Skills for Claude Code

These skills are associated with Claude Code because their author either published them under the harness's install path or tagged the repository for it on GitHub. Both are statements of intent by the author.

Neither is a test result. We have not run any of these with and without the skill enabled, so nothing here tells you whether a skill improves output, what it adds in tokens, or whether it duplicates behaviour the harness already has. When we run that comparison, the numbers will appear here with the task, the versions and the budget.

Worked on in the last 90 days (59)

Someone pushed a commit recently. This is the shortlist worth trying first.

levnikolaevich-claude-code-skills-ln-33-code-modernizer — last commit 2026-08-06
Modernizes a bounded capability by removing obsolete custom mechanisms or reducing bundle and maintenance cost. Use for proven modernizatio…
levnikolaevich-claude-code-skills-ln-34-benchmark-comparator — last commit 2026-08-06
Compares tools or implementations through reproducible A/B workloads, correctness oracles, and controlled measurements. Use to choose alter…
levnikolaevich-claude-code-skills-ln-35-surgical-change-implementer — last commit 2026-08-06
Implements a bounded product-code change through the smallest complete root-cause solution. Use for scoped delivery; not for planning, revi…
levnikolaevich-claude-code-skills-ln-41-test-strategy-planner — last commit 2026-08-06
Designs risk-based test portfolio decisions and prioritized scenarios without changing code. Use when requirements need a test strategy; no…
levnikolaevich-claude-code-skills-ln-42-acceptance-test-builder — last commit 2026-08-06
Creates, updates, consolidates, retires, and runs scoped acceptance tests using project-native tooling. Use when executable acceptance evid…
levnikolaevich-claude-code-skills-ln-51-opportunity-evaluator — last commit 2026-08-06
Evaluates new product directions using current demand, acquisition, competition, economics, and validation evidence. Use before commitment;…
levnikolaevich-claude-code-skills-ln-61-skill-reviewer — last commit 2026-08-06
Reviews standalone skills and their configured distribution surfaces before publication. Use for skill release readiness; not for product c…
levnikolaevich-claude-code-skills-ln-62-repository-publisher — last commit 2026-08-06
Validates, commits, pushes, and remotely verifies approved repository changes. Use when publication is requested; not for releases, package…
levnikolaevich-claude-code-skills-ln-63-release-publisher — last commit 2026-08-06
Prepares and publishes a tagged GitHub release from repository evidence. Use for an explicit release request; not for ordinary commits, pac…
levnikolaevich-claude-code-skills-ln-64-community-announcer — last commit 2026-08-06
Drafts and publishes fact-checked GitHub Discussions announcements. Use for releases, updates, or project news; not for release creation or…
levnikolaevich-claude-code-skills-ln-71-system-design-baseline-builder — last commit 2026-08-06
Creates a project baseline of architecture drivers and constraints. Use before design or planning; not for target design, plan review, impl…
levnikolaevich-claude-code-skills-ln-72-current-architecture-documenter — last commit 2026-08-06
Documents implemented current-state architecture from repository evidence. Use for onboarding or migration baselines; not for target design…
levnikolaevich-claude-code-skills-ln-73-system-design-proposal-builder — last commit 2026-08-06
Creates a decision-complete target system design from requirements and constraints. Use before implementation planning; not for requirement…
levnikolaevich-claude-code-skills-ln-74-architecture-decision-recorder — last commit 2026-08-06
Records one architecture decision with context, alternatives, tradeoffs, and consequences. Use for a significant choice; not for broad desi…
levnikolaevich-claude-code-skills-ln-75-architecture-diagram-builder — last commit 2026-08-06
Creates evidence-backed current or target architecture diagrams when the diagram is the primary deliverable. Not for UI design, architectur…
levnikolaevich-claude-code-skills-ln-76-architecture-migration-planner — last commit 2026-08-06
Plans a reversible architecture migration with compatibility, data movement, rollout, and rollback. Use for current-to-target transitions;…
