跳到正文
cccskills
免费在 GitHub 公开

mcp

Plan abi MCP server work — the 12-tool JSON-RPC 2.0 stdio surface plus its custom loopback HTTP compatibility listener. Use for abi-mcp, tools, transports, or middleware.

中文简介正在准备中。当前显示原文说明。

donaldfilimon/abi星标 19(GitHub 19 + cccskills 0)

实测评分 未实测

查看安装方法

包含的文件（1）

  • SKILL.md3.1 KB

SKILL.md（原文）

安装前可以查看交给 AI 代理的指令内容。

mcp

Entry point for the abi MCP server (crates/abi-mcp/src/). Routes to specialists:

You want to…Use
Smoke-test abi-mcp + verify the 12-tool contractmcp-smoke
Deep-dive the MCP superpowerabi-superpower-mcp
Transport / middleware / protocol limits detailabi-mcp-transport

Frozen contract (do not change without a parity/contract-test update)

  • 12 tools, in source order: ai_run, ai_complete, ai_learn, ai_train, wdbx_query, scheduler_stats, scheduler_info, connector_test, gpu_status, plugin_list, wdbx_stats, plugin_run.
  • protocol.MAX_REQUEST_SIZE = 64 KB; MAX_JSON_DEPTH = 32; per-field 16 KB cap in crates/abi-mcp/src/middleware.rs (declarative validation before dispatch).
  • Frozen enums: connector_test tool arg service ∈ {openai, anthropic, discord, twilio, grok}; ai_train tool arg format ∈ {jsonl, csv, text}.

Honest boundary

Stdio exits on stdin EOF (not a long-lived daemon). Startup also attempts the custom loopback listener (127.0.0.1:8080 by default, configured with ABI_MCP_HTTP_PORT / ABI_MCP_HTTP_TOKEN); bind failure leaves stdio running. GET /sse opens a persistent MCP 2024-11-05 HTTP+SSE session whose POST /message?sessionId=<id> responses arrive as SSE message events (202 on the POST; unknown session 404; at most 16 sessions), while POST /message without a session keeps the one-shot direct-reply mode. It is not Streamable HTTP (2025-03-26), and non-loopback serving is not supported. Rust handlers return bounded JSON-RPC errors without exposing internal error chains.

Client registrations (cleaned 2026-09): consistent across grok/claude/codex/opencode/cursor + abi project scopes. Use launcher for abi-mcp everywhere. See opencode and help skills for the exact current lists.

Finalized state (2026-09-16)

  • Best options: central only ~/.grok/skills + launch.sh sync (idempotent, 0 on re-run); donald-mode; bot-repo authority separate (abbey-bot etc); permission fixes in opencode.jsonc + .grok/config.toml; key comments (GITHUB_TOKEN="", disabled with # requires KEY).
  • Global MCPs standardized: .cursor/mcp.json, .claude.json, ~/.grok/config.toml [mcp_servers.*], /.config/opencode/opencode.jsonc — core: abi-mcp (via /.../abi/mcp/launcher.sh stdio), skill-loop@0.3.3, context7, fetch(uvx), filesystem(/.abi/), github(unauth), memory, playwright. (4 more disabled w/ comments).
  • Verifs: central sync-clis.py --dry-run = "0 actions/changes"; abi in-repo .agents/skills/sync-clis/launch.sh --dry-run (separate mech); mcp-smoke.sh = "RESULT: PASS — 12/12"; configs parse clean; no drift (timestamps match, dry=0); key files re-read (abs paths).
  • Maintain: ALWAYS edit only central ~/.grok/skills/* (or .grok/config.toml for grok MCPs); run sync; never hand-edit copies. Abbey-bot/others: own AGENTS/CLAUDE, separate.
  • No loose ends. All per context + final re-checks.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护，适用 Google 的隐私权政策和服务条款。

同一仓库的技能

abbey-system-prompt

免费

Maintain the Abbey / Aviva / Abi Discord system prompts in the Rust abbey-bot (`src/ask.rs`) and keep the hosted Grok bots (Grok Bot Abbey, Aviva Grok) in step with them. Use when the user says "improve grok bots", "abbey prompt", "persona prompt", "ask.rs", "system prompt", "tip floor", asks to change how Abbey/Aviva/Abi speak on Discord, or after an abbey-bot PR merges and the hosted bot's tip floor needs bumping. Runs as /abbey-system-prompt.

中文简介正在准备中。当前显示原文说明。

donaldfilimon/abi192026年10月27日 更新

abi-claims-validator

免费

Validate ABI docs and external collateral against repo evidence and docs/contracts/external-claims-audit.mdx. Use when auditing claims, scanning docs for unsupported QPS/sharding/FHE/AES language, checking one claim before publish, or re-confirming the external-claims audit. Agent procedure only — not a CLI or slash command. Pair with abi-doc-claims-sync when editing docs.

中文简介正在准备中。当前显示原文说明。

donaldfilimon/abi192026年10月27日 更新

abi-doc-claims-sync

免费

Synchronize ABI Markdown and docs claims with executable behavior. Use before editing README, AGENTS.md, CLAUDE.md, GEMINI.md, docs/**/*.mdx, walkthroughs, changelogs, or any old ABI Markdown that mentions WDBX, MCP, GPU, clustering, compression, FHE, agents, or benchmarks.

中文简介正在准备中。当前显示原文说明。

donaldfilimon/abi192026年10月27日 更新

abi-goal-orchestrator

免费

Plan and execute ABI repo work from the TODO board, roadmap/spec docs, stable Rust 1.99.1 constraints, and validation gates. Use when the user asks to find ABI todos/roadmaps, organize a large implementation from tasks/todo.md, or decide the next safe work slice. Distinct from the goals skill — that skill owns the persistent ledger tasks/goals.md; this skill plans from the active board and north-star specs.

中文简介正在准备中。当前显示原文说明。

donaldfilimon/abi192026年10月27日 更新

abi-mcp-transport

免费

Validate ABI MCP JSON-RPC stdio and its custom loopback HTTP compatibility endpoint, including auth, limits, notifications, and shutdown.

中文简介正在准备中。当前显示原文说明。

donaldfilimon/abi192026年10月27日 更新

abi-plugin-system

免费

Review ABI's 16 compiled-in plugin fixtures, manifest validation, manual bundled registry, and real CLI/MCP run dispatch without claiming dynamic loading.

中文简介正在准备中。当前显示原文说明。

donaldfilimon/abi192026年10月27日 更新

查看 donaldfilimon 的全部技能

报告此技能的问题