[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M76JZ007DXWSXEJAPDW48G76":3,"skill-same:01M76JZ007DXWSXEJAPDW48G76":54},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M76JZ007DXWSXEJAPDW48G76","rsi-skill",null,"Evaluate a prompt, system prompt, skill instruction or agent instruction against concrete test cases, then hill-climb it to a measurably better version using any open model. Use when the user wants to test or improve a prompt, asks \"is this prompt any good\", \"make this prompt better\", \"eval this\", \"hill-climb\", \"optimize my system prompt\", or has examples of inputs with the answers they expect.","bg-szy\u002FTOP-SKILLS","bg-szy","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F106576190?v=4","01M73A4E8KPV67SFXRY8XZGNBX","ShuZhiyong","01M73A4E96MQ294MHM74TZBVQD",6,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frsi-skill\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: rsi-skill\ndescription: Evaluate a prompt, system prompt, skill instruction or agent instruction against concrete test cases, then hill-climb it to a measurably better version using any open model. Use when the user wants to test or improve a prompt, asks \"is this prompt any good\", \"make this prompt better\", \"eval this\", \"hill-climb\", \"optimize my system prompt\", or has examples of inputs with the answers they expect.\nlicense: Apache-2.0\n---\n\nImprove a piece of instruction text by measuring it, not by guessing. Score the current\nprompt on test cases, look at what fails, have a model propose a revision, keep the\nrevision only if the score goes up on cases it trained on and does not drop on cases it\nnever saw, and repeat. Everything runs through `scripts\u002Frsi.py` (Python 3 standard\nlibrary, no install).\n\nIt works on any text that steers a model: a system prompt, a classifier instruction, a\nSKILL.md body, an agent's rules, a few-shot block. It changes instructions, not weights.\n\nWorked example with real numbers: [references\u002Fexample-gsm8k.md](references\u002Fexample-gsm8k.md)\n(GSM8K, 17% to 92% on held-out problems in four rounds).\n\n## 1. Pick a model endpoint\n\nRun `python3 scripts\u002Frsi.py backend`. It uses the first of these that works:\n\n1. `--base-url URL [--api-key-env VAR] [--model M]` if the user named an endpoint.\n2. **OptiQ Cloud** when `OPTIQ_CLOUD_KEY` is set (`https:\u002F\u002Fcloud.mlx-optiq.com\u002Fapi\u002Fv1`, open models).\n3. **A local `optiq serve`** on `127.0.0.1:8080` (open models on an Apple Silicon Mac; nothing leaves the machine).\n4. Any OpenAI-compatible API via `OPENAI_BASE_URL` and `OPENAI_API_KEY`.\n\nIf none is available, the command prints how to set one up. Ask the user which they\nprefer; never invent keys. The test cases and the prompt are sent to the chosen\nendpoint, so confirm with the user before using a remote one for private data.\n\nPass `--model` when the endpoint serves several models. For reasoning models:\n`--reasoning-effort none|low|high` where the API supports it, `--no-think` for servers that\nhonour `enable_thinking`, or a larger `--max-tokens`. Empty answers are reported as such.\n\n## 2. Write the task and the cases\n\n`python3 scripts\u002Frsi.py init DIR` creates `DIR\u002Fprompt.md` and `DIR\u002Fcases.jsonl`. Put the\nuser's current prompt in `prompt.md`. Each line of `cases.jsonl` is one case:\n\n```json\n{\"input\": \"text the model receives\", \"expect\": \"what a good answer has\", \"check\": \"contains\"}\n```\n\n| check | passes when |\n|---|---|\n| `exact` | the answer equals `expect` (case, quotes and trailing punctuation ignored) |\n| `contains` | the answer contains `expect` (case-insensitive) |\n| `regex` | the answer matches the regex in `expect` |\n| `number` | the last number in the answer equals `expect` (commas, `$`, `%` ignored) |\n| `json:\u003Cfield>` | a JSON object in the answer has `field` equal to `expect` |\n| `judge` | the same model grades the answer PASS against the rubric in `expect` |\n\nPrefer the cheapest check that captures \"correct\"; use `judge` only for open-ended\nanswers. Aim for 10 to 40 cases that cover the real spread, including the hard ones the\nuser has seen fail. With fewer than 6 there is no held-out set, so say the result may\noverfit. Help the user write cases from real inputs rather than inventing them all.\n\n## 3. Measure, then climb\n\n- `python3 scripts\u002Frsi.py eval DIR` scores the current prompt and lists every failure.\n  Show the user the baseline before changing anything.