code-yeongyu-oh-my-openagent-agent-browser — last commit 2026-08-06
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate website…
code-yeongyu-oh-my-openagent-codex-qa — last commit 2026-08-06
QA the omo Codex Light edition (lazycodex / packages/omo-codex) itself, in strict isolation so ONLY our plugin is exercised, never the user…
code-yeongyu-oh-my-openagent-comment-checker — last commit 2026-08-06
Use when Codex needs to understand or respond to automatic comment-checker feedback emitted after an edit-like PostToolUse hook.
code-yeongyu-oh-my-openagent-dev-browser — last commit 2026-08-06
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, tes…
code-yeongyu-oh-my-openagent-get-unpublished-changes — last commit 2026-08-06
Compare HEAD with the latest published npm versions and list all unpublished changes by release layer. Triggers: unpublished changes, chang…
code-yeongyu-oh-my-openagent-github-triage — last commit 2026-08-06
Read-only GitHub triage for issues AND PRs. 1 item = 1 background task (category: quick). Analyzes all open items and writes evidence-backe…
code-yeongyu-oh-my-openagent-github-triage-b55188 — last commit 2026-08-06
Read-only GitHub triage for issues AND PRs. 1 item = 1 background task (category: quick). Analyzes all open items and writes evidence-backe…
code-yeongyu-oh-my-openagent-hyperplan — last commit 2026-08-06
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain,…
code-yeongyu-oh-my-openagent-hyperplan-445a3c — last commit 2026-08-06
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain,…
code-yeongyu-oh-my-openagent-init-deep — last commit 2026-08-06
(builtin) Initialize hierarchical AGENTS.md knowledge base
code-yeongyu-oh-my-openagent-lcx-contribute-bug-fix — last commit 2026-08-06
Contribute a verified bug fix for LazyCodex, lazycodex-ai, omo-codex, bundled Codex skills, or upstream Codex CLI bugs. Opens a fork PR onl…
code-yeongyu-oh-my-openagent-lcx-doctor — last commit 2026-08-06
Diagnose LazyCodex and Codex CLI installation health against the latest sources. Use whenever the user asks for a doctor or health check, s…
code-yeongyu-oh-my-openagent-lcx-report-bug — last commit 2026-08-06
Create a high-signal bug issue or PR in the repo that owns the defect. Use this whenever the user asks to report, file, open, or triage a L…
code-yeongyu-oh-my-openagent-lsp — last commit 2026-08-06
Use when Codex needs language-server diagnostics, definitions, references, symbols, or rename safety checks in the current workspace.
code-yeongyu-oh-my-openagent-omomomo — last commit 2026-08-06
Easter egg command - about oh-my-opencode. Triggers: omomomo, about, easter egg.
code-yeongyu-oh-my-openagent-opencode-qa — last commit 2026-08-06
QA opencode itself, per case: verify the CLI/terminal (opencode run, db, serve, export), prove a specific plugin hook/action/event fired vi…
code-yeongyu-oh-my-openagent-pre-publish-review — last commit 2026-08-06
Nuclear-grade 16-agent pre-publish release gate. Runs /get-unpublished-changes to detect all changes since last npm release, spawns up to 1…
code-yeongyu-oh-my-openagent-pre-publish-review-1a78b4 — last commit 2026-08-06
Nuclear-grade 16-agent pre-publish release gate. Runs /get-unpublished-changes to detect all changes since last npm release, spawns up to 1…
code-yeongyu-oh-my-openagent-publish — last commit 2026-08-06
Publish oh-my-opencode to npm by triggering the GitHub Actions publish workflow and verifying its artifacts. Ship-only: never runs pre-publ…
code-yeongyu-oh-my-openagent-remove-deadcode — last commit 2026-08-06
Remove unused code from this project with ultrawork mode, LSP-verified safety, atomic commits. Triggers: remove dead code, dead code, clean…
code-yeongyu-oh-my-openagent-rules — last commit 2026-08-06
Use when the user asks about Codex Rules behavior, injected project rules, supported rule file locations, matching, or environment configur…
code-yeongyu-oh-my-openagent-security-research — last commit 2026-08-06
Team Mode security research skill. Orchestrates 3 vulnerability hunters and 2 PoC engineers to audit a codebase in parallel, prove exploita…
code-yeongyu-oh-my-openagent-teammode — last commit 2026-08-06
Codex-only team orchestration: run a named team of cooperating Codex workers with durable, script-managed state. MUST USE when the user ask…
