never-twice
Load at the start of every task and before every answer that recommends something, states a status, or says "done". It keeps a shared error log (ERRORS.md) so the same mistake never happens twice across sessions: read the log for the task's topic first, verify before claiming, think the whole plan before writing it, show real evidence before saying done, and log every new mistake with the rule that prevents it. Triggers on "no errors", "sin errores", "don't make mistakes", "get it right", "be perfect", or any task where a wrong answer costs the user time or money.
- License 许可
- MIT
- 最近更新
- 2026-11-15
- Stars
- ★ 6
- Forks
- 0
01 前言 Front Matter
- name
- never-twice
- license
- MIT
- description
- Load at the start of every task and before every answer that recommends something, states a status, or says "done". It keeps a shared error log (ERRORS.md) so the same mistake never happens twice across sessions: read the log for the task's topic first, verify before claiming, think the whole plan before writing it, show real evidence before saying done, and log every new mistake with the rule that prevents it. Triggers on "no errors", "sin errores", "don't make mistakes", "get it right", "be perfect", or any task where a wrong answer costs the user time or money.
02 资源文件 1
- 参考文档skill-report.json14.0 KB
03 SKILL.md 正文
Never twice
No method makes an agent perfect. This one gets as close as it can with three promises:
- The same mistake never happens twice.
- Nothing is claimed without checking it.
- Every answer is the final answer. No "first this, then actually that".
The error log
Keep one file that every session can read, for example ERRORS.md at the root of the workspace. One line per mistake:
- YYYY-MM-DD · TOPIC · what happened · root cause · RULE so it never happens again
Example lines:
- 2026-11-05 · UI LABELS · "Closed sales" also counted booked calls · the label did not say what it counted · RULE: every metric label says exactly what it counts.
- 2026-11-05 · STATUS SCREENS · Explained "(UNKNOWN)" as "not registered"; it was the quality rating · guessed from the screen · RULE: before explaining a field, find in the code what renders it.
Step 1. Before starting: read the mistakes for this topic
- Search the log for the task's topic (client, product, platform, tool). Every matching line is a rule for this task.
- Also read what was already decided: project notes, client files, memory.
Step 2. Verify before deciding
- Every fact you use (number, ID, price, name, status, what a field means) comes from the source: code, live page, API, file, screenshot. Never from memory.
- If a fact cannot be checked and it changes the decision, find a way to check it first. If there is none, say "not verified" once, and say how it will be known.
Step 3. Think the whole plan before writing it
For every step:
- What can go wrong? What happens if it fails? Can it be undone?
- What is the safest order? Things that break nothing go first. Irreversible things (delete, pay, publish) go last, and only if needed.
- What is the least you need from the user or their client? Ask for it all together, once.
- What is the obvious trap an expert would see?
Then write one answer: the recommendation first, then the steps, then (only if needed) what is not verified. No apologies, no "earlier I said".
Step 4. Do the work with its own method
Use the right discipline for the job: tests first for code, a diagnosis loop for bugs, a review checklist before any deliverable.
Step 5. Before saying "done": real evidence
Show the proof: the live version, the passing tests, the frames, the record read back after saving. If something could not be seen, say so. No proof, no "done".
Step 6. When a mistake happens
- Fix it.
- Add one line to the error log with its rule.
- If the rule belongs to one project, also put it in that project's notes.
- Tell the user in one line what was fixed. No long apology.
Final check (10 seconds, before every message)
- Did I read the error log for this topic?
- Is every claim checked, or marked "not verified"?
- Is this one answer I will not have to change?
- Did I show real proof for anything I call done?
04 同仓库更多 Skills
serpmaven
Scrape Google search results (SERP) to JSON with SERP Maven (serpmaven) - a real Chrome browser on a residential proxy with sticky sessions. Run it as a CLI, a Python library, a local HTTP search API (`serve`), an MCP server or a Docker image; set the proxy login, workers, pages and cost tracking. Use when the user wants Google results, rank tracking, a self-hosted SERP API, or live Google search for an AI agent.
revnu-landing-page-audit
Find out why a landing page isn't turning visitors into signups, demos or sales. Audits one page against what the ad, post or search that sends people there promised, then checks the first screen, proof, call to action, friction and mobile. Returns at most 7 prioritized fixes, plus what is fine and what could not be checked; rewrites specific lines and fixes the page in the repo when asked. Never promises a conversion lift. Works without a Revnu account. Use when the user says or asks: "audit my landing page", "why isn't this page converting", "review my homepage", "my ads get clicks but no signups", "people bounce from the pricing page", "CRO review", "improve conversion rate", "is my hero section clear", "roast my landing page", "rewrite my headline", "what's wrong with this page", "landing page feedback", "make the signup page convert better". Not for SEO or AI-search audits, page speed engineering on its own, or building a new page from scratch.
revnu-growth-context
Write down once who buys, what they're stuck on, what it costs, what proof you have and what you've already tried, so every growth task starts from facts instead of a questionnaire. Creates or updates .agents/revnu-growth.md from the repo, the live site and the user, and imports an existing product-marketing.md. Use when the user says "set up our marketing context", "who is our ideal customer", "write our ICP", "describe the product for marketing", "positioning doc", "what's our brand voice", "remember this about our customers", "log what we tried", "what have we learned from marketing", "we changed pricing, update the context", "update our growth notes", "summarize the business for the agent", "import my product-marketing.md", "start a growth doc", or before a first marketing, SEO, outreach or launch task when no context file exists. Works without a Revnu account.
revnu-get-listed
Get onto the third-party pages AI answers and search cite when buyers ask for the best tool in your category: "best X" roundups, directories, review sites, GitHub awesome lists, community threads and comparison pages. Finds which ones are cited, ranks them by fit and effort, and drafts each submission, PR or pitch by the target's own rules. Use when the user says "get us listed", "which directories should we submit to", "how do we get into best-of lists", "why does ChatGPT recommend competitors and not us", "get mentioned in AI answers", "submit to awesome lists", "get on G2", "where are our competitors listed", "pitch listicle authors", "find backlink opportunities", "launch directories", "get into roundups", "Product Hunt alternatives", "where should we be listed", "get cited by Perplexity". Never submits, pays or posts without a yes. Works without a Revnu account.
revnu-ai-readiness-audit
Audit whether your website gives ChatGPT, Perplexity, Claude, Gemini and Google's AI Overviews something worth quoting, and fix the pages that don't. Use when the user says or asks "is my site ready for AI search", "audit my site for AI answers", "AEO audit", "GEO audit", "why doesn't ChatGPT quote our pricing", "make our pages citable by AI", "do I need llms.txt", "does schema help with ChatGPT", "check our structured data", "is our content visible without JavaScript", "AI SEO audit", "optimize our homepage for AI answers", "LLM SEO check", "why does AI get our product wrong", "fix our site for AI Overviews". Checks fetchability and indexability, answers in the raw HTML, entity facts, schema (including JS-injected markup), headings, dates and llms.txt, then gives at most 10 prioritised fixes and edits the repo when asked. Works without a Revnu account.
proxy-troubleshooting
Diagnose residential proxy failures, with NodeMaven's gateway as the reference - 407 with correct credentials, 406, 410, 500, a connection that hangs, ERR_TUNNEL_CONNECTION_FAILED in a browser, Playwright or Puppeteer ignoring proxy credentials, a sticky session that changes IP, geo-targeting that is silently ignored, passwords with special characters, and unexpected traffic from headless Chrome. Use when a proxy connection fails, returns the wrong location, or costs more traffic than expected.