Explore skills
Showing 26851–26880 of 77104 skills
Verify documentation keeps up with a code change in dynamic-neural-field-composer - Doxygen on public API, the matching wiki page, and stale references elsewhere. Use before opening a PR, or when asked whether docs need updating.
Jgocunha/dynamic-neural-field-composer
Stars: 19Claude CodeCodexCheck a change for performance regression against this machine's recorded baseline - decide whether the diff needs checking, run the deck benchmark under the hygiene wrapper, and attribute any regression to an element. Use before opening a PR that touches the simulation hot path.
Jgocunha/dynamic-neural-field-composer
Stars: 19Claude CodeCodexRead the branch diff in dynamic-neural-field-composer and print a PR title and description in chat, filling the repo's pull request template. Use when asked to write, draft or suggest a PR title/description, or "what should the PR say".
Jgocunha/dynamic-neural-field-composer
Stars: 19Claude CodeCodexEnd-to-end workflow for resolving one GitHub issue in dynamic-neural-field-composer - branch, TDD, build, review, docs, PR. Use when asked to fix, implement, or close a specific issue number.
Jgocunha/dynamic-neural-field-composer
Stars: 19Claude CodeCodexSplit a multi-area agent-office task across parallel subagents per .claude/rules/PARALLEL_WORK.md — contract first, disjoint file ownership, lead-only shared config, phased integration. Use for any task touching two or more of assets, core, adapters, desktop, renderer logic, renderer adapters or docs, or whenever the user asks to work in parallel.
arxdsilva/agent-office
Stars: 9Claude CodeCodexGenerates Angular code and provides architectural guidance. Trigger when creating projects, components, services, or HTTP communication, or for best practices on reactivity (signals, linkedSignal, resource, httpResource), queries and content projection, forms, dependency injection, routing, server and hybrid rendering (SSR, prerendering, hydration), accessibility (ARIA), animations, styling (component styles, Tailwind CSS), testing, naming conventions, or CLI tooling.
HitKeep/hitkeep
Stars: 108Claude CodeCodexEdit, trim, cut, caption, retime, combine, or export video, audio, and image files through Cassette. Use this skill whenever the user asks to change, preview, or render media in the project, even if they never say "Cassette" or name a tool, for example "trim the intro off demo.mp4", "add subtitles to this clip", "make a 30-second cut", "put a title on it", "export the video". Drives the tools of the `cassette` MCP server (oh-my-cassette), which relays a running conversation with the Cassette editing agent.
Cassette-Editor/oh-my-cassette
Stars: 220Claude CodeCodexScaffold a well-designed agent loop with best-practice coaching and a cross-model review council. Use when the user wants to design, build, or set up an agent loop, iterative agent workflow, self-review loop, LLM-as-judge loop, multi-model council, reviewer/judge gate, or /goal-style looping process. Start from a named pattern template (security-scan, code-review, bug-hunt, docs-sync, research-synthesis) or from a blank interview. Guide goal refinement, typed verification criteria, reviewer and judge selection, privacy boundaries, termination guards, no-progress stops, and lightweight observability, then emit a RUN_IN_SESSION.md handoff prompt plus portable loop.yaml, loop.resolved.json, LOOP.md, and run-loop.py.
ksimback/looper
Stars: 719Claude CodeCodexDeploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".
ever-co/ever-works
Stars: 200Claude CodeCodex编辑或审阅已有中文文本中的空话、重复和模板化表达,保留原意、事实、确定程度和作者声音。 主文件包含通用表达模式、中文句式、体裁判断、作者样本使用和文件保护,适用于去 AI 腔与自然化润色。 商务营销、论文与审稿回复、基金申请分别按需加载专用 reference。用于写作质量编辑,不判定作者身份。
Hyacehila/humanizer-zh-next
Stars: 256Claude CodeCodexPlan a huge chunk of work — more than one agent session can hold — as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
egma-ai/egma
Stars: 146Claude CodeCodexUse when 统计资产/做资产表/分析人物/场景/道具。产出暖金主题HTML资产分析报告。
hashgraph-online/awesome-codex-plugins
Stars: 1.5kClaude CodeCodexReview UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
lootlog/monorepo
Stars: 29Claude CodeCodexEffect development guidance. Use when implementing or reviewing code that composes Effect APIs or patterns, or that adds or changes API signatures.
