[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M785AJP441MT9ENREEWQY2MB":3,"skill-same:01M785AJP441MT9ENREEWQY2MB":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":33,"commitSha":34,"skillDirectory":35,"forksCount":14,"repositoryHtmlUrl":36,"repositoryHomepageUrl":6,"ownerHtmlUrl":37,"ownerBlogUrl":6,"ownerDescription":38,"updatedAt":39,"install":40,"resources":53},"01M785AJP441MT9ENREEWQY2MB","caveman",null,"Cuts low-information padding from written documents: throat-clearing openers, stacked hedges, empty transitions, nominalizations, redundant pairs, filler words. English & Indonesian. Produces professional prose with zero wasted words (latest caveman method). Use for thesis, journals, reports, DOCX\u002FPDF review. Intensity: lite, full, ultra. Ralph Wiggum loop optional. Code blocks preserved exactly for AI file generation.","freeforall1932-design\u002Fskills-repo","freeforall1932-design","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F300004558?v=4","01M7857WA4YZEAY92CZK81AS79","free for all","01M7857WAYPXNBAZFGX3FYT8FD",0,"Unlicense","https:\u002F\u002Fgithub.com\u002Ffreeforall1932-design\u002Fskills-repo\u002Fblob\u002Fmain\u002Flegacy\u002Fclaude-skills\u002Fcode\u002Fcaveman\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: caveman\ndescription: >\n  Cuts low-information padding from written documents: throat-clearing openers, stacked\n  hedges, empty transitions, nominalizations, redundant pairs, filler words. English &\n  Indonesian. Produces professional prose with zero wasted words (latest caveman method).\n  Use for thesis, journals, reports, DOCX\u002FPDF review. Intensity: lite, full, ultra.\n  Ralph Wiggum loop optional. Code blocks preserved exactly for AI file generation.\nversion: 4.0\nmode: full\ntriggers: [\"caveman\", \"be brief\", \"be concise\", \"shorten\", \"cut the fluff\", \"ringkas\"]\n---\n\n# Caveman — cut the fluff (latest method)\n\nSmall word good, if word carry meaning. Big empty phrase always bad, no matter how dressed up.\n\nThat's the spirit, not the execution. This skill does **not** produce broken grammar or clipped,\nunnatural sentences. It produces **normal, professional prose** that happens to contain zero words\nthat aren't doing work. (This is the latest official caveman method: compression without sounding\nlike a cartoon caveman.)\n\n## The deletion test\n\nFor every sentence or clause, ask: **if I delete this, does the reader lose a fact, a number,\na name, a decision, or a logical link?**\n\n- No loss → cut it, or fold what's left into the sentence next to it.\n- Real loss → keep it, exactly as precise as it was.\n\nThis test matters more than any list of banned phrases. Judge the sentence, not just the words.\n\n## Scope\n\nApply when creating or editing **documents**: thesis, papers, reports, memos, professional emails,\nproposals, summaries — anything read as a finished written artifact.\n\nDon't apply to:\n- Casual chat \u002F back-and-forth conversation (warm, natural register)\n- Emotional or supportive conversation\n- Creative writing (fiction, poetry — voice is the point)\n\nIf ambiguous, lean toward normal register. Sharpen writing, don't flatten every reply.\n\n## What to cut (English)\n\n- **Throat-clearing openers:** \"It is important to note that...\", \"This paper aims to...\", \"As we all know...\"\n- **Stacked hedges:** \"could possibly perhaps\" → \"may\"; keep at most one hedge per claim\n- **Empty transitions:** \"Moving forward,\", \"That being said,\", \"At the end of the day,\"\n- **Restated conclusions:** saying a finding, then repeating it as \"In conclusion...\"\n- **Nominalizations:** \"conduct an analysis of\" → \"analyze\"; \"make a decision on\" → \"decide\"; \"provide assistance to\" → \"help\"\n- **Vague qualifiers:** \"a significant number of\" → the actual figure, if known (never invent one)\n- **Redundant pairs:** \"each and every\", \"full and complete\", \"past history\", \"end result\", \"completely eliminate\" → one word\n- **Padding passive voice:** \"It was determined by the team that...\" → \"The team found...\" (leave passive when actor unknown or field convention)\n- **Writing-about-the-writing:** \"As mentioned previously,\", \"This section will now discuss...\"\n- **Verbal-tic intensifiers:** \"very\", \"really\", \"quite\", \"basically\", \"actually\" used as reflex; upgrade real emphasis (\"very important\" → \"critical\")\n\n## Apa yang dipotong (Bahasa Indonesia)\n\n- **Pembuka basi:** \"Perlu diketahui bahwa...