agents-skills-feedback-loop
SolidAdds per-skill learnings loops for dated patterns, mistakes, and domain facts. Use when wiring skill memory, consolidation, or drift audits.
Install
Quality Score: 86/100
Skill Content
Details
- Author
- vasilyu1983
- Repository
- vasilyu1983/AI-Agents-public
- Created
- 10 months ago
- Last Updated
- 1 weeks ago
- Language
- Python
- License
- MIT
Integrates with
Similar Skills
Semantically similar based on skill content — not just same category
learning-loop
(Industry standard: Loop Agent / Single Agent) Primary Use Case: Self-contained research, content generation, and exploration where no inner delegation is required. Self-directed research and knowledge capture loop. Use when: starting a session (Orientation), performing research (Synthesis), or closing a session (Seal, Persist, Retrospective). Ensures knowledge survives across isolated agent sessions.
learning-loop
Capture durable lessons, errors, and verified fixes in a project-local learning ledger, consult it before re-deriving known failures, and track recurrence toward promotion, using the bundled deterministic learning_ledger.py CLI. Use when the user says "capture this lesson", "log this error to the ledger", "check the learning ledger", "record a recurrence", "any known fix for this?", or "/agent-collab:learning-loop." Also offer this proactively when the same failure recurs across sessions, or when a hard-won diagnosis is about to be lost because it lives only in one session's context.
learn
Use when the user says 'learn!', 'capture this', 'update the skill', 'remember this for next time', or when a session surfaces a non-obvious pitfall, a doc-vs-reality gap, or a missing step in a skill/rule that was in use. Routes session learnings back into this repo's persistent guidance — skills/*/SKILL.md (+ references/), rules/coding-*.md, CLAUDE.md — rather than auto-memory. Automatically identifies which skills and rules were loaded during the session, checks for existing coverage (especially fabric-gotchas), verifies the learning against official docs before encoding it, proposes the edit at the right heading as a diff for approval, then hands off to /commit. Never edits silently, never writes domain knowledge to memory.