gyy0592

gyy0592/claude-config

Instructions file

Configuration instructions for Claude Code, an AI coding tool, in the gyy0592/claude-config project. They require Claude settings to be changed through the setclaude.sh script and then run.

gyy0592/claude-config

Skill Claude CodeCodex

Audits whether the Corporal's current turn / current task complies with all 44 mandatory requirements (4-step opening / truthfulness + facts-first / four-module reflection / dispatch / monitoring / status files / anti-over-engineering / Private-specific items), outputs censor.md listing each item as ✅ pass / ❌ fail /…

gyy0592/claude-config

Skill Claude CodeCodex

Manage the user's claude-config git repo — sync, commit, push skill changes and settings. Use ONLY when the user explicitly asks to sync, update, push, or check their claude config — e.g. '/claude-config-sync', 'sync my config', 'push config'. Never trigger automatically.

gyy0592/claude-config

Skill Claude CodeCodex

Generate a structured, navigable code documentation document for a Python codebase — the 'code tree'. Use this skill whenever the user asks to document a codebase, explain how the code works end-to-end, generate a code tree, write code documentation, understand call chains, or map out how functions relate to each…

gyy0592/claude-config

Skill Claude CodeCodex

Diagnostic and fix reference for Codex CLI failures. MUST read when: codex review fails with any error, bwrap sandbox errors appear (loopback / RTMNEWADDR / Operation not permitted), stream disconnection occurs (Reconnecting... / stream disconnected before completion), codex hangs or exits unexpectedly, or any codex…

gyy0592/claude-config

Skill Claude CodeCodex

Rewrites any passage to maximize information density while losing zero information. Every sentence becomes as short as it can be, yet keeps full subject, verb, and object, and carries no ambiguous references. Use as the final language-level pass inside paper-reader and any writing-heavy skill, and use it standalone…

gyy0592/claude-config

Skill Claude CodeCodex

Enumerates every distinct contribution/innovation of a research paper and explains each with the four-ingredient rule (motivation, intuition, scenario/example, core formula). Use when the user asks "what are the contributions of this paper", "what's novel here", "summarize the innovations", "what did they actually do…

gyy0592/claude-config

Skill Claude CodeCodex

Interactive launcher that collects entry file / repo root / output directory / cap via AskUserQuestion, then hands off to the recursive-dep-trace-parallel skill. Guesses plausible defaults by scanning the current working directory for entry-point-shaped files and infers the repo root from the chosen entry. Use…

gyy0592/claude-config

Skill Claude CodeCodex

Audits whether the current code is already running at maximum speed by checking GPU/CPU/IO bottleneck saturation. Red-alarms if NONE of GPU/CPU/IO is bottlenecked — that proves speedup is mathematically possible and the code is wasting compute. Loads 5 sub-skills progressively. Trigger this skill aggressively whenever…

gyy0592/claude-config

Skill Claude CodeCodex

Structured error logging for AI mistakes. Triggers when: (1) user invokes /error-log; (2) user expresses frustration or anger at AI for making a mistake — cursing, insults, phrases like 'what the hell', 'you broke it', 'are you stupid', '你怎么又错了', '搞什么', '垃圾', '废物'. On trigger: AI self-diagnoses the error from…

gyy0592/claude-config

Skill Claude CodeCodex

Standards for writing experiment code and scripts — config-driven parameters, structured output directories, code snapshots, real-time CSV recording, and pre-flight confirmation. This skill is the mandatory reference for ANY code that produces outputs worth keeping. MUST read this skill when: (1) writing or modifying…

gyy0592/claude-config

Skill Claude CodeCodex

Zero-assumption instruction compliance protocol. Enforces a mandatory 'understand → clarify → confirm → audit → execute' pipeline before any action. Triggers when: (1) user points out AI violated instructions, did something unauthorized, went beyond scope, or made assumptions ('你怎么自己做了', '我没让你做这个', '不要自作主张', 'I didn't…