\", \"Perlu dicatat bahwa...\", \"Dapat disimpulkan...\", \"Pada dasarnya...\"\n- **Hedge bertumpuk:** \"mungkin bisa jadi\", \"diduga kemungkinan besar\" → satu hedge saja\n- **Transisi kosong:** \"Ke depannya,\", \"Dengan kata lain,\", \"Pada akhirnya,\", \"Tidak perlu dikatakan lagi...\"\n- **Nominalisasi:** \"melakukan analisis terhadap\" → \"menganalisis\"; \"mengambil keputusan\" → \"memutuskan\"; \"memberikan bantuan\" → \"membantu\"\n- **Kata ganda:** \"benar-benar menghilangkan\", \"sangat penting sekali\", \"hasil akhir\", \"mulai dari awal\" → satu kata\n- **Intensifier:** \"sangat\", \"sekali\", \"sebenarnya\", \"pokoknya\" bila tanpa makna tambahan\n- **Menulis-tentang-tulisan:** \"Seperti yang telah disebutkan sebelumnya,\", \"Bagian ini akan membahas...\"\n\n## What never to cut\n\n- **Facts** — numbers, names, dates, citations, specific findings. Never invent figures.\n- **Genuine hedges** in technical, medical, legal, financial claims. \"May cause\", \"is associated with\" carry real information. When in doubt, keep the hedge.\n- **Real logical connectors** — \"because\", \"although\", \"therefore\", \"however\" (and \"tetapi\", \"karena\", \"oleh karena itu\").\n- **Required structure** — headings, citation formats, methodology sections.\n- **The author's voice** when editing someone's draft. Cut padding, don't sand off their phrasing.\n\n## Code preservation (critical for file generation)\n\nWhen the AI generates code to assemble files (Python with python-docx, R, Pandoc pipelines, etc.):\n- **Code blocks must remain byte-for-byte exact. Never compress code.**\n- Surrounding prose may be compressed; the code itself is a technical artifact, not prose.\n- Inline code, file paths, LaTeX equations, citation keys: preserved exactly.\n\n## Editing an existing document\n\n1. Work in natural chunks — paragraph by paragraph, or section by section.\n2. Apply the deletion test to each sentence.\n3. Rewrite in place, keeping original structure, terminology, and claims. Don't soften\u002Fstrengthen claims while cutting words.\n4. For review without full rewrite: flag candidates rather than silently cutting — e.g. `Cuttable: \"...\" — restates the sentence before it`.\n5. Where useful, note compression: \"142 words → 89 words\".\n\n## Drafting new text\n\n1. Write the claim or fact first; don't lead with a sentence announcing the claim.\n2. Draft, then reread once hunting for throat-clearers, hedge-stacks, nominalizations.\n3. Default to active voice and concrete nouns, unless passive carries real information.\n\n## Intensity levels\n\n| Level | What changes | Best for |\n|-------|-------------|----------|\n| **lite** | Cut obvious filler only. Full sentences. Some warmth kept. | Emails, formal reports, journal submissions |\n| **full** | Full deletion test applied. Professional prose, zero wasted words. Default. | Thesis, papers, internal documents |\n| **ultra** | Maximum density. Only when deletion test allows aggressive merging. | Summaries, token-limited contexts |\n\nAll levels produce professional prose — not broken grammar. Compression depth, not speech style, is what changes.\n\n## Ralph Wiggum loop (optional)\n\n| Command | Effect | When |\n|---------|--------|------|\n| `ralph off` | One pass. Speed. Default. | Deadlines, limited tokens |\n| `ralph once` | One verification pass after output. | Quick double-check |\n| `ralph on` | Iterative improvement until quality met. | Polish, quality focus |\n| `ralph max 3` | Maximum 3 iterations. | Limit token burn |\n\n## Auto-clarity\n\nDrop caveman when:\n- Security warnings, legal disclaimers\n- Irreversible action confirmations\n- Multi-step sequences where order matters\n- User asks to clarify or repeats question\n\nResume after the clear part.\n\n## Worked example (English)\n\n**Input (61 words):** It is important to note that, over the course of the observation period, a significant number of the shipments that were processed experienced delays which could possibly be attributed to a variety of different factors, including but not limited to handover procedures between shifts. In conclusion, it can be seen that handover procedures were found to be a major contributing factor.\n\n**Output (16 words):** Many shipments processed during the observation period were delayed, mainly due to gaps in shift-handover procedures.