donaldfilimon/abi / .agents/skills/agent-plan-train
agent-plan-train
VerifiedPlan and execute ABI repo work from current TODOs, roadmap/spec docs, stable Rust 1.99.1 constraints, and validation gates. Use when user asks to find all ABI todos/roadmaps, compile ABI goals/specs, organize a large ABI implementation goal, or decide the next safe work slice in the abi repository.
agent-plan-train
Workflow
- Start in
/Users/donald/sources/repos/abiunless the user gives another ABI checkout. - Inspect
git status --short --branchbefore edits; preserve unrelated dirty work. - Read
AGENTS.md,tasks/todo.md, andtasks/lessons.md. - Optional: refresh the inventory with the abi-mega
abi_inventoryPython helper (--repo /Users/donald/sources/repos/abi) if available (ships with the codexabi-megaplugin, not this repo); skip when absent. - Optional: load a sibling goals markdown named
current-goalsunder this skill'sreferences/dir if present (codex plugin copies carry it; the canonical repo copy does not) — otherwise derive the source map fromtasks/todo.md+docs/spec/wdbx-north-star.mdx. - Derive a small executable slice. Prefer changes that make one TODO, roadmap gap, doc mismatch, or validation gap measurably more true.
- Keep claims honest: source/build/tests override prose.
- Verify with the narrow command that proves the slice, then the broader gate when the blast radius justifies it.
Goal Rules
- Treat
tasks/todo.mdas the active board anddocs/spec/wdbx-north-star.mdxas the Current/Partial/Proposed map. - Do not convert disclosed stubs into fake completions. Native dispatch, production clustering, production FHE, and learned-compression claims need real source/tests.
- Do not add legacy CLI names. Preserve the frozen top-level command set and the MCP 12-tool contract.
- When changing public feature APIs, update both the real and stub modules and run
./tools/check.sh. - When changing docs, run
.agents/skills/docs-validate/validate.shin addition to code gates.
Useful Commands
# optional; codex abi-mega plugin only:
# abi_inventory --repo /Users/donald/sources/repos/abi
./tools/cargo.sh --version
./tools/check.sh
Use the optional sibling goals markdown named current-goals under this skill's references/ dir (when present — see Workflow step 5) for the current source inventory and validation ladder.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 468k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 197k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |