📝 add workpad with reshape goal, ecosystem research, commit-conventions spec
This commit is contained in:
@@ -0,0 +1,5 @@
|
|||||||
|
The task is to use this repo to prepare to push to another.
|
||||||
|
|
||||||
|
This folder contains one single plugin, which will become g4b_ai basicly as skills, because these are my core skills i use personally most, or at least, replace some that i did, so some are not yet fully adapted. but it is one plugin basicly. however i want to have themed plugins, so this should become a marketplace, which the reliquary is basicly.
|
||||||
|
|
||||||
|
the job is to reshape this into a proper base marketplace, and push it afterwards to git@git.g4b.org:dirigence/reliquary.git instead. The .claude folder can stay, but the .claude-plugin e.g. becomes a claude plugin. core claude and readme have to be replaced, they wander also into the plugin, just as the skills folder. the reliquary should also make it possible to be used as claude marketplace and grabbing the tools independently. but it will not be only claude based, we might integrate other marketplace formats, or other skills, parallel. I do assume, this won't be an issue.
|
||||||
@@ -0,0 +1,125 @@
|
|||||||
|
# Skills, Plugins, and Marketplaces Across Coding Agents (May 2026)
|
||||||
|
|
||||||
|
A practical survey of how coding agents *other than* Claude Code package
|
||||||
|
reusable behavior, and how portable those formats actually are.
|
||||||
|
|
||||||
|
> Reference: Claude Code's "Agent Skills" are folders with a `SKILL.md` +
|
||||||
|
> YAML frontmatter (`name`, `description`), auto-loaded from
|
||||||
|
> `~/.claude/skills/` or `.claude/skills/`. Plugins use
|
||||||
|
> `.claude-plugin/plugin.json` and are installed from a marketplace
|
||||||
|
> (`.claude-plugin/marketplace.json`) via `/plugin marketplace add` and
|
||||||
|
> `/plugin install`. Anthropic published this as an open Agent Skills
|
||||||
|
> spec.
|
||||||
|
|
||||||
|
The big picture in 2026: the spec has *largely won*. Most agents now
|
||||||
|
either load Anthropic-style `SKILL.md` natively or via a thin shim, and
|
||||||
|
**`AGENTS.md` + MCP** are the two cross-agent standards everyone agrees
|
||||||
|
on.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 1. Gemini CLI (Google)
|
||||||
|
|
||||||
|
- **Equivalent:** "Extensions" (the umbrella) and "Agent Skills" (introduced March 2026).
|
||||||
|
- **On-disk format:** Extensions live in `~/.gemini/extensions/<name>/` with a `gemini-extension.json` manifest. They can bundle MCP servers, `GEMINI.md` context, custom slash commands as `.toml`, hooks, sub-agents, themes, and skills. Skills go in `<extension>/skills/<name>/SKILL.md`, or directly in `~/.gemini/skills/` / `.gemini/skills/` for ad-hoc use ([Gemini CLI extensions](https://geminicli.com/docs/extensions/), [reference](https://geminicli.com/docs/extensions/reference/)).
|
||||||
|
- **Install / distribution:** `gemini extensions install <github-url-or-path>` clones into the extensions dir; `gemini extensions update` re-pulls. There is an official browseable catalog at [geminicli.com/extensions](https://geminicli.com/extensions/) and a `gemini-cli-extensions` GitHub org ([github.com/gemini-cli-extensions](https://github.com/gemini-cli-extensions)).
|
||||||
|
- **Skill-like unit can contain:** prompt + optional supporting files; in extensions, also tools (via MCP), hooks, sub-agents.
|
||||||
|
- **Spec compatibility:** The skills format is **deliberately Anthropic-compatible** — same `SKILL.md` + YAML frontmatter ([Google Cloud Community: "Agent Skills"](https://medium.com/google-cloud/your-gemini-cli-extensions-just-got-smarter-introducing-agent-skills-a8fbfa077e7f)). A community shim, [`gemini-cli-skillz`](https://github.com/intellectronica/gemini-cli-skillz), already exposed Anthropic-style skills via MCP before native support landed.
|
||||||
|
|
||||||
|
## 2. OpenCode (sst/opencode)
|
||||||
|
|
||||||
|
- **Equivalent:** "Agent Skills" (native) + "Plugins" (TypeScript hooks).