\n\n## Worked example (Bahasa Indonesia)\n\n**Input:** Perlu diketahui bahwa selama periode observasi, sejumlah besar pengiriman yang diproses mengalami keterlambatan yang kemungkinan besar bisa disebabkan oleh berbagai macam faktor yang berbeda, termasuk namun tidak terbatas pada prosedur serah terima antar shift. Sebagai kesimpulan, dapat dilihat bahwa prosedur serah terima merupakan faktor utama.\n\n**Output:** Banyak pengiriman selama periode observasi terlambat, terutama karena celah prosedur serah terima antar shift.\n\n## Persistence\n\nActive until \"stop caveman\" \u002F \"normal mode\". Default: full. Switch: `\u002Fcaveman lite|full|ultra`.","# Caveman — cut the fluff (latest method)\n\nSmall word good, if word carry meaning. Big empty phrase always bad, no matter how dressed up.\n\nThat's the spirit, not the execution. This skill does **not** produce broken grammar or clipped,\nunnatural sentences. It produces **normal, professional prose** that happens to contain zero words\nthat aren't doing work. (This is the latest official caveman method: compression without sounding\nlike a cartoon caveman.)\n\n## The deletion test\n\nFor every sentence or clause, ask: **if I delete this, does the reader lose a fact, a number,\na name, a decision, or a logical link?**\n\n- No loss → cut it, or fold what's left into the sentence next to it.\n- Real loss → keep it, exactly as precise as it was.\n\nThis test matters more than any list of banned phrases. Judge the sentence, not just the words.\n\n## Scope\n\nApply when creating or editing **documents**: thesis, papers, reports, memos, professional emails,\nproposals, summaries — anything read as a finished written artifact.\n\nDon't apply to:\n- Casual chat \u002F back-and-forth conversation (warm, natural register)\n- Emotional or supportive conversation\n- Creative writing (fiction, poetry — voice is the point)\n\nIf ambiguous, lean toward normal register. Sharpen writing, don't flatten every reply.\n\n## What to cut (English)\n\n- **Throat-clearing openers:** \"It is important to note that...\", \"This paper aims to...\", \"As we all know...\"\n- **Stacked hedges:** \"could possibly perhaps\" → \"may\"; keep at most one hedge per claim\n- **Empty transitions:** \"Moving forward,\", \"That being said,\", \"At the end of the day,\"\n- **Restated conclusions:** saying a finding, then repeating it as \"In conclusion...\"\n- **Nominalizations:** \"conduct an analysis of\" → \"analyze\"; \"make a decision on\" → \"decide\"; \"provide assistance to\" → \"help\"\n- **Vague qualifiers:** \"a significant number of\" → the actual figure, if known (never invent one)\n- **Redundant pairs:** \"each and every\", \"full and complete\", \"past history\", \"end result\", \"completely eliminate\" → one word\n- **Padding passive voice:** \"It was determined by the team that...\" → \"The team found...\" (leave passive when actor unknown or field convention)\n- **Writing-about-the-writing:** \"As mentioned previously,\", \"This section will now discuss...\"\n- **Verbal-tic intensifiers:** \"very\", \"really\", \"quite\", \"basically\", \"actually\" used as reflex; upgrade real emphasis (\"very important\" → \"critical\")\n\n## Apa yang dipotong (Bahasa Indonesia)\n\n- **Pembuka basi:** \"Perlu diketahui bahwa...\", \"Perlu dicatat bahwa...\", \"Dapat disimpulkan...\", \"Pada dasarnya...\"\n- **Hedge bertumpuk:** \"mungkin bisa jadi\", \"diduga kemungkinan besar\" → satu hedge saja\n- **Transisi kosong:** \"Ke depannya,\", \"Dengan kata lain,\", \"Pada akhirnya,\", \"Tidak perlu dikatakan lagi...\"\n- **Nominalisasi:** \"melakukan analisis terhadap\" → \"menganalisis\"; \"mengambil keputusan\" → \"memutuskan\"; \"memberikan bantuan\" → \"membantu\"\n- **Kata ganda:** \"benar-benar menghilangkan\", \"sangat penting sekali\", \"hasil akhir\", \"mulai dari awal\" → satu kata\n- **Intensifier:** \"sangat\", \"sekali\", \"sebenarnya\", \"pokoknya\" bila tanpa makna tambahan\n- **Menulis-tentang-tulisan:** \"Seperti yang telah disebutkan sebelumnya,\", \"Bagian ini akan membahas...\"\n\n## What never to cut\n\n- **Facts** — numbers, names, dates, citations, specific findings. Never invent figures.\n- **Genuine hedges** in technical, medical, legal, financial claims. \"May cause\", \"is associated with\" carry real information. When in doubt, keep the hedge.\n- **Real logical connectors** — \"because\", \"although\", \"therefore\", \"however\" (and \"tetapi\", \"karena\", \"oleh karena itu\").\n- **Required structure** — headings, citation formats, methodology sections.\n- **The author's voice** when editing someone's draft. Cut padding, don't sand off their phrasing.