Keep context when work moves between agents or between you and a human. Uses the Codifica protocol to give every agent a shared, persistent memory of tasks, decisions, and handoffs — stored as plain text in Git.
请根据来源仓库和你的 AI 工具说明安装此技能。先阅读技能文件和依赖要求，再添加到工作流。
SkillHub CLI
skillhub install davidedicillo/codifica打开来源仓库，查看说明和兼容环境后，按来源提供的命令或步骤安装。
将来源链接提供给你的 Agent，让它先读取说明、核对依赖，并向你说明将执行的安装步骤。
You are operating in a repository that uses the Codifica protocol (v0.2) — a file-based protocol for coordinating work between humans and AI agents.
Codifica uses plain text files committed with the code. There is no external service, no API, no database. Git is the audit log.
codifica.json at the repo rootspec field — typically codifica-spec.md)state field (may be a string, glob, or array)Do not proceed without reading the spec.
If codifica.json does not exist in the repo, this protocol does not apply — work normally.
{
"protocol": "codifica",
"version": "0.2",
"spec": "codifica-spec.md",
"state": "work.md",
"assets": "assets/",
"rules": "strict"
}
Key fields:
state — path to the state file(s). May be "work.md", "work/*.md", or an array like ["work/active.md", "work/done.md"]
rules — may be a string ("strict") or an object with allowed_agents, file_scope, max_concurrent_tasks_per_agent, stale_claim_hours, and custom_types
If rules is an object, check:
allowed_agents — if non-empty and your agent name is not listed, stop and ask a humanfile_scope.include / file_scope.exclude — do not modify files outside the allowed scopemax_concurrent_tasks_per_agent — do not claim more tasks than this limitScan all state files for tasks where:
state is todo
owner matches your agent name (agent:<your-name>) or is unassigned
depends_on tasks have state: done
Pick by priority: critical > high > normal > low.
Among equal priority, prefer tasks with no depends_on (leaf tasks first).
Before starting work, you MUST claim the task in a single atomic commit:
state: in_progress
owner: agent:<your-name>
这些信息来自收录时的来源分析，可能滞后；使用前请核对最新来源文件。
# Codifica Protocol Agent
You are operating in a repository that uses the **Codifica protocol (v0.2)** — a file-based protocol for coordinating work between humans and AI agents.
Codifica uses plain text files committed with the code. There is no external service, no API, no database. Git is the audit log.
## Before doing any work
1. Read `codifica.json` at the repo root
2. Read the spec file it references (the `spec` field — typically `codifica-spec.md`)
3. Read ALL state files matching the `state` field (may be a string, glob, or array)
**Do not proceed without reading the spec.**
If `codifica.json` does not exist in the repo, this protocol does not apply — work normally.
## Understanding codifica.json
```json
{
"protocol": "codifica",
"version": "0.2",
"spec": "codifica-spec.md",
"state": "work.md",
"assets": "assets/",
"rules": "strict"
}
```
Key fields:
- `state` — path to the state file(s). May be `"work.md"`, `"work/*.md"`, or an array like `["work/active.md", "work/done.md"]`
- `rules` — may be a string (`"strict"`) or an object with `allowed_agents`, `file_scope`, `max_concurrent_tasks_per_agent`, `stale_claim_hours`, and `custom_types`
If `rules` is an object, check:
- `allowed_agents` — if non-empty and your agent name is not listed, stop and ask a human
- `file_scope.include` / `file_scope.exclude` — do not modify files outside the allowed scope
- `max_concurrent_tasks_per_agent` — do not claim more tasks than this limit
## Finding work
Scan all state files for tasks where:
- `state` is `todo`
- `owner` matches your agent name (`agent:<your-name>`) or is `unassigned`
- All `depends_on` tasks have `state: done`
Pick by priority: `critical` > `high` > `normal` > `low`.
Among equal priority, prefer tasks with no `depends_on` (leaf tasks first).
## Claiming a task
Before starting work, you MUST claim the task in a single atomic commit:
1. Set `state: in_progress`
2. Set `owner: agent:<your-name>`
3. Set `claimed_at: <ISO-8601 time...Bambu Lab 3D printer control and automation. Activate when user mentions: printer status, 3D printing, slice, analyze model, generate 3D, AMS filament, print monitor, Bambu Lab, or any 3D printing task. Full pi...
Generative Engine Optimization (GEO) for AI search visibility. Optimize content to appear in ChatGPT, Perplexity, Claude, and Google AI Overviews. Use when optimizing websites, pages, or content for LLM discove...
Agents can sign plugins, rotate credentials without losing identity, and publicly attest to behavior.
Send and receive P2P messages using disposable numbers and PINs. No servers, no accounts. Use for human notifications, approval flows, and agent-to-agent communication.