

Public-safe hackathon source registry + filtering output (no crawling, no submissions). It is an AI Agent Skill for Claude Code / OpenClaw, with 930 downloads so far.

How do I install AOI Hackathon Scout (Lite)?

Run "/install aoi-hackathon-scout-lite" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is AOI Hackathon Scout (Lite) free?

Yes, AOI Hackathon Scout (Lite) is completely free (open-source). You can download, install and use it at no cost.

Which platforms does AOI Hackathon Scout (Lite) support?

AOI Hackathon Scout (Lite) is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created AOI Hackathon Scout (Lite)?

It is built and maintained by edmonddantesj (@edmonddantesj); the current version is v0.1.6.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463815 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259802 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200680 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191345 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190333 · by oswalpalash

💬 Comments