Research uncertain design choices, algorithms, or API usage through approved web searches or optional ChatGPT consultation. Get concise options with sources, with separate approval required before sending text externally and before implementing a chosen approach.
Research uncertain questions with an explicit, user-approved web search or ChatGPT consultation, then present options and wait for implementation approval.
Review the instructions the agent will receive before you install.
When implementing tasks, Claude Code can encounter uncertainties — design choices, algorithm details, API usage, or best practices. This skill provides an explicit-consent research path, presents findings, and waits for user approval before writing code.
The skill supports web research and an optional ChatGPT consultation. It never sends conversation context, files, browser state, or credentials to a third party without the user's explicit approval of the exact, redacted text.
Step 1: Propose the research boundary — State the source to use, the exact query or redacted prompt, whether any local/workspace text would leave the machine, and the likely cost. Wait for the user to approve that exact boundary.
Step 2: Research — After approval, use web search or a browser session the user has
explicitly selected and authorized. Use a pinned, user-configured browser automation
connector; do not install packages automatically, use @latest, or access browser cookies,
other tabs, saved passwords, or sessions.
Step 3: Present — Distill findings into concise options with sources, presented to the user.
Step 4: Await Approval — Do NOT write code until the user says "go ahead" or picks an option.
Step 5: Implement — Once approved, execute with confidence.
Do not treat ?, ??, or another shorthand as consent. First propose a minimal prompt,
for example: 请评估这个已脱敏的方案的正确性、完整性和可改进之处：<text>.
Explicitly identify every piece of text that would be sent. Only after the user confirms
the exact prompt may you open the selected ChatGPT session, submit that prompt, and present
the response. Do not include conversation history by default.
Redact secrets, personal data, proprietary code, customer data, and internal URLs before proposing the prompt. If safe redaction is not possible, do not submit it.
If browser automation is necessary, the user must separately authorize the selected browser profile and connector version. Restrict the session to the consultation tab. Do not inspect, reuse, export, or rely on cookies from other tabs or profiles.
User: PyTorch 中自定义 ADMM 优化器怎么设计？
Claude: 我可以搜索公开资料，或将以下已脱敏问题发给 ChatGPT：
“如何设计 PyTorch 自定义 ADMM 优化器？请比较可行模式。”
不会发送工作区文件或对话历史。是否允许？
User: 允许发送这段文字
Claude: [Opens only the authorized consultation tab, submits the approved prompt]
Claude: GPT suggests approach A with these pros/cons. Proceed?
User: 行
Claude: [Implements code]
User: ?? ADMM convergence criteria best practices
Claude: I can search public sources for the exact redacted query
“ADMM convergence criteria best practices”. No workspace files or conversation
history will be sent. May I send that text to WebSearch and fetch the results?
User: Yes, send that query
Claude: [WebSearch + WebFetch → finds Boyd et al. paper, extracts criteria]
Claude: Boyd recommends ||r|| < ε·max(||Ax||, ||Bz||, ||c||). Use this?
User: Yes
Claude: [Implements]
page.fill() for instant text injection instead of keyboard.type()| Problem | Solution |
|---|---|
| ChatGPT shows login page | Let the user log in themselves; do not handle cookies or credentials |
| The prompt contains sensitive context | Redact it or use local reasoning instead |
| Browser automation is unavailable | Use web search or stop and ask the user for a different approved method |
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Assess a new or existing AI project by examining its code, goals, and constraints. Recommend skills confirmed to exist in the available registry, then outline tasks and implementation phases with dependencies, completion criteria, and checks.
Review code and infrastructure for security risks, map potential threats, and plan stronger defenses. The skill covers OWASP checks, attack and defense exercises, and incident response, with validation required for each environment.
Turn a repeatable task into an Andru.ia skill with clear inputs, outputs, examples, and limits. Draft SKILL.md, check the folder structure and required validations, and prepare a pull request describing the changes for review.
Prepare an industry briefing once a project's sector is defined. It covers sector context, potentially applicable regulations, familiar interface patterns, technology choices, and risks, while separating verified evidence from hypotheses and questions requiring further review.
Create presentation drafts from text, outlines, or documents through the 2slides API. Match a reference image's style, choose themes, add AI voice narration, and export slide images or audio for review and use.
Plan a 360-degree or peer feedback process and create empty response templates from confirmed requirements. Produces consistent CSV, SQL, JSON Schema, or Notion property mappings while keeping visibility choices and scoring configuration separate.