Skill Claude CodeCodex
Update per-package CHANGELOG.md files for a Ratel release. Drafts entries with git-cliff (scoped per package), lets you curate, then writes the CHANGELOGs. Handles both RC entries and GA-graduation collapse (merging X.Y.Z-rc. sections into a single X.Y.Z section). Invoke before tagging a release.
Skill Claude CodeCodex
Publish local .claude skills/loops to Ametyst — verbatim, flattened, no brain rewrite; optional retire-local (MOVE originals to deprecated-skills/, never delete) makes Ametyst the source of truth.
Instructions file CodexOpenCode
Instructions for ratel-ai/ratel, covering agents.md — working in the ratel repo, build & test, rust, ts and python (from src/sdk/python/; needs uv).
Instructions file
Instructions for ratel-ai/ratel, a project described as: Context engineering for AI agents. 80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.
Plugin Claude Code
Ratel plugins for scoped MCP gateway setup, hybrid capability search, usage, and debugging.
Instructions file CodexOpenCode
Instructions for ratel-ai/ratel-local, covering agents.md, setup, core commands, rules and ways of working.
Instructions file
Instructions for ratel-ai/ratel-local, a project described as: MCP server library + ratel-local CLI: expose a Ratel tool catalog as a Model Context Protocol server. Manage upstream MCP servers, OAuth, and Claude Code import from one binary.
Plugin Claude Code
Persistent project-scoped Ratel gateway with BM25, semantic, and hybrid capability search.
MCP server Claude CodeCodexCursor +2
Ratel Local package: a project-scoped persistent MCP gateway with BM25, semantic, and hybrid capability search plus the ratel-local CLI. Runs locally from the @ratel-ai/ratel-local npm package.
Hook
Runs before the agent uses a tool, executing log-tool-usage.mjs via node. From ratel-ai/ratel-local.
Hook
Runs after a tool call finishes, executing log-tool-usage.mjs via node. From ratel-ai/ratel-local.
Skill Claude CodeCodex
Analyze Ratel Local tool usage logs and propose improvements to the configured tool catalog. Use when the user asks to review Ratel tool usage, improve available MCP tools, audit failed or repeated tool calls, tune Ratel upstream servers, or suggest better tools based on Codex or Claude Code hook logs.
Skill Claude CodeCodex
Configure, use, and debug the Ratel Local plugin and ratel-local CLI. Use when working with Codex or Claude Code plugin setup, native trace exporters, importing or linking existing MCP servers into Ratel config, adding upstream MCP servers, configuring capability retrieval, running auth, opening the local UI, checking…
Skill Claude CodeCodex
Read a partner's agent codebase, score it across the 12-dimension catalog, and emit an evidence-cited markdown plus branded scored HTML report. Use for a first-touch audit: assess/review/audit our agent, where to improve, spot low-hanging fruit, an honest read of what's weak, what Ratel would notice, or…
Skill Claude CodeCodex
Break a bloated, monolithic agent system prompt into a lean stable core plus extracted Ratel-style skills. Use when a prompt is too long or does too many things, to extract or factor procedures into skills, decompose or split a prompt, cut per-turn token cost, or /ratel-decompose-prompt. Writes a markdown…
Skill Claude CodeCodex
Inspect an existing agent codebase, map each agent's tools and skills, then implement Ratel so every agent discovers and loads only its intended capabilities. Use when asked to add, wire, set up, or integrate Ratel; connect existing tools or SKILL.md playbooks to an agent through Ratel; or migrate a Vercel AI SDK…
Skill Claude CodeCodex
Inspect an agent codebase to decide where tracing belongs, turn on Ratel's native OTLP telemetry, and pick the OTel backend the team already runs to export to, then write a proposal covering instrumentation, backend selection, and the dashboards that prove value. Use when mounting observability, asking where tracing…
Skill Claude CodeCodex
Audit a codebase's tool and skill definitions against a failure-mode rubric and write a markdown tuning plan with per-definition before/after rewrites that make them retrievable by Ratel's hybrid lexical + semantic index and usable by the model. Use when the model picks the wrong tool, tools never get picked…