[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M753SYTSB0AFSAS5SBYZ07SN":3,"skill-same:01M753SYTSB0AFSAS5SBYZ07SN":49},{"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":29,"commitSha":30,"skillDirectory":5,"forksCount":14,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":33,"ownerDescription":6,"updatedAt":34,"install":35,"resources":48},"01M753SYTSB0AFSAS5SBYZ07SN","mistral-data-handling",null,"Implement Mistral AI PII handling, data retention, and GDPR\u002FCCPA compliance patterns.\nUse when handling sensitive data, implementing data redaction, configuring retention policies,\nor ensuring compliance with privacy regulations for Mistral AI integrations.\nTrigger with phrases like \"mistral data\", \"mistral PII\",\n\"mistral GDPR\", \"mistral data retention\", \"mistral privacy\", \"mistral CCPA\".","SamuelChien\u002Fmega-skills-collection","SamuelChien","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F4652114?v=4","01M74KK34WVHA0P5ZYSJRDDFMG","Samuel Chien","01M74KK35FQN1N9VZ9EPTH3P2S",0,"MIT","https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fmistral-data-handling\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: mistral-data-handling\ndescription: |\n  Implement Mistral AI PII handling, data retention, and GDPR\u002FCCPA compliance patterns.\n  Use when handling sensitive data, implementing data redaction, configuring retention policies,\n  or ensuring compliance with privacy regulations for Mistral AI integrations.\n  Trigger with phrases like \"mistral data\", \"mistral PII\",\n  \"mistral GDPR\", \"mistral data retention\", \"mistral privacy\", \"mistral CCPA\".\nallowed-tools: Read, Write, Edit\nversion: 1.0.0\nlicense: MIT\nauthor: Jeremy Longshore \u003Cjeremy@intentsolutions.io>\ncompatible-with: claude-code, codex, openclaw\n---\n# Mistral Data Handling\n\n## Overview\nManage data flows through Mistral AI APIs safely. Covers input sanitization before sending to models, response filtering, conversation history management, and fine-tuning dataset preparation with PII redaction.\n\n## Prerequisites\n- Mistral API key\n- `@mistralai\u002Fmistralai` SDK installed\n- Understanding of data classification (PII, PHI, PCI)\n- Logging infrastructure for audit trails\n\n## Instructions\n\n### Step 1: PII Redaction Before API Calls\n```typescript\ninterface RedactionRule {\n  pattern: RegExp;\n  replacement: string;\n  type: string;\n}\n\nconst PII_RULES: RedactionRule[] = [\n  { pattern: \u002F\\b[A-Z0-9._%+-]+@[A-Z0-9.-]+\\.[A-Z]{2,}\\b\u002Fgi, replacement: '[EMAIL]', type: 'email' },\n  { pattern: \u002F\\b\\d{3}[-.]?\\d{3}[-.]?\\d{4}\\b\u002Fg, replacement: '[PHONE]', type: 'phone' },\n  { pattern: \u002F\\b\\d{3}-\\d{2}-\\d{4}\\b\u002Fg, replacement: '[SSN]', type: 'ssn' },\n  { pattern: \u002F\\b\\d{4}[\\s-]?\\d{4}[\\s-]?\\d{4}[\\s-]?\\d{4}\\b\u002Fg, replacement: '[CARD]', type: 'credit_card' },\n  { pattern: \u002F\\b\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}\\b\u002Fg, replacement: '[IP]', type: 'ip_address' },\n];\n\nfunction redactPII(text: string): { cleaned: string; redactions: string[] } {\n  const redactions: string[] = [];\n  let cleaned = text;\n\n  for (const rule of PII_RULES) {\n    const matches = cleaned.match(rule.pattern);\n    if (matches) {\n      redactions.push(...matches.map(m => `${rule.type}: ${m}`));\n      cleaned = cleaned.replace(rule.pattern, rule.replacement);\n    }\n  }\n\n  return { cleaned, redactions };\n}\n```\n\n### Step 2: Safe Mistral API Wrapper\n```typescript\nimport { Mistral } from '@mistralai\u002Fmistralai';\n\nconst mistral = new Mistral({ apiKey: process.env.MISTRAL_API_KEY! });\n\nasync function safeChatCompletion(\n  messages: Array\u003C{ role: string; content: string }>,\n  options?: { redactPII?: boolean; model?: string }\n) {\n  const processedMessages = messages.map(msg => {\n    if (options?.redactPII !