Brali Agent Skill · reviewed · usable

Attempt First, Use AI for Feedback, Retest Without It

For learning tasks, make a genuine attempt before asking AI to explain, critique, or extend your work, then reproduce the target skill without assistance. Recent evidence on generative AI in education is mixed enough that the workflow should preserve learner activity rather than assume the chatbot itself improves learning.

AgentSkills.ioreviewedusableSkill LearningMetacognitionMemory
Open SKILL.mdCanonical recordVerification JSONAll Agent Skills

Portable instruction

What the agent should do

Name the skill you are actually trying to acquire. Attempt a problem, explanation, translation, derivation, or answer unaided. Ask AI to identify gaps, give a contrasting example, or explain one sticking point. Check the feedback against trusted material when accuracy matters, then perform a fresh attempt without AI.

Check-in

Can I now perform or explain the target skill without leaning on the AI output?

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/ai-learning-attempt-feedback-retest/SKILL.md
Project: .claude/skills/ai-learning-attempt-feedback-retest/SKILL.md

Claude Agent Skills docs

Hermes Agent

Install directly from this URL

hermes skills install https://brali-lifeos.github.io/skill-packs/ai-learning-attempt-feedback-retest/SKILL.md

Hermes skills docs

OpenClaw

Place in a discovered skill root

Workspace: <workspace>/skills/ai-learning-attempt-feedback-retest/SKILL.md
Global: ~/.openclaw/skills/ai-learning-attempt-feedback-retest/SKILL.md

OpenClaw skills docs

Brali verification

Coverage and trust state are checked together.

Canonical ID: brali:ai-learning-attempt-feedback-retest
Evidence state: reviewed
Skill mode: usable
Recommendation eligible: yes
SHA-256: ed32b9951337029e19c06a64be5d12f5c276f2141e489e28887c5a2ae0bde702

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.