203 skills · sorted by relevance
Detects whether a task concerns software development or research and strategy by examining the request and project files. Workflow skills can use the result to choose agents, output formats, and review criteria suited to the work.
Investigate reproducible bugs by recreating symptoms, testing one possible cause at a time, and checking fixes in both a simplified test case and the original scenario. Retry limits keep unsuccessful fixes from continuing unchecked.
Test one risky assumption through a prototype with an agreed deadline, hypothesis, and success signal. Record observations and the source revision, then return a keep, discard, or inconclusive verdict with the status of each artifact.
Examine an existing plan, decision, or design through one question at a time, each with a suggested answer. Clarify assumptions, contradictions, and dependencies, then summarize agreed decisions, needed changes, and unresolved blockers.
Create a product requirements document for a new feature or product. Clarify users, problems, goals, and constraints, then organize prioritized requirements, acceptance criteria, implementation phases, and risks into a structured document for AI-assisted development.
Sort incoming issues and pull requests, verify their claims, and assign clear triage states. Record missing information, decisions needed, and actionable handoff notes so maintainers can see which items are ready for work.
Compare two to four viable approaches against your requirements and constraints. See each option’s benefits, drawbacks, effort, risk, and ease of reversal, alongside a reasoned recommendation and next steps for the option you choose.
An early-stage framework for documenting an existing product’s design and architecture. Command parsing, output setup, and metadata generation are implemented; extracting colors, components, APIs, and architecture remains in progress or planned.
Display a session dashboard showing Claude token usage, API costs, estimated savings from TLDR file summaries, cache reuse, and hook activity. Use it to compare compression results and check whether TLDR and automated hooks are running.
Investigate how an existing codebase works and document its components, connections, and file references. Combine current code findings with historical notes to produce a research document grounded in specific paths and line numbers.
Memory integrity audit. Detects hallucinations, circular confirmations, and state poisoning. Runs automatically after 2 consecutive failures or at nightly deep dive. Uses Opus 4.6 as the auditor model.
The English summary is being prepared. Showing the original description.
Analyze Claude Code and Claude Desktop Code token usage, cost, quota burn, model mix, cache read/write, and 5-hour block consumption using ccusage evidence. Use when the user asks why Claude quota was exhausted, whether a model such as fable/opus/sonnet is unusually expensive, how many tokens were spent today or historically, or needs a human-friendly explanation of local Claude Code CLI/Desktop usage.
The English summary is being prepared. Showing the original description.
Generate a prioritised compliance checklist for GDPR, SOC 2, ISO 27001, FCA, HIPAA, or other frameworks with a gap analysis. Use when asked for a compliance checklist, gap analysis, readiness assessment, or audit preparation for any regulatory framework. Produces a structured checklist with prioritised gaps, quick wins, and evidence requirements. Optimised for Opus 4.7 and newer models. Not a substitute for legal or compliance professional advice.
The English summary is being prepared. Showing the original description.
Extract pixel-level data from an image of a chart or graph and produce a structured data table. Use when asked to extract data from a chart image, transcribe numbers from a graph, digitise a chart, or turn a screenshot of data into a table. Produces a structured table with extracted values, confidence levels, and a reconstructed chart source. Best used with Claude Opus 4.7 or newer for reliable chart data extraction.
The English summary is being prepared. Showing the original description.
Use Claude Code as an independent `claude -p` subagent when the user explicitly asks for Claude, wants a second-agent opinion from Claude, or asks to delegate a well-scoped task to Claude. Supports selecting `--model` and thinking/effort level with defaults of the current `opus` alias and `high`.
The English summary is being prepared. Showing the original description.
This skill should be used when the user asks to "search for papers", "find research papers", "search arXiv", "search PubMed", "look up a DOI", "download a paper", "search IEEE", or "search Scopus".
The English summary is being prepared. Showing the original description.
Find Claude Code sessions tracked by the Agent Monitor by project (cwd), model, status, or date, then rank the matches by cost or recency. Pulls the session list and the distinct cwd / facet values so filters use real values rather than guesses. Use when locating a session — "find my EstateWise sessions", "which Opus runs errored this week", "most expensive sessions in /repo".
The English summary is being prepared. Showing the original description.
Break down Claude Code usage by model family (Opus / Sonnet / Haiku) from the Agent Monitor dashboard — each family's share of tokens, share of cost, and the spots where an expensive model is doing cheap work. Pulls per-model token and cost splits from /api/pricing/cost, current rates from /api/pricing, fleet token totals from /api/analytics, and per-session model assignment from /api/sessions. Use when deciding model routing or whether to downshift work to a cheaper tier.
The English summary is being prepared. Showing the original description.
Use when generating or handling 3D assets through the Scenario MCP server, including text-to-3D or image-to-3D meshes, GPT-6 Astra 3D or Claude Opus 5.5 3D, GLB, FBX, OBJ, STL, or VOX files, PBR-textured or game-ready models, voxel models, multi-view reconstruction, editing a mesh by prompt, retexture, remesh, UV unwrap, auto-rigging a biped or quadruped, or retargeting an animation, previewing a mesh in the 3D viewer, or downloading a model for import into Unity, Unreal, Godot, or Blender.
The English summary is being prepared. Showing the original description.
用火山引擎 Podcast AI 模型生成中文双人对话播客。当用户要把文章、报告、话题文本转成播客音频、生成对话式音频内容时使用，需要环境具备火山引擎 APP_ID 和 ACCESS_KEY。支持 mp3/ogg_opus/pcm/aac、语速调节、自定义音色、断点续传。不用于：单人朗读式 TTS（用普通语音合成）、英文播客（模型主要优化中文）、播客文稿本身的撰写（先用写作类 skill 产出文本再来）。
The English summary is being prepared. Showing the original description.
Dynamic model selection based on task complexity scoring. Replaces static model mappings with a weighted signal system that picks Opus, Sonnet, or Haiku-class speed per task. Works with agent-assignment-matrix.md.
The English summary is being prepared. Showing the original description.
Manually route a query to the optimal Claude model (Haiku/Sonnet/Opus)
The English summary is being prepared. Showing the original description.
Conducting systematic, scoping, and narrative literature reviews. Covers PRISMA/PRISMA-ScR protocols, search strategy (Boolean, MeSH), database selection (PubMed, Scopus, Web of Science, Embase), screening, data extraction, evidence synthesis (narrative, meta-analysis, thematic), and reporting. Use when planning or executing a formal literature review.
The English summary is being prepared. Showing the original description.
Auri: assistente de voz inteligente (Alexa + Claude claude-opus-4-20250805). Visao do produto, persona Vitoria Neural, stack AWS, modelo Free/Pro/Business/Enterprise, roadmap 4 fases, GTM, north star WAC e analise competitiva.
The English summary is being prepared. Showing the original description.