Drop into a skill folder
Personal: ~/.claude/skills/apply-80-20-principle/SKILL.md
Project: .claude/skills/apply-80-20-principle/SKILL.md
Brali Agent Skill · practical · usable
Use 80/20 as a Prioritization Hypothesis
Rank the few inputs most likely to matter, test that ranking against observed results, and revise it instead of treating 80/20 as a law or exact forecast.
Portable instruction
What the agent should do
Define one outcome, list the inputs that could influence it, rank a small number by expected impact and cost, choose one to check, and compare the observed result with your initial ranking. Revise the ranking when the data disagrees.
Check-in
Which input actually changed the outcome, what did it cost, and what should move up, down, or out of the priority list?
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/apply-80-20-principle/SKILL.mdPlace in a discovered skill root
Workspace: <workspace>/skills/apply-80-20-principle/SKILL.md
Global: ~/.openclaw/skills/apply-80-20-principle/SKILL.md
Brali verification
Coverage and trust state are checked together.
Canonical ID: brali:apply-80-20-principle
Evidence state: practical
Skill mode: usable
Recommendation eligible: yes
SHA-256: fe1da3bced51148cf4ae84c297e13460b178799a07d059acaae0a308505d50b2
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.