Skills for Real Engineers. Straight from my .agents directory.
memory-management
Agent skill fromaaron-he-zhu/aaron-marketing-skills
Use when the user asks to "remember project context", review saved findings, initialize runtime memory, archive stale work, reconcile notes, or erase a subject; manages authorized HOT/WARM/COLD working memory across all disciplines while preserving registry event ownership and privacy controls. Not for changing canonical registry facts - route those through the owning registry. 项目记忆/跨会话
How to install memory-management
npx skills add aaron-he-zhu/aaron-marketing-skills# or add only this skill to Claude Code: copy the folder
protocol/memory-management/
# into
~/.claude/skills/memory-management/ (all projects)
.claude/skills/memory-management/ (one project)
1# Memory Management23Manages the project's authorized working memory. HOT/WARM/COLD notes improve retrieval; they are not a second truth system. The seven registry event streams remain canonical, their JSON projections are rebuildable views, and only registry owners may accept or mutate canonical facts.45## Quick Start67```text8Initialize private runtime memory from the repository templates.9Show current priorities and their source records.10Consolidate duplicate notes without changing registry truth.11Archive WARM files not updated in 90 days.12Purge subject-7f42 from project memory under this confirmed erasure request.13```1415## Skill Contract1617**Reads:** authorized runtime memory, registry projections/events, approved decisions, and [state-model.md](../../references/state-model.md). **Writes:** HOT/WARM/COLD notes, archives, indexes, and authorized tombstone/erase events; it never accepts registry proposals or writes canonical facts on behalf of an owner. **Done when:** the requested operation is complete, writes have explicit authorization, affected paths/events are reported, HOT is within 80 lines and 25 KB, and registry verification still passes.1819Operational `memory/**` is Git-ignored by default. Initialize from `memory/templates/`; never commit runtime data, event streams, projections, audits, exports, or subject records unless the user deliberately creates a separate protected data-governance process.2021### Authority Order2223When sources conflict, use this order:24…
Excerpt shown under the repository's Apache-2.0 license.
More skills in aaron-marketing-skills
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