|
||||||
|
- **On-disk format:** `SKILL.md` files with YAML frontmatter (`name`, `description`), under repo `.opencode/skills/` or `~/.config/opencode/skills/` ([Agent Skills | OpenCode](https://opencode.ai/docs/skills/)). Plugins are TS modules registered in config and exposing lifecycle hooks ([Plugins | OpenCode](https://opencode.ai/docs/plugins/)).
|
||||||
|
- **Install / distribution:** Mostly **git clone / npm** today. There is no official first-party marketplace UI, but several third-party catalogs exist: [awesome-opencode](https://github.com/awesome-opencode/awesome-opencode), [n-skills](https://github.com/numman-ali/n-skills) (curated, multi-agent), and [BuySkills](https://buyskills.ai/plugins/opencode/) (paid + free).
|
||||||
|
- **Skill-like unit:** prompt + supporting files; plugins add tools/hooks. MCP is a first-class tool surface.
|
||||||
|
- **Spec compatibility:** **Native Anthropic Agent Skills** — same `SKILL.md` shape, intentionally cross-agent. Drop-in compatible with Claude Code skill folders in practice.
|
||||||
|
|
||||||
|
## 3. Codex CLI (OpenAI)
|
||||||
|
|
||||||
|
- **Equivalent:** **`AGENTS.md`** for always-on instructions, **Agent Skills** for on-demand workflows, and **Plugins** as a packaging layer.
|
||||||
|
- **On-disk format:** `AGENTS.md` is plain markdown, layered from repo root downward, concatenated nearest-last so deeper files override ([Codex AGENTS.md guide](https://developers.openai.com/codex/guides/agents-md)). Skills are `SKILL.md` folders, mirroring Anthropic's spec ([Agent Skills – Codex](https://developers.openai.com/codex/skills)). Custom prompts are **deprecated** in favor of skills.
|
||||||
|
- **Install / distribution:** Skills can ship inside plugins, which can also bundle "app mappings", MCP server config, and presentation assets in a single package. Distribution is git-based; no centralized marketplace UI as of May 2026.
|
||||||
|
- **Skill-like unit:** instructions + optional scripts/resources; plugins add MCP servers and tool config.
|
||||||
|
- **Spec compatibility:** **Native Anthropic Agent Skills.** Codex was the first non-Anthropic agent to commit to AGENTS.md, and the second (after Gemini) to ship the skills spec natively.
|
||||||
|
|
||||||
|
## 4. Cursor
|
||||||
|
|
||||||
|
- **Equivalent:** **Rules** (`.cursorrules` legacy, `.cursor/rules/*.mdc` modern), **MCP** for tools, plus **Agent Skills** (added 2026).
|
||||||
|
- **On-disk format:** `.cursor/rules/*.mdc` are markdown-with-frontmatter rule files, scoped per-glob and either always-on or auto-attached ([Rules | Cursor Docs](https://cursor.com/docs/rules)). Skills follow `SKILL.md` ([Mastering Cursor 2026](https://rzaeeff.medium.com/mastering-cursor-rules-agent-skills-modes-models-and-best-practices-81908ec4f4a4)).
|
||||||
|
- **Install / distribution:** Rules are **manual copy / git**; the community hub is [cursor.directory](https://cursor.directory/) (no in-IDE installer until recently). MCP servers install via Cursor's settings UI.
|
||||||
|
- **Skill-like unit:** Rules are prompt-only. Skills can include workflows, hooks, and pull in domain knowledge on demand. Tools come via MCP, not via the rules format.
|
||||||
|
- **Spec compatibility:** Cursor reads **AGENTS.md** and now **Anthropic-style `SKILL.md`** folders ([awesome-cursor-skills](https://github.com/spencerpauly/awesome-cursor-skills)). Rules → skills migration is encouraged for richer workflows.
|
||||||
|
|
||||||
|
## 5. Aider
|
||||||
|
|
||||||
|
- **Equivalent:** **Conventions files** (any markdown, loaded with `--read`) and built-in slash commands. No plugin/skill system.
|
||||||
|
- **On-disk format:** Plain markdown convention docs (often `CONVENTIONS.md`); `.aider.conf.yml` for config ([Aider docs](https://aider.chat/docs/)).
|
||||||
|
- **Install / distribution:** Manual. Aider is intentionally minimal — no marketplace, no plugins.
