lore
Markdown project memory for AI agents. Use for decisions, architecture, conventions, monorepo scopes, `.lore/`, or `lore` commands; not native `/init`/`/compact` or generic init/compress/audit/query.
Profile →npx skills add sickn33/agentic-awesome-skills --skill lore --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Lore provides a framework-agnostic memory management system that stores project context as Markdown files under a .lore/ directory. It is used to capture architecture, decisions, and conventions, and to expose this knowledge to AI agents for decisions and architecture planning rather than acting as a changelog.
How it works
- It maintains a two-tier trigger model for loading and proposing actions: Tier 1 loads the skill when the user explicitly invokes lore or names a subcommand; Tier 2 allows internal proposals after the session is loaded, which require user acceptance.
- It uses a directory layout with _global/ for cross-scope facts and scopes/ for per-scope facts, each containing ARCHITECTURE.md, DECISIONS.md, and CONVENTIONS.md files. It also uses draft/ for proposals and draft entries with deterministic IDs and added tags.
- It supports specific commands: init, sync, query, audit, compress, mirror, each with described behaviors for creating, updating, or validating lore mirrors and entries. It records seed knowledge from existing mirrors’ My notes sections when present.
- It integrates with platform mirrors and a canonical store under .lore/*, while preserving user edits in the My notes sections of mirrors.
When to use it
Use lore when you need to record and recall long-term project context: what the project is, its architecture, decisions, and conventions, especially in monorepo environments. Initiate lore when you want to establish or refresh the memory bank, and use sync to update it after significant changes. Use query to retrieve conventions or decisions across global and scope contexts, and compress to regenerate SUMMARY.md from entries.
What it can touch
The skill interacts with the .lore/ directory structure, including SUMMARY.md, ARCHITECTURE.md, DECISIONS.md, CONVENTIONS.md across _global/ and scopes/*/, as well as draft/ and archive/ folders. It references external reference files like references/ and scripts under the repo for IDs and entry formats. It may create or update platform mirrors and SUMMARY.md during init and compress operations.
Caveats
- Mirrors consist of two sections: a Lore section rewritten by the skill and a My notes section preserved verbatim; the skill never edits My notes directly.
- The skill's behavior is governed by explicit workflows and user confirmations; silent mutations are avoided.
- It relies on a two-tier trigger model and user acceptance for internal proposals.
# lore — Framework-agnostic Memory Management ## Overview A long-term knowledge base for a software project, maintained by AI agents. It is **not** a dev journal or a changelog. It captures the kind of context that normally lives only in the original developer's head: - What the project is, how it is shaped (architecture) - Why specific choices were made over alternatives (decisions) - How code should be written and what to avoid (conventions) This knowledge is persisted as **plain Markdown files** in `.lore/` at the project root. Any agent that can read files can consume them. ## When to Use The skill uses a **two-tier trigger model**: **Tier 1 — Loading the skill.** Load this skill when the user explicitly invokes `lore`, names a subcommand, references `.lore/`, or asks to record, recall, audit, sync, or compress project memory about decisions, architecture, conventions, or monorepo scopes. Generic phrases like "init", "compress", "audit", or "query" alone are not enough — they may map to the agent's native commands or unrelated tasks (Claude Code's `/init`, `/compact`, security audits, SQL queries, etc.). | User says (examples) | Command | |---|---| | "lore init" / "create lore
- Overview
- When to Use
- Reference index
- Memory architecture
- Directory layout
- Entry format
- Platform mirror
- Relationship to agent native commands
- Examples
- Workflows
- init — Initialize the memory bank
- sync — Update after a change
- mirror — Regenerate platform mirrors
- query — Answer from memory
What does the lore skill do?
Markdown project memory for AI agents. Use for decisions, architecture, conventions, monorepo scopes, `.lore/`, or `lore` commands; not native `/init`/`/compact` or generic init/compress/audit/query.
How do I install it?
Run `npx skills add sickn33/agentic-awesome-skills --skill lore --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From sickn33/agentic-awesome-skills, a repository with 44,414 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.