gyy0592/claude-config

Skill Claude CodeCodex

Generate a project-specific draftsimplify.md for a code repository — a high-level plan for an upcoming maintainability refactor that preserves runtime behavior bit-for-bit. Use this skill whenever the user wants to PLAN a code-cleanup / refactor / maintainability pass on a whole repository, before any code is changed.…

gyy0592/claude-config

Skill Claude CodeCodex

Generate a high-level draft document (draft.md) from a user's task description. Use ONLY when the user explicitly invokes /gen-draft or says '写draft', '生成draft'. Never trigger automatically. The draft captures WHAT and WHY, never HOW.

gyy0592/claude-config

Skill Claude CodeCodex

Generate a full 13-section detailed experiment report for flamemoonshot training runs, including formulas, reproducibility checklist, failure analysis, and visualizations. Use when the user asks for a detailed/full/complete report, 完整报告, 详细报告, or invokes /gen-report-detailed.

gyy0592/claude-config

Skill Claude CodeCodex

Generate a comprehensive experiment report with full output discovery, visualization generation, and paper-style figure analysis. Use when the user asks to write a report, summarize an experiment, document results, 写报告, 整理实验, 总结实验结果, or invokes /gen-report.

gyy0592/claude-config

Skill Claude CodeCodex

Re-calibrates the distinction between a good general rule and a bad patch when extending any rule system (CLAUDE.md, skill rulebook, coding-style guide, review checklist). Load whenever the user flags patching behavior ("不通用" / "修修补补" / "打补丁" / "抽象层不对" / "sibling rule smell" / "this is a special case of an existing…

gyy0592/claude-config

Skill Claude CodeCodex

Spawn a /loop 30m task that monitors the active humanize RLCR loop and any background shells launched in this session. Use ONLY when the user explicitly invokes it — e.g. '/humanize-watchdog', 'start humanize watchdog', 'monitor my humanize loop'. The watchdog checks every 30 minutes whether the RLCR loop is still…

gyy0592/claude-config

Skill Claude CodeCodex

Rigorous mathematical explainer for a single concept, step, or equation. Use whenever the user asks to "explain mathematically", "show the derivation", "rewrite that with math", or whenever a previous explanation felt vague about a formula. Also invoke when paper-reader, pipeline-walk, or contrib-extract needs to…

gyy0592/claude-config

Skill Claude CodeCodex

A dispatcher that chooses between two smaller skills when a request involves changing code or rules.

gyy0592/claude-config

Skill Claude CodeCodex

Strict process for the smallest possible diff when the user asks to modify code or docs. Trigger aggressively whenever a user says "最小修改" / "别动其他东西" / "改得太多" / "画蛇添足" / "我没让你做那个" / "顺手改" / "minimum modification" / "only fix X" / "don't touch anything else" / "no scope creep", AND whenever the AI is about to touch more…

gyy0592/claude-config

Skill Claude CodeCodex

Document-level rigour auditor. Enforces that every term, symbol, abbreviation, experimental label, and formula appears with its definition adjacent to its first occurrence — and re-states it on distant reuse. Also enforces no-step-skipping in math derivations. Invoke whenever writing or reviewing a technical report…

gyy0592/claude-config

Skill Claude CodeCodex

Writes a structured Before/After comparison that makes the mathematical and conceptual delta between two approaches immediately visible. Use whenever the user wants to contrast a new method with prior art, a closed form with its approximation, method A vs method B, or "old way vs new way" — e.g. "compare Adam vs SGD…

gyy0592/claude-config

Skill Claude CodeCodex

Produces a reader-friendly overview of an academic paper in a fixed eight-section structure with intuitive analogies, structured Before/After comparisons, key formulas with where-blocks, and experiment tables. Use when the user says "overview this paper", "quick analysis", "概览", "快速分析", "分析这篇论文", or invokes…