|
||||||
|
- **Skill-like unit:** Effectively a system-prompt fragment. No tool/hook/subagent extensibility beyond what aider builds in.
|
||||||
|
- **Spec compatibility:** Reads `AGENTS.md` if you point it at one with `--read AGENTS.md`. Does **not** auto-discover `SKILL.md`. Closest cross-agent surface is "write your conventions in AGENTS.md and `--read` it."
|
||||||
|
|
||||||
|
## 6. Cline / Roo Code
|
||||||
|
|
||||||
|
- **Cline:** Custom instructions file, `.clinerules`, and a first-party **MCP Marketplace** inside the VS Code extension — one-click install of MCP servers ([Roo vs Cline 2026](https://www.morphllm.com/comparisons/roo-code-vs-cline)). No native Anthropic-style skills.
|
||||||
|
- **Roo Code:** Forked Cline. Adds **Custom Modes** — named personas (Architect, Debugger, ESP32 Expert, etc.) defined in `.roomodes` JSON, with a **Custom Mode Marketplace / Mode Gallery** for sharing. Supports MCP but no MCP marketplace ([Roo Code docs](https://docs.roocode.com/)).
|
||||||
|
- **Note:** Roo Code announced shutdown of all products on **May 15, 2026** ([Morph comparison](https://www.morphllm.com/comparisons/roo-code-vs-cline)); the team is migrating to roomote.dev. Treat Roo formats as legacy.
|
||||||
|
- **On-disk format:** `.clinerules` (markdown), `.roomodes` (JSON of mode definitions).
|
||||||
|
- **Skill-like unit:** A "mode" is system prompt + tool allowlist + model config — closest non-Anthropic analog to a skill but agent-bound, not a portable folder.
|
||||||
|
- **Spec compatibility:** Neither natively loads `SKILL.md`. Both speak MCP.
|
||||||
|
|
||||||
|
## 7. Continue.dev
|
||||||
|
|
||||||
|
- **Equivalent:** `config.yaml` (formerly `config.json`), **custom slash commands**, **rules**, and the **Continue Hub** (rebranded "Mission Control").
|
||||||
|
- **On-disk format:** `~/.continue/config.yaml` declares models, context providers, slash commands (named prompt templates), rules, and MCP servers ([Continue config reference](https://docs.continue.dev/reference)).
|
||||||
|
- **Install / distribution:** **Hub / Mission Control** is a real web marketplace — browse configs, one-click add, auto-sync across IDEs, share with team ([Hub vs Local](https://docs.continue.dev/guides/understanding-configs)). This is the most polished marketplace UX outside Claude Code.
|
||||||
|
- **Skill-like unit:** Slash commands are prompt + optional model routing; rules are always-on context; MCP supplies tools. No equivalent of a self-contained skill folder with hooks + scripts.
|
||||||
|
- **Spec compatibility:** Does **not** natively load `SKILL.md`. You'd reimplement a skill as a custom slash command + rule + MCP server.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## AGENTS.md as the de-facto cross-agent standard
|
||||||
|
|
||||||
|
`AGENTS.md` is the closest thing to a universal coding-agent format today.
|
||||||
|
[agents.md](https://agents.md/) reports 60,000+ projects using it, and it's
|
||||||
|
read natively by **Codex, Cursor, Copilot, Gemini CLI, OpenCode, and
|
||||||
|
Aider** (via `--read`). It's now stewarded by the Agentic AI Foundation
|
||||||
|
under the Linux Foundation, alongside MCP and the Goose framework
|
||||||
|
([AGNTCon + MCPCon 2026](https://www.aiexpertmagazine.com/agntcon-mcpcon-north-america-2026-everything-you-need-to-know/)).
|
||||||
|
Claude Code reads `CLAUDE.md` but most teams symlink or duplicate to
|
||||||
|
`AGENTS.md` ([AGENTS.md vs CLAUDE.md](https://hivetrail.com/blog/agents-md-vs-claude-md-cross-tool-standard)).
|
||||||
|
|
||||||
|
It is **prose-only** — no tools, no hooks, no subagents. It's the lowest
|
||||||
|
common denominator, and that is its strength.
