GitHub-Issues mit `gh issue create` strukturiert anlegen, inklusive deutschem Markdown-Body, Emoji-Präfix im Titel und repo-nativen Labels aus `gh label list`. Verwenden, wenn Codex ein neues GitHub-Issue für Features oder User Stories, Bugs, Refactorings, technische Schulden, Research-Spikes, Dokumentationsaufgaben, Chores oder Epics entwerfen oder direkt erstellen soll.

Use when designing safe public APIs that wrap unsafe Rust code, adding unsafe blocks to existing types, reviewing unsafe code for soundness, or creating new types backed by raw pointers, MaybeUninit, or FFI

INVOKE THIS SKILL at the START of any LangChain/LangGraph/Deep Agents project, before writing any agent code. Determines which framework layer is right for the task: LangChain, LangGraph, Deep Agents, or a combination. Must be consulted before other agent skills.

Deploy Tempo Zones, start zone nodes, validate router swap-and-deposit flows, and debug zone sync, portal ingestion, withdrawal, sequencer key, and generated zone artifact issues in this repository. Use when working with just deploy-zone, zone-up, deploy-router, demo-swap-and-deposit, or generated/<name>/zone.json.

Lossless LLM-optimized compression of source documents. Use when the user requests to 'distill documents' or 'create a distillate'.

Review checkpoint specs and tests to identify tests that encode ambiguous interpretations rather than explicit requirements. Use when asked to check checkpoint_N.md against test_checkpoint_N.py, when auditing tests for ambiguity, or when reviewing snapshot eval failures for interpretive issues.

Write, critique, and iterate prompts for OpenAI GPT-5 series models. Use for tasks like: (1) turning vague requirements into high-signal instructions, (2) selecting between quick vs deep reasoning behaviors, (3) creating robust structured-output prompts (JSON schemas, tool calls), (4) designing evaluation prompts and rubrics, and (5) debugging prompt failures (hallucinations, format drift, tool misuse). Trigger when the user mentions GPT-5, prompt engineering, system/developer messages, structured outputs, agent prompts, or wants best-practice templates.

Structured workflow for discovering, reproducing, and fixing bugs in Searchlite by inspecting real code paths (CLI/HTTP/core), validating durability invariants, and producing regression tests; use when investigating incorrect results, crashes, data loss risks, or “it sometimes fails” reports.

Enforce the phase implementation workflow for Palette Kit v0.3 phases. Use when implementing a roadmap phase, creating a phase branch, validating the lint/typecheck/test/build pipeline, generating a patch for review, or preparing commit/push/PR steps.

>-

Security review checklist for code and infrastructure

>

>-

Use after scope-need and relevant specialist skills approve work. Takes the scoped-need document and produces a flat, ordered list of discrete changes required. Each change is scoped to be a single commit.

>-

Format high-quality Git commit messages from staged or unstaged changes with stable conventions. Use when Codex is asked to create, polish, or validate commit messages, especially for Conventional Commits, commitlint-compatible repositories, squash/fixup flows, or teams that require consistent subject/body/footer structure.

Use this skill when a bug report needs structured investigation before planning or coding.

>-

Build, query, and inspect the project knowledge graph in .planning/graphs/

Plan and implement Python changes with ruff, pyright, and pytest validation before commit.

Git 변경사항을 분석하여 Conventional Commits 형식의 커밋 메시지를 생성합니다. 커밋, commit, 커밋 메시지 요청 시 자동 활성화됩니다.

Turns a Gardener runtime failure into a deterministic session recording + test.

AWS security finding analysis: analyze findings, map to Atmos components/stacks, generate structured remediation with exact Terraform changes and deploy commands

Use when you have made code changes and want another CLI agent to review them before committing or continuing. Covers crafting review prompts, scoping reviewer permissions to read-only, interpreting feedback, and follow-up clarification sessions.

Use Moneta shared memory via MCP tools to recall project knowledge

This is an example `workflow-<slug>/SKILL.md` generated from a workflow spec.

