Brali Agent Skill · practical · usable

Decision Calibration Journal

Before an uncertain decision, record your expectation, confidence, and key assumption. Later compare them with the outcome and update how you make similar choices.

AgentSkills.iopracticalusableDecision MakingMetacognition
Open SKILL.mdCanonical recordVerification JSONAll Agent Skills

Portable instruction

What the agent should do

Before a meaningful uncertain choice, write the expected outcome, how confident you are in plain language, and the assumption that matters most. Revisit the note after the outcome is clear.

Check-in

Which assumption held, which one failed, and what would you change in a similar decision next time?

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/decision-calibration-journal/SKILL.md
Project: .claude/skills/decision-calibration-journal/SKILL.md

Claude Agent Skills docs

Hermes Agent

Install directly from this URL

hermes skills install https://brali-lifeos.github.io/skill-packs/decision-calibration-journal/SKILL.md

Hermes skills docs

OpenClaw

Place in a discovered skill root

Workspace: <workspace>/skills/decision-calibration-journal/SKILL.md
Global: ~/.openclaw/skills/decision-calibration-journal/SKILL.md

OpenClaw skills docs

Brali verification

Coverage and trust state are checked together.

Canonical ID: brali:decision-calibration-journal
Evidence state: practical
Skill mode: usable
Recommendation eligible: yes
SHA-256: 2d37cf23c65645a93ce7047ac03ba11bd7c5300a61d71fb6a83ad446074cd4f3

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.