2.6k
GitHub Stars
5
Bundled Files
2 months ago
Catalog Refreshed
3 months ago
First Indexed
Readme & install
Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.
Installation
Preview and clipboard use veilstrat where the catalogue uses aiagentskills.
npx veilstrat add skill openclaw/skills --skill openclaw-skill-intelligence-ingestion- _meta.json329 B
- index.html7.1 KB
- README.md1.0 KB
- SKILL.md5.4 KB
- vercel.json104 B
Overview
This skill auto-ingests any external content (URLs, articles, tweets, pasted text) and evaluates it for OpenClaw strategic value. It classifies the content, performs a structured strategic assessment, maps findings to the OpenClaw architecture, writes a standardized Obsidian note, updates memory, and returns a concise confirmation to the user. The pipeline runs automatically when external content is shared, no permission prompts required.
How this skill works
When a URL or text is received, the skill reads the full content (or searches for tweet text if needed), then assigns one primary category and up to two secondary tags. It runs a strategic assessment template, maps the item to the OpenClaw stack layers, creates a templated Obsidian note at the designated vault path, appends the finding to today’s memory log, and, for high-impact items, updates MEMORY.md and relevant tracking files. Finally, it returns a short, actionable summary to the user.
When to use it
- User shares any URL (articles, GitHub, tweets, threads) or pastes external text.
- User asks 'analyze this', 'evaluate this', or requests strategic value on shared content.
- User forwards content from messaging apps (Telegram, X) or provides links that need parsing.
- When you want consistent archival and memory updates for externally sourced intelligence.
- When deciding whether new info impacts active engineering bottlenecks or tooling.
Best practices
- Always attempt full content fetch; if paywalled, mark content unavailable and use provided text.
- Assign one clear primary category and no more than two secondary tags for consistent indexing.
- Be explicit about relation to the Active Engineering Bottleneck when assessing strategic value.
- Use the exact Obsidian filename and note template to maintain archive consistency.
- Append succinct, opinionated analyst notes (Keke's voice) that highlight implications and next steps.
Example use cases
- User posts a research blog about a new model routing technique — classify as strategy and map to Pilot Protocol.
- A tweet thread reveals an API deprecation — tag as threat, create an urgent action item, and update MEMORY.md.
- A tutorial on a new tool appears — tag as tutorial/product, add to TOOLS.md flag list, and propose experiments.
- User shares a community discussion proposing a new principle — flag for PRINCIPLES.md review and memory entry.
FAQ
No. The skill is designed to run automatically on shared external content unless the user explicitly says they do not want analysis.
What happens if the content is non-English or paywalled?
Non-English content is analyzed in original language and notes are written in English. Paywalled or inaccessible content is recorded as 'content unavailable' and processed using any provided excerpts.