Brali Agent Skill · practical · usable

Balance Safety and Risk

When safety increases: - Assess risks: Ask, "Am I compensating for safety by taking unnecessary risks?" - Set boundaries: Stick to cautious habits even in safer environments. - Focus on long-term impact: Remember that short-term safety doesn’t eliminate long-term consequences. Example: Driving a car with advanced safety features? Avoid speeding just because you feel more protected.

AgentSkills.iopracticalusableCognitive Biases
Open SKILL.mdCanonical recordVerification JSONAll Agent Skills

Portable instruction

What the agent should do

When safety increases: - Assess risks: Ask, "Am I compensating for safety by taking unnecessary risks?" - Set boundaries: Stick to cautious habits even in safer environments. - Focus on long-term impact: Remember that short-term safety doesn’t eliminate long-term consequences. Example: Driving a car with advanced safety features? Avoid speeding just because you feel more protected.

Check-in

Check in when you avoid risky behaviors that counteract increased safety.

Install

One portable file, host-specific location.

Inspect SKILL.md first. The evidence state and skill mode are part of the contract.

Install for normal use.

Claude Code

Drop into a skill folder

Personal: ~/.claude/skills/cognitive-biases-how-to-when-safety-increases-assess-ri-6161ad40/SKILL.md
Project: .claude/skills/cognitive-biases-how-to-when-safety-increases-assess-ri-6161ad40/SKILL.md

Claude Agent Skills docs

Hermes Agent

Install directly from this URL

hermes skills install https://brali-lifeos.github.io/skill-packs/cognitive-biases-how-to-when-safety-increases-assess-risks-ask-am-i/SKILL.md

Hermes skills docs

OpenClaw

Place in a discovered skill root

Workspace: <workspace>/skills/cognitive-biases-how-to-when-safety-increases-assess-ri-6161ad40/SKILL.md
Global: ~/.openclaw/skills/cognitive-biases-how-to-when-safety-increases-assess-ri-6161ad40/SKILL.md

OpenClaw skills docs

Brali verification

Coverage and trust state are checked together.

Canonical ID: brali:cognitive-biases-how-to-when-safety-increases-assess-risks-ask-am-i
Evidence state: practical
Skill mode: usable
Recommendation eligible: yes
SHA-256: 228a8d7dea68c08415fcdeca3dace16de2534df7ba110f67b68a541cb88022d4

Brali CI verified. This means identity, state, mode, provenance and file integrity matched the generated corpus. It is not third-party vendor endorsement.

Why every hack gets a skill

Brali keeps a one-to-one machine surface: one hack record, one stable skill identity. Trust state determines what the skill is allowed to do.

License

Original Brali knowledge is available for non-commercial reuse under CC BY-NC-SA 4.0. Keep attribution, canonical record link, evidence state and skill mode.