Agent skill

instinct-apply

Surfaces relevant instincts during work. Use when starting a task to check if any learned behaviors apply.

Stars 357
Forks 44

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

bash
# 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

  1. Read the task/context
  2. Check instinct triggers
  3. If trigger matches, follow the action
  4. Note confidence level - higher confidence = more certain

Instinct Structure

yaml
---
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:

  1. Don't apply it blindly
  2. Note the mismatch
  3. 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-style instincts
  • Running tests? → Check testing instincts
  • Making commits? → Check git instincts
  • Debugging? → Check debugging instincts

Be efficient. Instincts are meant to help, not slow down.

Expand your agent's capabilities with these related and highly-rated skills.

humanplane/homunculus

session-memory

Maintains awareness across sessions. Spawns observer agent on start, loads context, notifies of evolution opportunities.

357 44
Explore
davila7/claude-code-templates

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.

23,776 2,298
Explore
davila7/claude-code-templates

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.

23,776 2,298
Explore
davila7/claude-code-templates

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.

23,776 2,298
Explore
davila7/claude-code-templates

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.

23,776 2,298
Explore
davila7/claude-code-templates

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.

23,776 2,298
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results