\n- `python3 scripts\u002Frsi.py run DIR --rounds 5` holds 30% of the cases aside, then each round\n  asks the model to fix the failures and keeps a revision only if training cases improve\n  and held-out cases do not get worse. Revisions that quote test inputs verbatim are\n  rejected as overfitting. It stops early when every training case passes.\n- `--propose-model M` uses a stronger model on the same endpoint to write revisions.\n- Results land in `DIR\u002Fresults\u002F`: `best_prompt.md` and `history.json` (every round's\n  scores and candidate prompt).\n\n## 4. Report\n\nTell the user the baseline and final scores (train and held out), the model and endpoint,\nand show the diff between the original and the best prompt. Name any case that still\nfails and why. Apply `best_prompt.md` only after the user agrees.\n\n## Where to try it next\n\nAgent-style tasks with checkable answers make good targets. The LocalLLaMA mini\nbenchmarks on Hugging Face are small enough to iterate on:\n[typed-decisions](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002FLocalLLaMA\u002Ftyped-decisions),\n[typed-extraction](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002FLocalLLaMA\u002Ftyped-extraction),\n[browsecomp-plus-mini](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002FLocalLLaMA\u002Fbrowsecomp-plus-mini),\n[terminal-bench-mini](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002FLocalLLaMA\u002Fterminal-bench-mini) and\n[deepswe-mini](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002FLocalLLaMA\u002Fdeepswe-mini). Ask before\ndownloading a dataset.\n\n## Notes\n\n- A higher score means the prompt fits these cases better; it is only as good as the cases.\n- One run is one sample. Re-run `eval` on the best prompt to confirm before trusting it.\n","Improve a piece of instruction text by measuring it, not by guessing. Score the current\nprompt on test cases, look at what fails, have a model propose a revision, keep the\nrevision only if the score goes up on cases it trained on and does not drop on cases it\nnever saw, and repeat. Everything runs through `scripts\u002Frsi.py` (Python 3 standard\nlibrary, no install).\n\nIt works on any text that steers a model: a system prompt, a classifier instruction, a\nSKILL.md body, an agent's rules, a few-shot block. It changes instructions, not weights.\n\nWorked example with real numbers: [references\u002Fexample-gsm8k.md](references\u002Fexample-gsm8k.md)\n(GSM8K, 17% to 92% on held-out problems in four rounds).\n\n## 1. Pick a model endpoint\n\nRun `python3 scripts\u002Frsi.py backend`. It uses the first of these that works:\n\n1. `--base-url URL [--api-key-env VAR] [--model M]` if the user named an endpoint.\n2. **OptiQ Cloud** when `OPTIQ_CLOUD_KEY` is set (`https:\u002F\u002Fcloud.mlx-optiq.com\u002Fapi\u002Fv1`, open models).\n3. **A local `optiq serve`** on `127.0.0.1:8080` (open models on an Apple Silicon Mac; nothing leaves the machine).\n4. Any OpenAI-compatible API via `OPENAI_BASE_URL` and `OPENAI_API_KEY`.\n\nIf none is available, the command prints how to set one up. Ask the user which they\nprefer; never invent keys. The test cases and the prompt are sent to the chosen\nendpoint, so confirm with the user before using a remote one for private data.\n\nPass `--model` when the endpoint serves several models. For reasoning models:\n`--reasoning-effort none|low|high` where the API supports it, `--no-think` for servers that\nhonour `enable_thinking`, or a larger `--max-tokens`. Empty answers are reported as such.\n\n## 2. Write the task and the cases\n\n`python3 scripts\u002Frsi.py init DIR` creates `DIR\u002Fprompt.md` and `DIR\u002Fcases.jsonl`. Put the\nuser's current prompt in `prompt.md`. Each line of `cases.jsonl` is one case:\n\n```json\n{\"input\": \"text the model receives\", \"expect\": \"what a good answer has\", \"check\": \"contains\"}\n```\n\n| check | passes when |\n|---|---|\n| `exact` | the answer equals `expect` (case, quotes and trailing punctuation ignored) |\n| `contains` | the answer contains `expect` (case-insensitive) |\n| `regex` | the answer matches the regex in `expect` |\n| `number` | the last number in the answer equals `expect` (commas, `$`, `%` ignored) |\n| `json:\u003Cfield>` | a JSON object in the answer has `field` equal to `expect` |\n| `judge` | the same model grades the answer PASS against the rubric in `expect` |\n\nPrefer the cheapest check that captures \"correct\"; use `judge` only for open-ended\nanswers. Aim for 10 to 40 cases that cover the real spread, including the hard ones the\nuser has seen fail. With fewer than 6 there is no held-out set, so say the result may\noverfit. Help the user write cases from real inputs rather than inventing them all.