- 📁 agents/
- 📁 evals/
- 📁 references/
- 📄 SKILL.md
This skill should be used when the user asks to "generate an image", "create a logo", "draw an icon", "edit this photo", "change background to transparent", "remove background", "use GPT image", "use Codex to draw", "用 GPT image 生成图片", "用 Codex 画图", "帮我生成一张图", "改成透明背景", "把这张图编辑一下", or any prompt-to-image or reference-image-edit task that benefits from a structured CLI returning JSON results and JSONL progress events. Supports OpenAI `gpt-image-2` (via `OPENAI_API_KEY` or OpenAI-compatible base URL) and Codex `image_generation` (via `~/.codex/auth.json`) under one command surface, with masks, custom sizes up to 4K, transparent backgrounds, and a raw request escape hatch.
`required_core_version` and `requires["claude-code-hermit"]` in `hermit-meta.json`, and
Development guidance for contributing to the PowerPlatform Dataverse Client Python SDK repository. Use when working on SDK development tasks like adding features, fixing bugs, or writing tests.
This skill should be used when the user asks to "develop a feature", "implement a ticket", "build PROJ-123", "run the development pipeline", "develop this ticket end to end", or wants fully autonomous feature implementation with parallel research agents, planning, phased implementation, review, and PR creation. Zero checkpoints; pauses only on blockers.
- 📄 rag_query.py
- 📄 SKILL.md
Query ClawOS project documents with citations. Use when the user asks about
Analyze test coverage data from tobari.toon and help improve test coverage incrementally. Use when the user has run go test with tobari enabled (e.g., `GOFLAGS="$(tobari flags)" go test ./...`) and wants to improve test coverage or increase code coverage percentage. Triggers on phrases like "improve coverage", "increase coverage", "coverage improvement", or "add more tests".
>-
Pre-deployment checklist — verify contracts compile, tests pass, and deployment config is correct
- 📁 agents/
- 📁 examples/
- 📁 references/
- 📄 .editorconfig
- 📄 .gitattributes
- 📄 .gitignore
当用户希望用《毛泽东选集》/教员的方法分析现实问题、把毛选中的方法论转成现代分析框架，或明确提出“用毛选帮我分析”“用教员的方法帮我分析 xxx”“用新青年帮我分析”“按新青年的方法拆一下”“按主要矛盾/阶段判断/统一战线/实践检验的方法分析”时使用。适用于工作推进、复杂协作、关系边界、学习成长、生活决策、团队治理等结构性问题；一旦触发，就默认按复杂结构题处理。澄清是所有任务的硬前提：先锁目标，再持续澄清到关键结构基本清楚，之后才进入分析。澄清题默认使用带 A/B/C/D 和“其他”的选项式追问。正式输出前再确认用户要文字版还是 HTML 版。
Reference for how an agent's memory, filesystem, and runtime are organized. Part 1 explains the memory system — the durability hierarchy from conversation to shared library, plus auxiliary layers (soul, token ledger, time veil) and the network-topology layer that lives across stores. Part 2 is the filesystem reference — where manifests, system prompts, history, mailboxes, heartbeats, logs, signal files, and config live, with exact field-level schemas. Part 3 is the runtime anatomy — turn loop, state machine, signal consumption lifecycle, molt mechanics, and mail atomicity. Read Part 1 to understand how knowledge flows between layers; Part 2 when debugging or inspecting on-disk state; Part 3 when reasoning about *how an agent runs*.
- 📄 EXAMPLES.md
- 📄 INSTALL.md
- 📄 OPCODES.md
Maximum-fidelity Python source reconstruction from Nuitka `.nbc` / `NBC/2` files produced by `nuitka_decompiler.py`. Use when the user pastes or references a `.nbc` file, an `AI_READY_NBC` bundle, sections such as `@MOD`, `@CONSTS`, `@RAW_CHUNK`, `@OPS`, `@ASM`, `@FORENSICS`, `module_code_*`, `mod_consts[N]`, or asks to rebuild Python source from a Nuitka C-compiled module. The goal is evidence-backed reconstruction, not guaranteed perfect 1:1 recovery; uncertain spans must be marked.
- 📁 .claude/
- 📁 .claude-plugin/
- 📁 .github/
- 📄 .gitignore
- 📄 CHANGELOG.md
- 📄 CODE_OF_CONDUCT.md
Prevent Terraform/OpenTofu hallucinations by diagnosing and fixing failure modes: identity churn, secret exposure, blast-radius mistakes, CI drift, and compliance gate gaps. Use when generating, reviewing, refactoring, or migrating IaC and when building delivery/testing pipelines.
