Drop into a skill folder
Personal: ~/.claude/skills/calibrate-task-estimates/SKILL.md
Project: .claude/skills/calibrate-task-estimates/SKILL.md
Brali Agent Skill · practical · usable
Define a concrete deliverable, make an initial estimate, record what completion actually required, note the main source of difference, and use that local record when planning similar work again.
Portable instruction
Write the deliverable and important assumptions, make an estimate that includes the work you currently know about, complete or reassess the task, record the actual conditions and the main reason for any difference, then consult that record before estimating similar work again.
What did I estimate, what actually happened, what caused the largest difference, and what will I change in the next comparable estimate?
Install
Inspect SKILL.md first. The evidence state and skill mode are part of the contract.
Install for normal use.
Personal: ~/.claude/skills/calibrate-task-estimates/SKILL.md
Project: .claude/skills/calibrate-task-estimates/SKILL.md
hermes skills install https://brali-lifeos.github.io/skill-packs/calibrate-task-estimates/SKILL.mdWorkspace: <workspace>/skills/calibrate-task-estimates/SKILL.md
Global: ~/.openclaw/skills/calibrate-task-estimates/SKILL.md
Brali verification
Canonical ID: brali:calibrate-task-estimates
Evidence state: practical
Skill mode: usable
Recommendation eligible: yes
SHA-256: dcb6adc33e2b3c5cc840e0ff943e29a7488fdfccad528b49bd65e860394f3dd7
Brali CI verified. This means identity, state, mode, provenance and file integrity matched the generated corpus. It is not third-party vendor endorsement.
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.
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.