|
||||||
|
|
||||||
|
## MCP as the cross-agent tool surface
|
||||||
|
|
||||||
|
Every agent in this list speaks MCP: Claude Code, Codex, Gemini CLI,
|
||||||
|
OpenCode, Cursor, Cline, Roo, Continue. If you want to ship reusable
|
||||||
|
*tools* (not instructions) to N agents with one artifact, MCP is the
|
||||||
|
only realistic answer in 2026.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## What's actually portable today?
|
||||||
|
|
||||||
|
A realistic verdict:
|
||||||
|
|
||||||
|
| Artifact | Portability |
|
||||||
|
|---|---|
|
||||||
|
| **MCP server** | Universal. Works in all 8 agents surveyed. Best surface for tools. |
|
||||||
|
| **AGENTS.md** | Near-universal for prose instructions. Codex, Cursor, Gemini, OpenCode, Aider, Copilot. |
|
||||||
|
| **Anthropic `SKILL.md` skill** | Native in Claude Code, **Codex, Gemini CLI, OpenCode, Cursor**. Not native in Aider, Cline, Roo, Continue — but most can be shimmed via MCP. This is the new emerging standard for richer-than-prose units. |
|
||||||
|
| **Slash commands** | Per-agent. Claude `.md` ≠ Gemini `.toml` ≠ Continue YAML ≠ Cursor. Don't try. |
|
||||||
|
| **Hooks** | Per-agent. Claude, OpenCode, Gemini, Codex each have their own hook shapes. |
|
||||||
|
| **Subagents / modes / personas** | Per-agent. Claude subagents, Roo modes, Cline modes, Codex subagents — different file shapes, no convergence yet. |
|
||||||
|
| **Plugin / marketplace manifest** | Per-agent. Claude `plugin.json`, Gemini `gemini-extension.json`, Codex plugin, OpenCode plugin — not interchangeable. |
|
||||||
|
|
||||||
|
**Practical recipe for a cross-agent capability in 2026:**
|
||||||
|
|
||||||
|
1. Ship tools as an **MCP server** (npm or container).
|
||||||
|
2. Ship instructions as **`AGENTS.md`** at repo root, plus a Claude-compatible **`SKILL.md`** folder for richer on-demand workflows (works natively in Claude/Codex/Gemini/OpenCode/Cursor).
|
||||||
|
3. Maintain a thin **per-agent plugin manifest** (`.claude-plugin/plugin.json`, `gemini-extension.json`, etc.) that points at the same skills + MCP server. The bodies are reused; only the wrapper differs.
|
||||||
|
|
||||||
|
So: **one artifact for everything is not realistic**, but **two artifacts (MCP + SKILL.md) plus thin per-agent manifests** covers the vast majority of the modern coding-agent landscape.
|
||||||
|
|
||||||
|
> *Caveats: the skill ecosystem moved fast in Q1–Q2 2026 (Codex deprecated custom prompts in April; Roo announced shutdown for May 15; Gemini's skills support is March-2026 new). Verify the latest docs before committing to any format.*
|
||||||
@@ -0,0 +1,99 @@
|
|||||||
|
# Commit Message Conventions
|
||||||
|
|
||||||
|
Every commit message MUST be prefixed with a gitmoji that describes the nature of the change.
|
||||||
|
|
||||||
|
Format: `<emoji> <short description>`
|
||||||
|
|
||||||
|
## Gitmoji Reference
|
||||||
|
|
||||||
|
| Emoji | Description |
|
||||||
|
|-------|-------------|
|
||||||
|
| 🎨 | Improve structure / format of the code |
|
||||||
|
| ⚡️ | Improve performance |
|
||||||
|
| 🔥 | Remove code or files |
|
||||||
|
| 🐛 | Fix a bug |
|
||||||
|
| 🚑️ | Critical hotfix |
|
||||||
|
| ✨ | Introduce new features |
|
||||||
|
| 📝 | Add or update documentation |
|
||||||
|
| 🚀 | Deploy stuff |
|
||||||
|
| 💄 | Add or update the UI and style files |
|
||||||
|
| 🎉 | Begin a project |
|
||||||
|
| ✅ | Add, update, or pass tests |
|
||||||
|
| 🔒️ | Fix security or privacy issues |