\n\n## 3. Measure, then climb\n\n- `python3 scripts\u002Frsi.py eval DIR` scores the current prompt and lists every failure.\n  Show the user the baseline before changing anything.\n- `python3 scripts\u002Frsi.py run DIR --rounds 5` holds 30% of the cases aside, then each round\n  asks the model to fix the failures and keeps a revision only if training cases improve\n  and held-out cases do not get worse. Revisions that quote test inputs verbatim are\n  rejected as overfitting. It stops early when every training case passes.\n- `--propose-model M` uses a stronger model on the same endpoint to write revisions.\n- Results land in `DIR\u002Fresults\u002F`: `best_prompt.md` and `history.json` (every round's\n  scores and candidate prompt).\n\n## 4. Report\n\nTell the user the baseline and final scores (train and held out), the model and endpoint,\nand show the diff between the original and the best prompt. Name any case that still\nfails and why. Apply `best_prompt.md` only after the user agrees.\n\n## Where to try it next\n\nAgent-style tasks with checkable answers make good targets. The LocalLLaMA mini\nbenchmarks on Hugging Face are small enough to iterate on:\n[typed-decisions](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002FLocalLLaMA\u002Ftyped-decisions),\n[typed-extraction](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002FLocalLLaMA\u002Ftyped-extraction),\n[browsecomp-plus-mini](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002FLocalLLaMA\u002Fbrowsecomp-plus-mini),\n[terminal-bench-mini](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002FLocalLLaMA\u002Fterminal-bench-mini) and\n[deepswe-mini](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002FLocalLLaMA\u002Fdeepswe-mini). Ask before\ndownloading a dataset.\n\n## Notes\n\n- A higher score means the prompt fits these cases better; it is only as good as the cases.\n- One run is one sample. Re-run `eval` on the best prompt to confirm before trusting it.\n",{"name":5,"license":15,"description":7},"master","fd76f882a04e445e899d5cfb2732f2105ea054ee","skills\u002Fmarketplace\u002Frsi-skill",0,"https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS","https:\u002F\u002Fbg-szy.github.io\u002FTOP-SKILLS\u002F","https:\u002F\u002Fgithub.com\u002Fbg-szy","https:\u002F\u002Fwww.ecust.edu.cn\u002F","a student of East China University of Science and Technology","2026-11-15 03:38:02",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add bg-szy\u002FTOP-SKILLS --skill rsi-skill",{"tool":40,"command":41},"bunx","bunx skills add bg-szy\u002FTOP-SKILLS --skill rsi-skill",{"tool":43,"command":44},"pnpm","pnpm dlx skills add bg-szy\u002FTOP-SKILLS --skill rsi-skill","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frsi-skill\u002FSKILL.md",true,[48],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"skill-report.json","REFERENCE","参考文档",76948,"https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frsi-skill\u002Fskill-report.json",[55,64,71,78,85,92],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":59,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":63},"01M7DXW9N826PKXK174PVW3038","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.","MIT","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fserpmaven\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":59,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":63},"01M7DXVHSTWDV65475QEQ915M7","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.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-landing-page-audit\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":59,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":63},"01M7DXV8X2D7B3VTD4HHYYHTGR","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\u002Frevnu-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.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-growth-context\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":59,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":63},"01M7DXV0DGJ1G0A60PAHC6J3C5","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.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-get-listed\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":59,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":63},"01M7DXTSPMGT9D6DSS0HP9BSTA","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.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-ai-readiness-audit\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":59,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":63},"01M7DXSZHCVTRS620GC3S97JZV","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.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fproxy-troubleshooting\u002FSKILL.md",[],[]]