Drop into a skill folder
Personal: ~/.claude/skills/challenge-assumed-intent/SKILL.md
Project: .claude/skills/challenge-assumed-intent/SKILL.md
Brali Agent Skill · practical · usable
Separate Observed Facts From Assumed Intent
When an ordinary ambiguous event feels intentional, separate the observable facts from your interpretation, list plausible alternatives, check relevant information, and use a neutral clarification before treating intent as established.
Portable instruction
What the agent should do
Write the observable event without motive language, mark the inferred intent as an interpretation, list other explanations that fit the known facts, check the information that is reasonably available, and ask a neutral clarifying question when another person can resolve the ambiguity.
Check-in
What did I directly observe, what intent did I infer, what else could explain it, and what information would actually distinguish those explanations?
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/challenge-assumed-intent/SKILL.mdPlace in a discovered skill root
Workspace: <workspace>/skills/challenge-assumed-intent/SKILL.md
Global: ~/.openclaw/skills/challenge-assumed-intent/SKILL.md
Brali verification
Coverage and trust state are checked together.
Canonical ID: brali:challenge-assumed-intent
Evidence state: practical
Skill mode: usable
Recommendation eligible: yes
SHA-256: 66323124ccb222862c2ca25b0112efa4e6993b20604783933b2456783dfe6303
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.