Agent skill
instinct-apply
Surfaces relevant instincts during work. Use when starting a task to check if any learned behaviors apply.
Install this agent skill to your Project
npx add-skill https://github.com/humanplane/homunculus/tree/main/plugins/homunculus/skills/instinct-apply
SKILL.md
Instinct Apply
You have learned behaviors. Use them.
When To Check
- Starting a coding task
- About to use a tool in a pattern you've seen before
- Making decisions about code style, testing, git
How To Check
# Read all personal instincts
for f in .claude/homunculus/instincts/personal/*.md; do
[ -f "$f" ] && echo "=== $(basename "$f") ===" && cat "$f" && echo
done 2>/dev/null
# Also check inherited instincts
for f in .claude/homunculus/instincts/inherited/*.md; do
[ -f "$f" ] && echo "=== $(basename "$f") ===" && cat "$f" && echo
done 2>/dev/null
How To Apply
- Read the task/context
- Check instinct triggers
- If trigger matches, follow the action
- Note confidence level - higher confidence = more certain
Instinct Structure
---
trigger: "when [condition]"
confidence: 0.7
domain: "code-style"
---
# Name
## Action
What to do
## Evidence
Why this exists
Confidence Interpretation
- 0.3-0.5: Tentative. Apply if it feels right.
- 0.5-0.7: Moderate. Apply unless there's a reason not to.
- 0.7-0.9: Strong. Apply consistently.
- 0.9+: Near certain. Always apply.
If Instinct Seems Wrong
When an instinct fires but the action feels wrong for the situation:
- Don't apply it blindly
- Note the mismatch
- This is useful data for the observer
Instincts can be wrong. They're learned from patterns, and patterns have exceptions.
Lightweight Application
Don't read all instincts for every action. Keep relevant ones in working memory.
Quick domain check:
- Writing code? → Check
code-styleinstincts - Running tests? → Check
testinginstincts - Making commits? → Check
gitinstincts - Debugging? → Check
debugginginstincts
Be efficient. Instincts are meant to help, not slow down.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
session-memory
Maintains awareness across sessions. Spawns observer agent on start, loads context, notifies of evolution opportunities.
verl-rl-training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
openrlhf-training
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
gguf-quantization
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
Claude Code Guide
Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best practices for interacting with the agent.
qdrant-vector-search
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.
Didn't find tool you were looking for?