Drop into a skill folder
Personal: ~/.claude/skills/ai-premortem-risk-planner/SKILL.md
Project: .claude/skills/ai-premortem-risk-planner/SKILL.md
Brali Agent Skill · practical · usable
AI-Assisted Premortem
Use an AI model as a brainstorming partner for possible failure modes, then verify important risks against the real plan before choosing mitigations.
Portable instruction
What the agent should do
Describe the plan without sensitive information, ask an AI for plausible ways it could fail, group the suggestions, verify the important ones yourself, and choose mitigations only for risks that survive the check.
Check-in
Which risks were genuinely relevant after verification, and which model suggestions were generic, impossible, or based on missing context?
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.
Install directly from this URL
hermes skills install https://brali-lifeos.github.io/skill-packs/ai-premortem-risk-planner/SKILL.mdPlace in a discovered skill root
Workspace: <workspace>/skills/ai-premortem-risk-planner/SKILL.md
Global: ~/.openclaw/skills/ai-premortem-risk-planner/SKILL.md
Brali verification
Coverage and trust state are checked together.
Canonical ID: brali:ai-premortem-risk-planner
Evidence state: practical
Skill mode: usable
Recommendation eligible: yes
SHA-256: cfc7e33e901c24b092c7f0151b17bc0facca25e2302523fc29b6eec1a2a02c02
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.