원클릭으로 Manus에서 모든 스킬 실행

agents-memory

스타0

포크0

업데이트2026년 7월 16일 13:19

Persistent project memory bootstrap and maintenance. Use in any repository with (or needing) an `AGENTS.md` + `./agents/` system. **Triggers:**\n* **Initialization:** Starting in a new repo, running `/init`, or requests to "set up agents memory."\n* **Development:** Planning features, proposing architecture (→ decisions), writing code (→ conventions), or navigating the codebase (→ architecture).\n* **Debugging:** Fixing complex bugs, investigating issues, or encountering recurring mistakes (→ known-errors).\n* **Memory Management:** Fetching or proposing workflows, glossary terms, conventions, decisions, or known errors.

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

Manus에서 실행

출처

MiquelGomezCorral

MiquelGomezCorral/my-opencode-config

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

Agents Memory

Persistent memory system for coding projects. It creates one router file (AGENTS.md) plus topical memory files under .agents/ so agents can load only the project context they need.

Use When

The user runs /init or asks to initialize project memory.
Starting work in a repo that lacks AGENTS.md or .agents/.
The user asks to set up, inspect, or update agent memory files.
A repeated project convention, decision, workflow, glossary term, or known error should be proposed for memory.

Files

AGENTS.md
.agents/
  architecture.md
  conventions.md
  decisions.md
  glossary.md
  workflow.md
  known-errors.md

Bootstrap Workflow

Inspect the current project before writing memory files: root files, package/dependency files, existing docs, and existing AGENTS.md or CLAUDE.md.
If project memory already exists, update only missing files or clearly stale references after confirming the intent.
Create AGENTS.md from templates/AGENTS.md and .agents/* from the matching templates.
Replace placeholders with facts discovered in the repo. Leave sections as None yet. when there is no evidence.
Do not invent conventions, decisions, commands, or architecture.
Summarize created or updated memory files and any sections that still need user input.

Operating Rules

Read AGENTS.md first in projects that have it.
Lazy-load .agents/* by need; do not read all memory files by default.
Treat closed decisions in .agents/decisions.md as authoritative unless the user explicitly reopens them.
If code contradicts memory, trust the current code and flag the memory entry as stale.
Memory updates during normal work are propose-only unless the user explicitly asks to write them.

Trigger Map

Situation	Read or update
Navigating repo or changing module boundaries	`.agents/architecture.md`
Writing code	`.agents/conventions.md`
Refactor, dependency swap, architecture choice	`.agents/decisions.md`
Project-specific acronym, domain term, entity	`.agents/glossary.md`
Build, test, release, commit, PR	`.agents/workflow.md`
Debugging a repeated failure	`.agents/known-errors.md`

Templates

Templates live in templates/ next to this skill. Use them as structure, not as final content.

이 저장소의 다른 Skills

같은 저장소

caveman-help

MiquelGomezCorral/my-opencode-config

Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".

2026-07-210

find-skills

MiquelGomezCorral/my-opencode-config

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

2026-07-210

review-swarm-upstream

MiquelGomezCorral/my-opencode-config

Review upstream changes to the local my-opencode reviewer swarm before selectively applying them. Use whenever the user asks to pull, sync, inspect, compare, or adopt reviewer or swarm changes from ~/Documents/yo/my-opencode. Never use it to install the upstream configuration wholesale.

2026-07-210

ponytail-help

MiquelGomezCorral/my-opencode-config

Quick-reference card for all ponytail modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /ponytail-help, "ponytail help", "what ponytail commands", "how do I use ponytail".

2026-07-210

ponytail

MiquelGomezCorral/my-opencode-config

Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", and whenever they complain about over-engineering, bloat, boilerplate, or unnecessary dependencies.

2026-07-210

agent-prompt-writing

MiquelGomezCorral/my-opencode-config

Use whenever the task involves writing, drafting, revising, or reviewing a system prompt for an AI agent — autonomous or semi-autonomous LLM systems that use tools in a loop, including operator agents, research/sub-agents, tool-using assistants, MCP servers, multi-agent orchestrators, and coding agents. Trigger even when the user says "instructions", "system message", "agent persona", or "rules for the model", not just the word "prompt". Do NOT use for one-shot prompts (classification, single generation, single Q&A) — those need lighter prompt techniques, not the full agent skeleton.

2026-07-210

name

agents-memory

description

Agents Memory

Persistent memory system for coding projects. It creates one router file (AGENTS.md) plus topical memory files under .agents/ so agents can load only the project context they need.

Use When

The user runs /init or asks to initialize project memory.
Starting work in a repo that lacks AGENTS.md or .agents/.
The user asks to set up, inspect, or update agent memory files.
A repeated project convention, decision, workflow, glossary term, or known error should be proposed for memory.

Files

AGENTS.md
.agents/
  architecture.md
  conventions.md
  decisions.md
  glossary.md
  workflow.md
  known-errors.md

Bootstrap Workflow

Inspect the current project before writing memory files: root files, package/dependency files, existing docs, and existing AGENTS.md or CLAUDE.md.
If project memory already exists, update only missing files or clearly stale references after confirming the intent.
Create AGENTS.md from templates/AGENTS.md and .agents/* from the matching templates.
Replace placeholders with facts discovered in the repo. Leave sections as None yet. when there is no evidence.
Do not invent conventions, decisions, commands, or architecture.
Summarize created or updated memory files and any sections that still need user input.

Operating Rules

Read AGENTS.md first in projects that have it.
Lazy-load .agents/* by need; do not read all memory files by default.
Treat closed decisions in .agents/decisions.md as authoritative unless the user explicitly reopens them.
If code contradicts memory, trust the current code and flag the memory entry as stale.
Memory updates during normal work are propose-only unless the user explicitly asks to write them.

Trigger Map

Situation	Read or update
Navigating repo or changing module boundaries	`.agents/architecture.md`
Writing code	`.agents/conventions.md`
Refactor, dependency swap, architecture choice	`.agents/decisions.md`
Project-specific acronym, domain term, entity	`.agents/glossary.md`
Build, test, release, commit, PR	`.agents/workflow.md`
Debugging a repeated failure	`.agents/known-errors.md`

Templates

Templates live in templates/ next to this skill. Use them as structure, not as final content.