|
||||||
|
| 🔐 | Add or update secrets |
|
||||||
|
| 🔖 | Release / Version tags |
|
||||||
|
| 🚨 | Fix compiler / linter warnings |
|
||||||
|
| 🚧 | Work in progress |
|
||||||
|
| 💚 | Fix CI Build |
|
||||||
|
| ⬇️ | Downgrade dependencies |
|
||||||
|
| ⬆️ | Upgrade dependencies |
|
||||||
|
| 📌 | Pin dependencies to specific versions |
|
||||||
|
| 👷 | Add or update CI build system |
|
||||||
|
| 📈 | Add or update analytics or track code |
|
||||||
|
| ♻️ | Refactor code |
|
||||||
|
| ➕ | Add a dependency |
|
||||||
|
| ➖ | Remove a dependency |
|
||||||
|
| 🔧 | Add or update configuration files |
|
||||||
|
| 🔨 | Add or update development scripts |
|
||||||
|
| 🌐 | Internationalization and localization |
|
||||||
|
| ✏️ | Fix typos |
|
||||||
|
| 💩 | Write bad code that needs to be improved |
|
||||||
|
| ⏪️ | Revert changes |
|
||||||
|
| 🔀 | Merge branches |
|
||||||
|
| 📦️ | Add or update compiled files or packages |
|
||||||
|
| 👽️ | Update code due to external API changes |
|
||||||
|
| 🚚 | Move or rename resources (e.g.: files, paths, routes) |
|
||||||
|
| 📄 | Add or update license |
|
||||||
|
| 💥 | Introduce breaking changes |
|
||||||
|
| 🍱 | Add or update assets |
|
||||||
|
| ♿️ | Improve accessibility |
|
||||||
|
| 💡 | Add or update comments in source code |
|
||||||
|
| 🍻 | Write code drunkenly |
|
||||||
|
| 💬 | Add or update text and literals |
|
||||||
|
| 🗃️ | Perform database related changes |
|
||||||
|
| 🔊 | Add or update logs |
|
||||||
|
| 🔇 | Remove logs |
|
||||||
|
| 👥 | Add or update contributor(s) |
|
||||||
|
| 🚸 | Improve user experience / usability |
|
||||||
|
| 🏗️ | Make architectural changes |
|
||||||
|
| 📱 | Work on responsive design |
|
||||||
|
| 🤡 | Mock things |
|
||||||
|
| 🥚 | Add or update an easter egg |
|
||||||
|
| 🙈 | Add or update a .gitignore file |
|
||||||
|
| 📸 | Add or update snapshots |
|
||||||
|
| ⚗️ | Perform experiments |
|
||||||
|
| 🔍️ | Improve SEO |
|
||||||
|
| 🏷️ | Add or update types |
|
||||||
|
| 🌱 | Add or update seed files |
|
||||||
|
| 🚩 | Add, update, or remove feature flags |
|
||||||
|
| 🥅 | Catch errors |
|
||||||
|
| 💫 | Add or update animations and transitions |
|
||||||
|
| 🗑️ | Deprecate code that needs to be cleaned up |
|
||||||
|
| 🛂 | Work on code related to authorization, roles and permissions |
|
||||||
|
| 🩹 | Simple fix for a non-critical issue |
|
||||||
|
| 🧐 | Data exploration / inspection |
|
||||||
|
| ⚰️ | Remove dead code |
|
||||||
|
| 🧪 | Add a failing test |
|
||||||
|
| 👔 | Add or update business logic |
|
||||||
|
| 🩺 | Add or update healthcheck |
|
||||||
|
| 🧱 | Infrastructure related changes |
|
||||||
|
| 🧑💻 | Improve developer experience |
|
||||||
|
| 💸 | Add sponsorships or money related infrastructure |
|
||||||
|
| 🧵 | Add or update code related to multithreading or concurrency |
|
||||||
|
| 🦺 | Add or update code related to validation |
|
||||||
|
| ✈️ | Improve offline support |
|
||||||
|
| 🦖 | Code that adds backwards compatibility |
|
||||||
|
|
||||||
|
## Custom Rules
|
||||||
|
|
||||||
|
| Emoji | Description |
|
||||||
|
|-------|-------------|
|
||||||
|
| 🤖 | Add or update agent files (CLAUDE.md, skills, AGENTS.md, copilot configs, etc.) |
|
||||||
|
|
||||||
|
## Initial Commit
|
||||||
|
|
||||||
|
New git repositories MUST use the following as their initial commit message:
|
||||||
|
|
||||||
|
```
|
||||||
|
🦇 BATMAN
|
||||||
|
```
|
||||||
Reference in New Issue
Block a user