lootlog/monorepo
Stars: 29Claude CodeCodex根据题目、建模分析和真实代码结果生成完整 Word 数学建模论文,用户显式要求时同时生成 LaTeX 论文。
XiaoMaColtAI/math-modeling-skill
Stars: 1.9kClaude CodeCodex根据题目、建模分析和真实代码结果生成完整 Word 数学建模论文,用户显式要求时同时生成 LaTeX 论文。
XiaoMaColtAI/math-modeling-skill
Stars: 1.9kClaude CodeCodexKoopman operator theory for infinite-dimensional linear lifting of nonlinear dynamics. Generates dynamics from observables.
plurigrid/asi
Stars: 72Claude CodeCodexoapply: Operad algebra evaluation via colimits. Composes machines/resource sharers.
plurigrid/asi
Stars: 72Claude CodeCodexStructuredDecompositions.jl: Sheaves on tree decompositions for FPT algorithms
plurigrid/asi
Stars: 72Claude CodeCodexBefore editing a file or symbol, find everything that depends on it, score how risky the change is, and stop for approval when it's high. Use before changing a shared function, type, API, schema or config, or when the user asks "is it safe to change this", "what breaks if I change X" or "what's the blast radius".
off-grid-ai/skills
Stars: 175Claude CodeCodexCheck everything before and after a production deploy, with a rollback plan and clear rollback triggers. Use when the user is about to deploy or just deployed, or says "is it safe to deploy", "pre-deploy check", "post-deploy check" or "we're going to prod". Not for committing, opening PRs or app store releases.
off-grid-ai/skills
Stars: 175Claude CodeCodexGet to know an unfamiliar codebase fast. Maps what it does, its modules, entry points, riskiest files, recent changes and the rules not to break, writes it to CODEBASE.md, then answers questions from that map with sources. Use when the user is new to a project or says "onboard me", "where do I start", "how does X work here", "where is the payment logic" or "give me an overview".
off-grid-ai/skills
Stars: 175Claude CodeCodexPlan a new project before any code exists. Researches the domain, then has an architect, a product lead and a security lead plan it independently, and merges them into one PLAN.md that names where they disagree. Use when the user is starting something new and says "plan this", "help me start this project", "write a PLAN.md" or "what should the stack be". Not for changes to an existing codebase (use learn-this-codebase first).
off-grid-ai/skills
Stars: 175Claude CodeCodexAdd end-to-end tests to code that has none, in tiers by confidence, and run every test before handing it over. Use before refactoring untested code, after inheriting a project, or when the user says "add tests for this flow", "write e2e tests for login" or "we have no tests for X".
off-grid-ai/skills
Stars: 175Claude CodeCodexTurn your agent into a senior peer who keeps the whole goal in view, checks your claims against real data, and disagrees in one line when the facts say so. Use when you say "/argue-with-me", "push back", "argue with me", "peer argument", "zoom out", "you're overindexing", "are you sure?", "check me", or when you insist, correct or redirect mid-task.
off-grid-ai/skills
Stars: 175Claude CodeCodexYour agent works like a careful CTO on your product, with one writer for all code, no lost features, and the right skills loaded for each job. Use at the start of real work in any product repo, or when you say "act as CTO", "act as CPTO", "follow the rules", "take ownership of this" or "run this like a tech lead".
off-grid-ai/skills
Stars: 175Claude CodeCodexGet the most done with several agents at once, builders write code in one shared tree with no test runs, a supervisor tests everything that landed together on a timer and removes the bottleneck each round. Use when you say "/build-while-you-sleep", "keep going", "finish the code", "no test runs", "group and test", "what's the bottleneck", "run agents in parallel", and on every supervisor wake-up.
off-grid-ai/skills
Stars: 175Claude CodeCodexMake your agent talk short and decide like a senior lead, result first, main point in bold, only real emergencies treated as urgent, clear work done without asking. Use when you say "/no-fluff", "keep it short", "just tell me", "stop asking and do it", "too long", or load it at the start of any session where you want plain answers and fewer questions.
off-grid-ai/skills
Stars: 175Claude CodeCodexTurn a few notes on your screens into one design rule, written down once and applied to every screen, so the next round of notes is smaller. Your agent proposes the rule, waits for your yes, changes every screen, and shows it back before and after. Use when you say "I've added comments", "look at my comments", "review loop", "/fix-it-everywhere", "run an iteration", or "apply this to the rest of the screens".
off-grid-ai/skills
Stars: 175Claude CodeCodexEvery screen, flow and feature your agent builds meets the bar of a mature consumer app, with no lost features, no dead ends and instant feedback on every action. Use before designing, building or reviewing any UI, or when you say "make it look great", "polish this", "no shoddy work", "product bar" or "review this screen".
off-grid-ai/skills
Stars: 175Claude CodeCodex