== false) {\n      const { cleaned, redactions } = redactPII(msg.content);\n      if (redactions.length > 0) {\n        console.warn(`Redacted ${redactions.length} PII items from ${msg.role} message`);\n      }\n      return { ...msg, content: cleaned };\n    }\n    return msg;\n  });\n\n  return mistral.chat.complete({\n    model: options?.model || 'mistral-small-latest',\n    messages: processedMessages,\n  });\n}\n```\n\n### Step 3: Fine-Tuning Dataset Sanitization\n```typescript\nimport { createReadStream, createWriteStream } from 'fs';\nimport { createInterface } from 'readline';\n\nasync function sanitizeTrainingData(\n  inputPath: string,\n  outputPath: string\n) {\n  const input = createInterface({ input: createReadStream(inputPath) });\n  const output = createWriteStream(outputPath);\n  let lineCount = 0;\n  let redactedCount = 0;\n\n  for await (const line of input) {\n    const record = JSON.parse(line);\n    const messages = record.messages.map((msg: any) => {\n      const { cleaned, redactions } = redactPII(msg.content);\n      if (redactions.length > 0) redactedCount++;\n      return { ...msg, content: cleaned };\n    });\n\n    output.write(JSON.stringify({ messages }) + '\\n');\n    lineCount++;\n  }\n\n  output.end();\n  return { lineCount, redactedCount };\n}\n```\n\n### Step 4: Conversation History with Retention\n```typescript\ninterface ConversationStore {\n  get(sessionId: string): Promise\u003Cany[]>;\n  append(sessionId: string, message: any): Promise\u003Cvoid>;\n  expire(sessionId: string): Promise\u003Cvoid>;\n}\n\nclass TimeBoundConversationStore implements ConversationStore {\n  private store = new Map\u003Cstring, { messages: any[]; createdAt: number }>();\n  private maxAgeMins: number;\n\n  constructor(maxAgeMins = 60) {\n    this.maxAgeMins = maxAgeMins;\n  }\n\n  async get(sessionId: string) {\n    const entry = this.store.get(sessionId);\n    if (!entry) return [];\n\n    const ageMs = Date.now() - entry.createdAt;\n    if (ageMs > this.maxAgeMins * 60 * 1000) {  # 1000: 1 second in ms\n      this.store.delete(sessionId);\n      return [];\n    }\n\n    return entry.messages;\n  }\n\n  async append(sessionId: string, message: any) {\n    const entry = this.store.get(sessionId) || { messages: [], createdAt: Date.now() };\n    entry.messages.push(message);\n    this.store.set(sessionId, entry);\n  }\n\n  async expire(sessionId: string) {\n    this.store.delete(sessionId);\n  }\n}\n```\n\n## Error Handling\n| Issue | Cause | Solution |\n|-------|-------|----------|\n| PII leaks to API | Regex missed pattern | Add custom rules for domain-specific PII |\n| Fine-tune rejected | Unsanitized data | Run sanitization before upload |\n| Conversation too long | No retention policy | Set max age and message count limits |\n| Audit trail gaps | No redaction logging | Log all redaction events |\n\n## Examples\n\n### Safe Embedding Generation\n```typescript\nasync function safeEmbed(texts: string[]) {\n  const cleaned = texts.map(t => redactPII(t).cleaned);\n  return mistral.embeddings.create({\n    model: 'mistral-embed',\n    inputs: cleaned,\n  });\n}\n```\n\n## Resources\n- [Mistral AI Data Policy](https:\u002F\u002Fdocs.mistral.ai\u002Fcapabilities\u002Fdata-policy\u002F)\n- [Mistral Fine-Tuning Guide](https:\u002F\u002Fdocs.mistral.ai\u002Fcapabilities\u002Ffinetuning\u002F)\n\n## Output\n\n- Configuration files or code changes applied to the project\n- Validation report confirming correct implementation\n- Summary of changes made and their rationale","# Mistral Data Handling\n\n## Overview\nManage data flows through Mistral AI APIs safely. Covers input sanitization before sending to models, response filtering, conversation history management, and fine-tuning dataset preparation with PII redaction.\n\n## Prerequisites\n- Mistral API key\n- `@mistralai\u002Fmistralai` SDK installed\n- Understanding of data classification (PII, PHI, PCI)\n- Logging infrastructure for audit trails\n\n## Instructions\n\n### Step 1: PII Redaction Before API Calls\n```typescript\ninterface RedactionRule {\n  pattern: RegExp;\n  replacement: string;\n  type: string;\n}\n\nconst PII_RULES: RedactionRule[] = [\n  { pattern: \u002F\\b[A-Z0-9._%+-]+@[A-Z0-9.-]+\\.[A-Z]{2,}\\b\u002Fgi, replacement: '[EMAIL]', type: 'email' },\n  { pattern: \u002F\\b\\d{3}[-.]?\\d{3}[-.]?\\d{4}\\b\u002Fg, replacement: '[PHONE]', type: 'phone' },\n  { pattern: \u002F\\b\\d{3}-\\d{2}-\\d{4}\\b\u002Fg, replacement: '[SSN]', type: 'ssn' },\n  { pattern: \u002F\\b\\d{4}[\\s-]?\\d{4}[\\s-]?\\d{4}[\\s-]?