visionaire-knowledge
Skill4 starsChanged 43 days agoMITView on GitHub
Inject relevant self-study knowledge into task context using BM25 search over Visionaire's knowledge base. Use before starting any creative, strategic, technical, or research task — brand work, Solana/Web3, content creation, prompt engineering, agent skills, or generative AI. Triggers on task starts and when phrases like "what do we know about", "recall knowledge", "check knowledge base", or "inject context" appear. Always run this before producing significant work so past study improves output quality.
In this repository17 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/popular-web-designs/templates/claude.mdCLAUDE.md
- llms.txtllms.txt
- public/llms-full.txtllms.txt
- public/llms.txtllms.txt
- openclaw-deckSkill
- arxivSkill
- blogwatcherSkill
- gemini-deep-researchSkill
- p5jsSkill
- polymarketSkill
- popular-web-designsSkill
- subagent-driven-developmentSkill
- twitter-algorithm-optimizerSkill
- visionaire-feedbackSkill
- youtube-contentSkill
- youtube-transcriptSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Before working on any significant task, search the knowledge base and inject relevant context.
- Distinctive: line 17
Read the output — treat it as ## Relevant Context for the task ahead
- Distinctive: line 18
If results are thin or off-topic, try a second query with different terms
- Distinctive: line 25
Don't inject stale or irrelevant results — use judgment on what's actually useful
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Visionaire Knowledge Injection
Before working on any significant task, search the knowledge base and inject relevant context.
Steps
- Derive a 3–7 word query from the task (e.g. "solana token mechanics", "brand strategy content", "prompt engineering techniques")
- Run the search:
node /data/.openclaw/skills/visionaire-knowledge/scripts/search-knowledge.mjs "<query>" --limit 5 - Read the output — treat it as ## Relevant Context for the task ahead
- If results are thin or off-topic, try a second query with different terms
Notes
- Knowledge base lives at
/data/.openclaw/workspace/memory/knowledge.json - Entries are scored by relevance + recency (30-day half-life decay — fresh study ranks higher)
- "(no relevant knowledge found)" is fine — just means the base hasn't studied that topic yet
- Don't inject stale or irrelevant results — use judgment on what's actually useful
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.