Instructions file CodexOpenCode
Instructions for akitaonrails/ai-memory, covering long-term memory (ai-memory), use the installed ai-memory agent skills, when you write a project rule, write it here, refreshing this snippet and agents.md — ai-memory contributor guide.
Instructions file
Instructions for akitaonrails/ai-memory: Read and follow AGENTS.md. This repository keeps a single canonical agent instruction file for Claude Code, OpenCode, Codex, Cursor, Gemini CLI, and other AGENTS-aware harnesses.
Skill Claude CodeCodex
Use this skill for any explicit wiki mutation in ai-memory: saving durable or time-bounded project knowledge, recording a rule or annotation, updating a note, or deleting a memory page. Trigger by semantic intent rather than exact wording; routine session capture is not a durable-page request.
Skill Claude CodeCodex
Use this skill for any request whose goal is session continuity across agents or time: finding a pending handoff, resuming previous work, saving next-session context, wrapping up, or discarding a mistaken handoff. Trigger by semantic intent rather than exact wording.
Skill Claude CodeCodex
Use this skill for any ai-memory knowledge-base maintenance request: consolidating observations, reviewing session lessons, proposing durable learnings, auditing or linting the wiki, finding contradictions, pruning stale memory, or running auto-improvement. Trigger by semantic intent rather than exact wording.
Skill Claude CodeCodex
Use this skill for any request whose goal is read-only retrieval from ai-memory: project history, prior context, decisions, rules, gotchas, recent activity, full wiki pages, or status/briefing. Trigger by semantic intent rather than exact wording, including when ai-memory is not named.
Skill Claude CodeCodex
Use this skill for any request to install, refresh, repair, inspect, or remove ai-memory's agent-facing routing: managed instruction snippets, Agent Skills, CLAUDE.md/AGENTS.md integration, or local/global skill roots. Trigger by semantic intent rather than exact wording.
Instructions file
Instructions for akitaonrails/ai-usagebar, covering claude.md, release checklist — must do all of these, hard invariants — never break these, secret-discipline rules (learned the hard way) and live api smoke discipline.
akitaonrails/llm-coding-benchmark
Skill Claude CodeCodex
Automatically evaluates an LLM coding benchmark result using a standardized 0-100 rubric across 8 dimensions. Use when a benchmark finishes, when the user asks to evaluate a model, analyze a run's quality, or generate a score for a result. Also activates for 'score', 'evaluate benchmark', 'audit model', or 'analyze…
akitaonrails/llm-coding-benchmark
Instructions file
Claude Code instructions for akitaonrails/llm-coding-benchmark, covering claude.md, project overview, key commands, run specific model(s) and force re-run even if result.json exists.
Instructions file
Claude Code instructions for akitaonrails/FrankClaw, covering claude.md — frankclaw development guide, project, build & test, architecture and code conventions.