\\d{4}\\b\u002Fg, replacement: '[CARD]', type: 'credit_card' },\n  { pattern: \u002F\\b\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}\\b\u002Fg, replacement: '[IP]', type: 'ip_address' },\n];\n\nfunction redactPII(text: string): { cleaned: string; redactions: string[] } {\n  const redactions: string[] = [];\n  let cleaned = text;\n\n  for (const rule of PII_RULES) {\n    const matches = cleaned.match(rule.pattern);\n    if (matches) {\n      redactions.push(...matches.map(m => `${rule.type}: ${m}`));\n      cleaned = cleaned.replace(rule.pattern, rule.replacement);\n    }\n  }\n\n  return { cleaned, redactions };\n}\n```\n\n### Step 2: Safe Mistral API Wrapper\n```typescript\nimport { Mistral } from '@mistralai\u002Fmistralai';\n\nconst mistral = new Mistral({ apiKey: process.env.MISTRAL_API_KEY! });\n\nasync function safeChatCompletion(\n  messages: Array\u003C{ role: string; content: string }>,\n  options?: { redactPII?: boolean; model?: string }\n) {\n  const processedMessages = messages.map(msg => {\n    if (options?.redactPII !== false) {\n      const { cleaned, redactions } = redactPII(msg.content);\n      if (redactions.length > 0) {\n        console.warn(`Redacted ${redactions.length} PII items from ${msg.role} message`);\n      }\n      return { ...msg, content: cleaned };\n    }\n    return msg;\n  });\n\n  return mistral.chat.complete({\n    model: options?.model || 'mistral-small-latest',\n    messages: processedMessages,\n  });\n}\n```\n\n### Step 3: Fine-Tuning Dataset Sanitization\n```typescript\nimport { createReadStream, createWriteStream } from 'fs';\nimport { createInterface } from 'readline';\n\nasync function sanitizeTrainingData(\n  inputPath: string,\n  outputPath: string\n) {\n  const input = createInterface({ input: createReadStream(inputPath) });\n  const output = createWriteStream(outputPath);\n  let lineCount = 0;\n  let redactedCount = 0;\n\n  for await (const line of input) {\n    const record = JSON.parse(line);\n    const messages = record.messages.map((msg: any) => {\n      const { cleaned, redactions } = redactPII(msg.content);\n      if (redactions.length > 0) redactedCount++;\n      return { ...msg, content: cleaned };\n    });\n\n    output.write(JSON.stringify({ messages }) + '\\n');\n    lineCount++;\n  }\n\n  output.end();\n  return { lineCount, redactedCount };\n}\n```\n\n### Step 4: Conversation History with Retention\n```typescript\ninterface ConversationStore {\n  get(sessionId: string): Promise\u003Cany[]>;\n  append(sessionId: string, message: any): Promise\u003Cvoid>;\n  expire(sessionId: string): Promise\u003Cvoid>;\n}\n\nclass TimeBoundConversationStore implements ConversationStore {\n  private store = new Map\u003Cstring, { messages: any[]; createdAt: number }>();\n  private maxAgeMins: number;\n\n  constructor(maxAgeMins = 60) {\n    this.maxAgeMins = maxAgeMins;\n  }\n\n  async get(sessionId: string) {\n    const entry = this.store.get(sessionId);\n    if (!entry) return [];\n\n    const ageMs = Date.now() - entry.createdAt;\n    if (ageMs > this.maxAgeMins * 60 * 1000) {  # 1000: 1 second in ms\n      this.store.delete(sessionId);\n      return [];\n    }\n\n    return entry.messages;\n  }\n\n  async append(sessionId: string, message: any) {\n    const entry = this.store.get(sessionId) || { messages: [], createdAt: Date.now() };\n    entry.messages.push(message);\n    this.store.set(sessionId, entry);\n  }\n\n  async expire(sessionId: string) {\n    this.store.delete(sessionId);\n  }\n}\n```\n\n## Error Handling\n| Issue | Cause | Solution |\n|-------|-------|----------|\n| PII leaks to API | Regex missed pattern | Add custom rules for domain-specific PII |\n| Fine-tune rejected | Unsanitized data | Run sanitization before upload |\n| Conversation too long | No retention policy | Set max age and message count limits |\n| Audit trail gaps | No redaction logging | Log all redaction events |\n\n## Examples\n\n### Safe Embedding Generation\n```typescript\nasync function safeEmbed(texts: string[]) {\n  const cleaned = texts.map(t => redactPII(t).cleaned);\n  return mistral.embeddings.create({\n    model: 'mistral-embed',\n    inputs: cleaned,\n  });\n}\n```\n\n## Resources\n- [Mistral AI Data Policy](https:\u002F\u002Fdocs.mistral.ai\u002Fcapabilities\u002Fdata-policy\u002F)\n- [Mistral Fine-Tuning Guide](https:\u002F\u002Fdocs.mistral.ai\u002Fcapabilities\u002Ffinetuning\u002F)\n\n## Output\n\n- Configuration files or code changes applied to the project\n- Validation report confirming correct implementation\n- Summary of changes made and their rationale",{"name":5,"author":24,"license":15,"version":25,"description":26,"allowed-tools":27,"compatible-with":28},"Jeremy Longshore \u003Cjeremy@intentsolutions.io>","1.0.0","Implement Mistral AI PII handling, data retention, and GDPR\u002FCCPA compliance patterns.