对 Python 改动做“问题优先”的代码审查。适用于审查 diff、定位行为回归、评估风险、检查测试覆盖缺口，尤其是 crawlers、storage、fish_intel_mvp 相关改动。

Transform one mentioned lecture transcript markdown file into a structured lecture note and save a merged output file in the same folder. Use when the user asks to create lecture notes from an existing transcript file. Keep transcript cleanup loose and preserve original wording as much as possible.

hologres-cli

Use this skill when creating or refactoring Svelte 5 / SvelteKit frontend code, especially UI components, local feature UIs, component APIs, and Tailwind-based styling. This skill improves code quality by enforcing modern Svelte 5 conventions, strong component boundaries, clear state ownership, reusable modular logic, and disciplined Tailwind usage. Not intended for visual design exploration or branding work.

Manage hotspot monitoring definitions for the wy-hotspot-monitoring workspace. Use this skill whenever the user asks to create, update, pause, resume, inspect, list, or delete monitoring items, or when they want to change keywords, scopes, sources, intervals, GitHub repo allowlists, or notification email settings. Prefer this skill over editing data files manually.

Upgrades React Native apps to newer versions by applying rn-diff-purge template diffs, updating package.json dependencies, migrating native iOS and Android configuration, resolving CocoaPods and Gradle changes, and handling breaking API updates. Use when upgrading React Native, bumping RN version, updating from RN 0.x to 0.y, or migrating Expo SDK alongside a React Native upgrade.

Deploy any project to Vercel. **Always deploy as preview** (not production) unless the user explicitly asks for production.

>

Applies the project's commit message convention. Use when writing commit messages, making git commits, or summarizing changes.

Solve one assignment problem file using a single endpoint with two logical tracks: (A) Math/Physics PDF problem solving (lecture slides/lecture notes as ground truth) and (B) code artifact generation. Save a final answer with detailed explanation next to the problem file.

>

Fast semantic code navigation via LSP. Load FIRST before ANY code task - even 'simple' ones. Trigger scenarios: (1) fixing lint/type/pyright/mypy warnings or errors, (2) fixing reportAny/reportUnknownType/Any type errors, (3) adding type annotations, (4) refactoring or modifying code, (5) finding where a function/class/symbol is defined, (6) finding where a symbol is used/referenced/imported, (7) understanding what a function calls or what calls it, (8) exploring unfamiliar code or understanding architecture, (9) renaming symbols across codebase, (10) finding interface/protocol implementations, (11) ANY task where you'd use ripgrep to find code or read-file to view a function. Use `leta show SYMBOL` instead of read-file, `leta refs SYMBOL` instead of ripgrep for usages, `leta grep PATTERN` instead of ripgrep for definitions, `leta files` instead of list-directory.

>

Expert Docker and Nginx deployment assistant. Use for Docker configuration, containerization, VPS deployment, infrastructure setup, SSL certificates, docker-compose files, nginx reverse proxy, deployment guides, infrastructure documentation, cloud deployment, container orchestration, production deployment, environment configuration, dockerfiles, server setup, deployment checklists.

Configure and use Biome (biomejs) for TypeScript linting and formatting. Use when setting up Biome in a project, configuring lint rules, migrating from ESLint/Prettier, fixing lint errors, setting up CI pipelines with Biome, or configuring git hooks for code quality. Covers biome.json configuration, file inclusion/exclusion patterns, rule overrides, and integration with build tooling.

Autonomously diagnose Magento 2 message queue problems — backlog growth, stuck consumers, broker connectivity, DLQ overflow — and scaffold new queues (communication, topology, consumer, publisher) from a specification. Produces an AMQP Report with root cause and fix.

go-code-review

Guidelines and instructions for developing the Z8 runtime. Includes coding standards, build processes, and testing workflows.

Self-improving agent architecture using ChromaDB for continuous learning, self-evaluation, and improvement storage. Agents maintain separate memory collections for learned patterns, performance metrics, and self-assessments without modifying their static .md configuration.

Opinionated constraints for building better interfaces with agents.

Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity.

Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.

Use when needing to programmatically invoke a CLI coding agent (Claude Code, OpenCode) from Python, delegate work to a sub-agent, or orchestrate multiple agents. Covers AgentShell instantiation, prompt execution, response streaming, session resumption, tool scoping, and cost tracking.