liza-studio

Skillmem — Development skill for Claude Code

Development community

Self-improving skill memory for coding agents: learn, recall, reinforce, decay — with provenance on every memory and trust only you grant.

How to install Skillmem

This entry records only its repository, not the path inside it, so there is no exact command to give. Open liza-studio/skillmem and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Skillmem does

Self-improving skill memory for coding agents: learn, recall, reinforce, decay — with provenance on every memory and trust only you grant. Local SQLite, no API key, no cloud.

Alternatives in Development

Haft — Engineering decisions engine that know when they're stale 1.4k ★
Academic Pptx Skill — A Claude Skill for creating academic presentations (conference talks, seminar slides, thesis defenses, grant b 811 ★
AgentHandover — What if OpenClaw, Claude Code, Codex etc. knew how to do your work without you saying it 600 ★

README

skillmem

[![CI](https://github.com/liza-studio/skillmem/actions/workflows/ci.yml/badge.svg)](https://github.com/liza-studio/skillmem/actions/workflows/ci.yml)

**Self-improving skills for Claude Code and Codex — your agents learn, recall, reinforce, and forget.**

![skillmem demo: a Russian query finds an English skill, unused skills decay](docs/demo.gif)

Strength has to be earned — saying a skill helped is not evidence, a passing test is:

![skillmem: self-report does not raise strength, a passing test does, and rare rules can be pinned](docs/demo-evidence.svg)

Generated from a real run: `scripts/demo.sh --record | python3 scripts/cast_to_svg.py > docs/demo-evidence.svg`.

skillmem gives Claude Code and the Codex CLI a local, persistent skill & memory layer. After every non-trivial task the agent can record *how it was done* as a skill; before the next task it recalls the relevant ones; skills that keep proving useful get stronger, and skills nobody uses fade away — the way human memory works.

$0 per write and per read — no LLM calls, no cloud, no API keys. Plain SQLite on your disk.
Bilingual hybrid search, fully local — FTS5 BM25 + Snowball stemming (EN/RU) matches inflected forms within a language; the multilingual ONNX embedder is what lets a Russian query find an English skill, so install the semantic extra if you work across both. All on CPU, offline.
Ebbinghaus strength model, earned not claimed — strength rises only on evidence from outside the agent's own judgement, falls after a failure, and fades on a schedule when unused; dead skills are swept to a backed-up archive (never deleted). Rules that are rare by nature can be pinned out of decay.
Provenance, and trust the owner grants — every memory records where it came from (owner / agent / imported / derived), and only the owner approves one as a rule (skillmem trust ). Anything unapproved — an impo