\nUse when handling sensitive data, implementing data redaction, configuring retention policies,\nor ensuring compliance with privacy regulations for Mistral AI integrations.\nTrigger with phrases like \"mistral data\", \"mistral PII\",\n\"mistral GDPR\", \"mistral data retention\", \"mistral privacy\", \"mistral CCPA\".\n","Read, Write, Edit","claude-code, codex, openclaw","main","c2b1fdccc779e99ac814e55fb69ca8d71215dd0f","https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection","https:\u002F\u002Fgithub.com\u002FSamuelChien","http:\u002F\u002Fsamuelchien.com\u002F","2026-05-26 08:27:14",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add SamuelChien\u002Fmega-skills-collection --skill mistral-data-handling",{"tool":41,"command":42},"bunx","bunx skills add SamuelChien\u002Fmega-skills-collection --skill mistral-data-handling",{"tool":44,"command":45},"pnpm","pnpm dlx skills add SamuelChien\u002Fmega-skills-collection --skill mistral-data-handling","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fmistral-data-handling\u002FSKILL.md",true,[],[50,57,64,71,78,86],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M76R4WZQZAXGGXMQCA0FZ716","zustand-store-ts","Create Zustand stores with TypeScript, subscribeWithSelector middleware, and proper state\u002Faction separation. Use when building React state management, creating global stores, or implementing reactive state patterns with Zustand.","https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fzustand-store-ts\u002FSKILL.md",[],[],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M76R4T9KENDH7FENGZQHBW4G","zustand-store-creator","Zustand Store Creator - Auto-activating skill for Frontend Development.\nTriggers on: zustand store creator, zustand store creator\nPart of the Frontend Development skill category.","https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fzustand-store-creator\u002FSKILL.md",[],[],{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M76R3YWN84B7SANJ52X799ZE","zero-trust-config-helper","Zero Trust Config Helper - Auto-activating skill for Security Advanced.\nTriggers on: zero trust config helper, zero trust config helper\nPart of the Security Advanced skill category.","https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fzero-trust-config-helper\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":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M76R3HNSV2AEYSKHM915GJ58","zapier-integration-helper","Zapier Integration Helper - Auto-activating skill for Business Automation.\nTriggers on: zapier integration helper, zapier integration helper\nPart of the Business Automation skill category.","https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fzapier-integration-helper\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":82,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M76R3DJSKAT4FA7DV4BF3GCE","zai-cli","Execute z.AI CLI providing vision, search, reader, and GitHub exploration via CLI and MCP.\nUse when user needs image\u002Fvideo analysis, OCR, UI-to-code conversion, error diagnosis,\nreal-time web search, web page to markdown extraction, or GitHub code exploration.\nTrigger with phrases like \"analyze this image\", \"search the web for\", \"read this page\",\n\"explore this repo\", or \"use zai\". Requires Z_AI_API_KEY.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fzai-cli\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M76R2KAM699XE9AJVAWE4H2E","yt-research","Research competitor YouTube channels, niches, and trending topics for your content strategy.\nUse this skill whenever the user says \"research channels\", \"analyze competitors\", \"find trending topics\",\n\"niche analysis\", \"competitive research\", \"what are other creators doing\", \"scrape YouTube channels\",\nor wants to understand the competitive landscape for a specific tool or topic area. Use when working with yt research. Trigger with 'yt', 'research'.","https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fyt-research\u002FSKILL.md",[],[]]