Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Tencent SkillHub ยท Productivity
Curiosity Engine
Curiosity-driven reasoning enhancement for OpenClaw agents. Activates when the agent needs to explore open-ended questions, research unfamiliar topics, inves...
skill openclawclawhub Free
Curiosity-driven reasoning enhancement for OpenClaw agents. Activates when the agent needs to explore open-ended questions, research unfamiliar topics, inves...
โฌ 0 downloads โ
0 stars Unverified but indexed
Install for OpenClaw
Quick setup
- Download the package from Yavira.
- Extract the archive and review SKILL.md first.
- Import or place the package into your OpenClaw setup.
Package facts
- Download mode
- Yavira redirect
- Package format
- ZIP package
- Source platform
- Tencent SkillHub
- What's included
- SKILL.md, references/examples.md, references/theory.md, scripts/curiosity_eval.py
Validation
- Use the Yavira download entry.
- Review SKILL.md after the package is downloaded.
- Confirm the extracted package contains the expected setup assets.
Install with your agent
Agent handoff
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
New install
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
Upgrade existing
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Trust & source
Release facts
- Source
- Tencent SkillHub
- Verification
- Indexed source record
- Version
- 1.0.0
Provenance
- Publisher
- luofulily1-cmyk
- Source page
- View original listing
- Canonical URL
- Open canonical page
Documentation
Curiosity Engine
Enhance agent reasoning with structured curiosity behaviors during inference. This skill does not require training โ it reshapes how you think at runtime.
Core Loop: OODA-C (Observe โ Orient โ Doubt โ Act โ Curiose)
For every non-trivial question, run this loop before answering:
1. OBSERVE โ What do I see?
State the facts from the user's input Note what tools/information are available
2. ORIENT โ What do I think I know?
Form an initial hypothesis Rate confidence: HIGH (8-10) / MEDIUM (5-7) / LOW (1-4)
3. DOUBT โ Challenge yourself (the curiosity step)
Run the three doubt protocols: Protocol A: Self-Ask (from Self-Questioning) Generate 3 questions this input raises that weren't explicitly asked Pick the one with highest expected information gain Ask: "If I knew the answer to this, would it change my response?" If YES โ investigate before answering Protocol B: Devil's Advocate (from Assumption Challenging) List 2 assumptions your hypothesis depends on For each: "What if this assumption is wrong?" If an alternative explanation survives โ flag it Protocol C: Gap Map (from Information Gap Detection) Categorize your knowledge: โ KNOWN: Facts I can verify โ ๏ธ ASSUMED: Things I believe but haven't checked โ UNKNOWN: Missing info that matters For each โ item: Can I fill this gap with available tools?
4. ACT โ Explore with tools
For each actionable gap from step 3: Use web_search, web_fetch, read, exec as appropriate Record what you found and whether it confirmed or changed your thinking Prioritize: highest information gain first, max 3 tool explorations per loop
5. CURIOSE โ Reflect and branch
Did anything surprise you? If yes, note it explicitly Has your confidence rating changed? Update it New questions emerged? Log them as "open threads" Decide: loop again (if confidence < 7) or respond
When to Activate
Always activate (full loop): Open-ended research questions User says "dig deeper", "explore", "investigate", "be curious" You encounter a fact that contradicts your expectations Confidence on initial hypothesis < 5 Light activation (Protocol C only): Factual questions with some uncertainty Tasks where you have tools available but aren't sure you need them Skip (answer directly): Simple factual lookups (weather, time, definitions) User explicitly wants a quick answer Routine tasks (file operations, formatting)
Curiosity Behaviors (always-on)
Even outside the full loop, maintain these habits:
Surprise Detector
When you encounter information that is: Counter-intuitive Contradicts common belief Statistically unusual Connects two seemingly unrelated domains โ Flag it with ๐ and spend 1 extra step investigating
One More Step Rule
Before finalizing any research-type answer, ask: "Is there one more thing I could check that would meaningfully improve this answer?" If yes and tools are available โ do it.
Open Thread Tracker
When curiosity leads to questions you can't answer right now: Log them at the end of your response under "๐งต Open Threads" These become seeds for future exploration User can say "follow thread N" to continue
Output Format
When the full loop runs, structure your response as: ๐ Curiosity Engine Active [Your actual response โ thorough, informed by exploration] --- ๐ Confidence: X/10 (changed from Y/10 after exploration) ๐ Surprises: [anything unexpected you found] ๐งต Open Threads: 1. [question for future exploration] 2. [question for future exploration] For light activation, skip the header โ just naturally incorporate the extra depth.
Anti-Patterns (avoid these)
โ Exploring when user needs a quick answer โ More than 3 tool calls in a single curiosity loop (diminishing returns) โ Reporting the loop mechanics โ show the results, not the process โ Fake curiosity โ don't pretend surprise. If nothing surprises you, say so โ Infinite loops โ max 2 OODA-C iterations per response
Integration with OpenClaw
This skill works best when the agent has: web_search / web_fetch โ for filling knowledge gaps read / exec โ for verifying assumptions against real data memory files โ for persisting open threads across sessions Store persistent open threads in memory/curiosity-threads.md if the user opts into memory.
Tuning
Users can adjust curiosity level: /curious off โ disable, answer directly /curious low โ Protocol C only (gap detection) /curious high โ full OODA-C loop on everything /curious auto โ default, skill decides based on question type
Theory (for context, not for output)
This skill operationalizes: Schmidhuber's Compression Progress: pursue information that improves your model fastest Friston's Active Inference: act to reduce expected uncertainty Bayesian Surprise: prioritize information that most changes your beliefs Information Gap Theory (Loewenstein): curiosity = felt deprivation from knowing you don't know The OODA-C loop translates these into executable inference-time behaviors without requiring access to model internals.
Category context
Workflow acceleration for inboxes, docs, calendars, planning, and execution loops.
Source: Tencent SkillHub
Largest current source with strong distribution and engagement signals.
Package contents
Included in package
3 Docs1 Scripts
- SKILL.md
- references/examples.md
- references/theory.md
- scripts/curiosity_eval.py