Agent skill · AI & Agents

myagents-memory-molt

仅当系统或用户明确指定完整名称 `myagents-memory-molt` 时使用； 不要根据任务语义或相似表述自行触发。

hAcKlycgithub.com/hAcKlycGitHub ↗
claude-codeships scriptsAGPL-3.0
Install
npx skills add hAcKlyc/MyAgents --skill myagents-memory-molt --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 5
SKILL.md size: 2 KB
Bundled scripts: yes
Declared author: MyAgents
Path: bundled-skills/myagents-memory-molt/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 795
Language: TypeScript

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# MyAgents Memory Molt Molt 是长期记忆机制的第三层：它不是把文件整理得更整齐，而是让工作区的长期记忆发生真实进化。 如果结束后没有任何旧判断被反对、没有任何新原则被接受、没有任何元层文件被改动，这次就是无效反思。 ## 三层位置 | 层 | 节奏 | 本质 | 允许改什么 | |---|---:|---|---| | `UPDATE_MEMORY.md` | 24h | session 级捕获 | 日志 / 增量记忆 | | `myagents-memory-gardener` | 72h | 修剪和下放 | USER / MEMORY / topic / gardener flags | | `myagents-memory-molt` | 14d | 信念审计和自我改写 | SOUL / USER / MEMORY / molt 文档 | ## 硬规则 1. **不能空手而归。** 至少产出一个新接受的信念、一个新拒绝的旧信念、一个升级到 SOUL/USER/MEMORY 的模式。 2. **找不舒服的信号。** 优先处理矛盾、反复纠正、长期拖延、和当前叙事不一致的证据。 3. **外部事实核验是硬要求。** 对会随时间衰减的事实判断，必须搜索验证；无法验证时显式标 `unverified`。 4. **用第一人称写内省。** 不写面向用户的汇报体。 5. **自审，不等用户审批。** 在权限允许范围内直接落地，事后通过 git history 留痕。 6. **识别迎合。** 标出哪些判断只是用户透传、哪些是自己独立验证后接受。 7. **承认不知道。** 证据不足时保留待验证状态，不硬下判断。 ## 工作流程 1. 在目标工作区运行 `python3 <skill>/scripts/prepare_molt.py --repo <workspace>`，采集范围清单。 2. 运行 `python3 <skill>/scripts/prepare_molt.py --repo <workspace> --init-progress`，生成 `memory/molts/YYYY-MM-DD-molt-NNN.progress.md`。 3. 创建并撰写 `memory/molts/YYYY-MM-DD-molt-NNN.md`。结构参考 [references/landing_template.md](references/landing_template.md)。 4. 按顺序完成五个认知动作：模式挖掘、信念审计、外部核验、身份一致性、综合落地。 5. 同步更新 progress 文件。所有 checkbox 必须变成 `[x]` 或 `[defer] + 理由`。 6. 直接落地修改 `SOUL` / `USER` / `

What's inside
Steps it walks through
  1. 三层位置
  2. 硬规则
  3. 工作流程
  4. 允许修改范围
  5. Commit
Ships with 4 files
  • references/cognitive_moves.md
  • references/external_verification.md
  • references/landing_template.md
  • scripts/prepare_molt.py
More from MyAgents
All skills →
supportMyAgents 本地问题诊断、恢复与反馈升级流程。用户描述报错、崩溃、无响应、配置后仍不可用、状态或结果不符合预期、…Workflow & Productivityhatch-petCreate, repair, validate, visually QA, and package MyAgents/Codex-compatible animated pets and pet…Testing & QAagent-browserBrowser automation CLI for AI agents. Use when the user needs to interact with websites, including…Testing & QAdocxComprehensive document creation, editing, and analysis with support for tracked changes, comments…Content & Marketingdownload-anythingFind and download virtually any digital resource from the internet — ebooks, academic papers…Media & Videomyagents-memory-gardener仅当系统或用户明确指定完整名称 `myagents-memory-gardener` 时使用； 不要根据任务语义或相似表述自行触发。AI & Agents
About this skill
What does the myagents-memory-molt skill do?

仅当系统或用户明确指定完整名称 `myagents-memory-molt` 时使用； 不要根据任务语义或相似表述自行触发。

How do I install it?

Run `npx skills add hAcKlyc/MyAgents --skill myagents-memory-molt --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 hAcKlyc/MyAgents, a repository with 795 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.

Keep going
All skills →
The full catalog, by category and by tool.
Open Source Radar →
The repositories these skills come from, watched daily.
The people behind them →
Makers and builders across the ecosystem.