code-yeongyu-oh-my-openagent-tech-debt-audit — last commit 2026-08-06
Thorough, file-cited technical debt audit across 9 dimensions using AST-grep (tree-sitter), grep, language-native tooling, and optionally C…
code-yeongyu-oh-my-openagent-ultrawork — last commit 2026-08-06
Binding ultrawork mode directive for omo on Codex. When a prompt contains ultrawork or ulw, the omo UserPromptSubmit hook injects a short b…
code-yeongyu-oh-my-openagent-ulw-loop — last commit 2026-08-06
Goal-like loop that uses ultrawork mode to decompose work into systematic, evidence-bound steps.
code-yeongyu-oh-my-openagent-ulw-plan — last commit 2026-08-06
ACTIVATES ONLY on an explicit user request for the ulw-plan workflow: the user themselves saying ulw-plan, ulw plan, /skill:ulw-plan, or as…
code-yeongyu-oh-my-openagent-ulw-plan-c7fffe — last commit 2026-08-06
ACTIVATES ONLY on an explicit user request for the ulw-plan workflow: the user themselves saying ulw-plan, ulw plan, /skill:ulw-plan, or as…
code-yeongyu-oh-my-openagent-work-with-pr — last commit 2026-08-06
Full PR lifecycle in a fresh task-owned git worktree: implement via the ulw-loop skill with mandatory evidence-bound manual QA → reviewer-r…
code-yeongyu-oh-my-openagent-work-with-pr-9071f0 — last commit 2026-08-06
Full PR lifecycle in a fresh task-owned git worktree: implement via the ulw-loop skill with mandatory evidence-bound manual QA → reviewer-r…
worldwonderer-oh-story-claudecode-browser-cdp — last commit 2026-08-06
Use this skill when you need to control a Chrome browser via CDP (Chrome DevTools Protocol) to reuse existing login sessions. Covers: launc…
worldwonderer-oh-story-claudecode-story — last commit 2026-08-06
网络小说工具箱主入口。根据用户需求自动路由到对应 skill，并可启动本地 Dashboard 查看拆文库、写作项目和编辑文本。触发方式：/story、$story、/story dashboard、$story dashboard、/网文、「我想写小说」「打开工作台」「检查更…
worldwonderer-oh-story-claudecode-story-cover — last commit 2026-08-06
小说封面生成。根据书名、作者名自动分析题材风格，调用 GPT-Image-2 直接生成含标题和署名的专业级网文封面。触发方式：/story-cover、/封面、「帮我做个封面」「生成封面图」「做个小说封面」「封面设计」。
worldwonderer-oh-story-claudecode-story-deslop — last commit 2026-08-06
网文去AI味。检测并清除文本中的AI写作痕迹，让文字回归自然、非模板化。触发方式：/story-deslop、/去AI味、「去AI味」「这篇太AI了」「网文去AI味」。
worldwonderer-oh-story-claudecode-story-import — last commit 2026-08-06
逆向导入已有小说。将已写好的小说（半成品或完本）反向解析为标准项目目录结构，兼容 story-long-write / story-short-write 后续写作流程；内部复用 story-long-analyze / story-short-analyze 的拆解管道，按篇…
worldwonderer-oh-story-claudecode-story-long-analyze — last commit 2026-08-06
长篇网文拆文。深度拆解爆款长篇小说的黄金三章、人设架构、爽点设计、节奏控制。单一深度拆解管道：跑完黄金三章（Stage 1）后产出快速预览报告并询问是否继续全量拆解，确认后从 Stage 2 续跑逐章摘要、聚合分析、设定关系、汇总报告，全程产物落盘拆文库/{书名}/。触发方式…
worldwonderer-oh-story-claudecode-story-long-scan — last commit 2026-08-06
长篇网文扫榜。分析起点、番茄、晋江等平台排行榜数据，提炼市场趋势与热门题材。触发方式：/story-long-scan、/长篇扫榜、「长篇什么火」「起点排行」。
worldwonderer-oh-story-claudecode-story-long-write — last commit 2026-08-06
长篇网文写作。从大纲到正文，辅助长篇网络小说的创作，包括世界观、人物、情节线管理。触发方式：/story-long-write、/写长篇、「帮我开书」「写大纲」「日更」「续写」「继续写」「修改第X章」「回炉」「重写第X章」。
worldwonderer-oh-story-claudecode-story-review — last commit 2026-08-06
多视角对抗式审查。full/lean 模式在已部署 reviewer agents 时并行 spawn；缺失/异常 agents 或 spawn 失败时自动降级 solo，参考文件不可读时使用内置 rubric fallback。触发方式：/story-review、/审查、「…
worldwonderer-oh-story-claudecode-story-setup — last commit 2026-08-06
网文写作工具集基础设施部署。为 Claude Code / OpenCode / Codex / ZCode / OpenClaw / Reasonix 提供内置适配；Web AI / 通用 Agent 可走 skills + AGENTS.md 文件模式。触发方式：/stor…
worldwonderer-oh-story-claudecode-story-short-analyze — last commit 2026-08-06
短篇网文拆文。拆解爆款短篇小说（番茄短篇 / 故事会 / 知乎盐选 / 追妻 / 世情 / 重生 / 虐渣等通俗题材）的故事核、结构、情感线、反转设计、写作手法、共鸣层次。单一全量拆解管道：跑完 Stage 2-6 产出完整拆文报告，落盘到拆文库/{书名}/，下游 story…
worldwonderer-oh-story-claudecode-story-short-scan — last commit 2026-08-06
短篇网文扫榜。分析知乎盐言、七猫、黑岩、点众等平台热门短篇数据，捕捉风口题材。触发方式：/story-short-scan、/短篇扫榜、「短篇什么火」「知乎故事排行」。
worldwonderer-oh-story-claudecode-story-short-write — last commit 2026-08-06
短篇网文写作。辅助短篇小说创作，从构思到成稿，聚焦情绪拉扯与节奏把控。触发方式：/story-short-write、/写短篇、「帮我写一篇短篇」「写个盐言故事」。

Page 2 of 24

How this page is ordered

Entries are grouped by whether anyone is still working on them, using the date of the most recent push to the repository. They are not ordered by stars, because a star is a bookmark somebody left once and never took back.

Where we have not checked an entry yet, it says so rather than being mixed in with the verified ones.