2.7K skills · sorted by relevance
Build and evaluate Mamba models for long sequences using state-space models, which summarize past inputs in an internal state. Covers setup, pretrained text generation, differences between Mamba-1 and Mamba-2, and speed comparisons with Transformers.
Query an indexed code graph, a database of code relationships, to find callers, dependencies, model associations, and call paths. Use the results to understand which components may need attention before changing a function or model.
Build formula-driven Excel financial models for linked financial statements, business valuation, and fundraising forecasts. Separate assumptions, calculations, and results, compare scenarios, and check that statement balances and saved calculation results are consistent.
Route codebase exploration, file analysis, and web research through context-mode tools in Antigravity CLI. Process large outputs outside the conversation and return focused findings, with indexed content available for later searches.
Build, run, and debug the Kilo JetBrains plugin using its Gradle workflows. It covers isolated development storage, chat logs, sandbox recovery, and switching between a pinned CLI release and locally built CLI code.
Prepare files for printing on Bambu Lab printers by opening sliced files in Bambu Connect or unsliced models in Bambu Studio. The user selects the printer, checks the setup, and starts printing in the app.
Check a paper's numerical consistency using fixed rules, then record blocking or warning decisions and outstanding findings. The workflow preserves a traceable correction history, while explicitly leaving broader semantic review unavailable in its Codex mode.
Operate an opencodex proxy, which acts as an intermediary for AI service requests. Use CLI commands to inspect configuration, manage accounts and models, review request routing, and check usage and runtime health.
Build machine learning workflows that connect data checks, training, evaluation, and deployment. The skill implements experiment tracking, model version management, and automated retraining, with reproducible environments and explicit validation thresholds before models enter production.
Explain code structure and behavior with text diagrams, including before-and-after views of changes. Trace data flow and state changes, clarify design choices, and examine assumptions, possible failures, and interactions between tasks running at the same time.
Model distributed systems and concurrent algorithms in TLA+ or PlusCal, then check possible states with TLC. Use the results to investigate deadlocks, broken rules, and differences between specifications and implementation code.
Configure a new OpenRig agent seat, a managed place for an agent to run, using a prior Claude or Codex conversation. Covers fork settings, new session identities, and checks that distinguish forking from restoring.
Select relevant code using Trailmark's map of function relationships, then delegate explanation, review, or edit proposals to a smaller model. Limit the supplied source, check cited evidence, and verify proposed changes before applying them.
Review source code without running it to identify potential security vulnerabilities. Findings include severity, confidence, attack scenarios, and suggested fixes, delivered as JSON for further triage and Markdown for human review.
Review Python, JavaScript/TypeScript, and Go code against security guidance for the languages and frameworks in use. Identify important weaknesses, suggest improvements, and produce prioritized reports with code references, or apply secure defaults when writing new code.
Audit a React codebase using React Doctor scan results and code inspection. It ranks issues by impact and effort, then writes detailed implementation plans that another agent can execute, while leaving source code unchanged during the audit.
Look up Claude Code commands and options for interactive work or automation. Covers non-interactive execution, session management, output formats, tool permissions, and agent definitions, with command examples for scripts and CI/CD workflows.
Bring a project's formal verification back in line with the code after the code changes: find the commits that touched verified code, update the model, harness, or properties to describe the code as it is now, rerun, and say whether each failure is drift in the verification or a bug in the code. Use for /maintain-formal-verification-skill, "is the model still true to the code", or after merges and refactors that touched verified code without rechecking it.
The English summary is being prepared. Showing the original description.
Bring a project's formal verification back in line with the code after the code changes: find the commits that touched verified code, update the model, harness, or properties to describe the code as it is now, rerun, and say whether each failure is drift in the verification or a bug in the code. Use for /maintain-formal-verification-skill, "is the model still true to the code", or after merges and refactors that touched verified code without rechecking it.
The English summary is being prepared. Showing the original description.
Configures and verifies an expanded, model-aware context window for OpenAI Codex CLI and Desktop. Use when Codex shows ~258K context, you want 500K or 1M tokens, auto-compaction fires too often, or model_context_window/model_auto_compact_token_limit needs repair. Not for changing the selected model or other Codex settings.
The English summary is being prepared. Showing the original description.
Reapply and repair Windows Codex Desktop after Store upgrades, including custom provider models hidden by Statsig available_models filtering, the dependent blue-purple Power slider and its Ultra toggle, Fast Mode request/UI gates, locale i18n, plugin UI gates, Chrome/browser_use gates, Goal command gates, Windows Computer Use availability gates and plugin/runtime repair, phone remote-control pairing under third-party/API-key main app usage, Desktop dynamicTools/inputSchema thread-start schema drift, local conversation visibility recovery after model_provider switches, restored-conversation missing-cwd continuation repair, ASAR integrity repair, signing/installing patched MSIX packages, SDK cleanup, Fast Mode wire verification, local plugin marketplace registration, and optional custom model_instructions_file setup (the bundled system prompt, also called 听话水).
The English summary is being prepared. Showing the original description.
Review generated or changed production code before it ships, using Clean Code, SOLID, DRY, KISS, YAGNI, and LLM-specific failure-mode checks in any programming language. Best used reactively after an agent writes, edits, refactors, or fixes code, before presenting, committing, or merging the result. Use when the user asks "review this PR", "is this safe to merge?", "make this cleaner", "audit this code", "refactor this", "fix this bug", or after a coding agent produced implementation code. Can also guide writing when explicitly invoked before a risky edit. Invoke it on your own initiative the moment you finish writing, editing, or refactoring non-trivial production code, before presenting or committing — don't wait to be asked. DO NOT USE for factual/conceptual questions, CI/tooling config, git workflow, running/debugging tests, pure architecture discussion, prose writing, data analysis, or test-code review (use test-guard).
The English summary is being prepared. Showing the original description.
Use this skill for WeChat Mini Program AI via wx.cloud.extend.AI (小程序, wx.cloud apps). Covers generateText and streamText with callbacks (onText, onEvent, onFinish); streamText needs a data wrapper, generateText returns the raw response. Models via wx.cloud.extend.AI.createModel with groups hunyuan-exp (小程序成长计划), cloudbase (main managed), or custom-*; model id goes in the data wrapper `model` field. MUST run two-step preflight before code — see body. NOT for browser/Web (use ai-model-web), Node.js backend (use ai-model-nodejs), or image generation (use ai-model-nodejs).
The English summary is being prepared. Showing the original description.
Use this skill when a browser/Web app (React, Vue, Next, Nuxt, static sites, SPAs, dashboards, AI chat UI, 页面, 前端, 网页) needs AI models via @cloudbase/js-sdk. Default routing for Web/frontend AI — call directly from the browser, do NOT propose a Node.js proxy. Covers generateText and streamText; models via ai.createModel with groups cloudbase, hunyuan-exp, or custom-*, model id in the `model` field. MUST run two-step preflight before code — see body. NOT for Node.js backend (use ai-model-nodejs), Mini Program (use ai-model-wechat), or image generation (Node SDK only).
The English summary is being prepared. Showing the original description.