agents-skills-feedback-loop

Solid

Adds per-skill learnings loops for dated patterns, mistakes, and domain facts. Use when wiring skill memory, consolidation, or drift audits.

AI & Automation 87 stars 19 forks Updated 1 weeks ago MIT

Install

View on GitHub

Quality Score: 86/100

Stars 20%
65
Recency 20%
90
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Agent Skills — Feedback Loop Use this skill to wire a **learnings loop** into another skill so it gets better with use, without rewriting `SKILL.md` automatically. The loop has four moving parts: 1. **`learnings.md`** — raw, append-only, committed. Shared working memory across machines; created on first append via `append_learning.py`, not seeded empty. 2. **`learnings.consolidated.md`** — pruned, dated, committed. Portfolio-grade institutional memory; seeded at wiring time. 3. **`learnings.local.md`** — machine-specific notes, gitignored. Use for one-operator-on-one-machine context that should not propagate. 4. **`scripts/append_learning.py` + `scripts/consolidate.py`** — keep raw entries well-shaped and promote durable ones to consolidated. The name is borrowed from the 2026 "learnings loop" pattern (MindStudio) and Anthropic's own skill-authoring guidance to ask Claude to self-reflect on what went wrong and fold it back into reusable context. **The mechanism deliberately does not match MindStudio's**: MindStudio's loop has the model rewrite the skill's persistent instructions directly from user corrections — that is the exact auto-rewrite this design forbids (see Anti-Patterns). This skill keeps the same "accumulate corrections across sessions" shape but routes it through append-only raw entries, human-reviewed consolidation, and an eval-gated promotion step before anything touches skill logic — mapped onto this repo's existing 4-type memory schema (see `agents-memor...

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

AI & Automation Listed

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.

6 Updated today
richfrem
AI & Automation Listed

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.

0 Updated 2 days ago
sumitake
AI & Automation Listed

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.

2 Updated 1 weeks ago
wardawgmalvicious