\n\n## Code preservation (critical for file generation)\n\nWhen the AI generates code to assemble files (Python with python-docx, R, Pandoc pipelines, etc.):\n- **Code blocks must remain byte-for-byte exact. Never compress code.**\n- Surrounding prose may be compressed; the code itself is a technical artifact, not prose.\n- Inline code, file paths, LaTeX equations, citation keys: preserved exactly.\n\n## Editing an existing document\n\n1. Work in natural chunks — paragraph by paragraph, or section by section.\n2. Apply the deletion test to each sentence.\n3. Rewrite in place, keeping original structure, terminology, and claims. Don't soften\u002Fstrengthen claims while cutting words.\n4. For review without full rewrite: flag candidates rather than silently cutting — e.g. `Cuttable: \"...\" — restates the sentence before it`.\n5. Where useful, note compression: \"142 words → 89 words\".\n\n## Drafting new text\n\n1. Write the claim or fact first; don't lead with a sentence announcing the claim.\n2. Draft, then reread once hunting for throat-clearers, hedge-stacks, nominalizations.\n3. Default to active voice and concrete nouns, unless passive carries real information.\n\n## Intensity levels\n\n| Level | What changes | Best for |\n|-------|-------------|----------|\n| **lite** | Cut obvious filler only. Full sentences. Some warmth kept. | Emails, formal reports, journal submissions |\n| **full** | Full deletion test applied. Professional prose, zero wasted words. Default. | Thesis, papers, internal documents |\n| **ultra** | Maximum density. Only when deletion test allows aggressive merging. | Summaries, token-limited contexts |\n\nAll levels produce professional prose — not broken grammar. Compression depth, not speech style, is what changes.\n\n## Ralph Wiggum loop (optional)\n\n| Command | Effect | When |\n|---------|--------|------|\n| `ralph off` | One pass. Speed. Default. | Deadlines, limited tokens |\n| `ralph once` | One verification pass after output. | Quick double-check |\n| `ralph on` | Iterative improvement until quality met. | Polish, quality focus |\n| `ralph max 3` | Maximum 3 iterations. | Limit token burn |\n\n## Auto-clarity\n\nDrop caveman when:\n- Security warnings, legal disclaimers\n- Irreversible action confirmations\n- Multi-step sequences where order matters\n- User asks to clarify or repeats question\n\nResume after the clear part.\n\n## Worked example (English)\n\n**Input (61 words):** It is important to note that, over the course of the observation period, a significant number of the shipments that were processed experienced delays which could possibly be attributed to a variety of different factors, including but not limited to handover procedures between shifts. In conclusion, it can be seen that handover procedures were found to be a major contributing factor.\n\n**Output (16 words):** Many shipments processed during the observation period were delayed, mainly due to gaps in shift-handover procedures.\n\n## Worked example (Bahasa Indonesia)\n\n**Input:** Perlu diketahui bahwa selama periode observasi, sejumlah besar pengiriman yang diproses mengalami keterlambatan yang kemungkinan besar bisa disebabkan oleh berbagai macam faktor yang berbeda, termasuk namun tidak terbatas pada prosedur serah terima antar shift. Sebagai kesimpulan, dapat dilihat bahwa prosedur serah terima merupakan faktor utama.\n\n**Output:** Banyak pengiriman selama periode observasi terlambat, terutama karena celah prosedur serah terima antar shift.\n\n## Persistence\n\nActive until \"stop caveman\" \u002F \"normal mode\". Default: full. Switch: `\u002Fcaveman lite|full|ultra`.",{"mode":24,"name":5,"version":25,"triggers":26,"description":32},"full",4,[5,27,28,29,30,31],"be brief","be concise","shorten","cut the fluff","ringkas","Cuts low-information padding from written documents: throat-clearing openers, stacked hedges, empty transitions, nominalizations, redundant pairs, filler words. English & Indonesian. Produces professional prose with zero wasted words (latest caveman method). Use for thesis, journals, reports, DOCX\u002FPDF review. Intensity: lite, full, ultra. Ralph Wiggum loop optional. Code blocks preserved exactly for AI file generation.\n","main","fd69413366e5700923cdaf27e816a6342375913e","legacy\u002Fclaude-skills\u002Fcode\u002Fcaveman","https:\u002F\u002Fgithub.com\u002Ffreeforall1932-design\u002Fskills-repo","https:\u002F\u002Fgithub.com\u002Ffreeforall1932-design","shipping product noone need or known for myself feel free to use it if useful","2026-11-02 13:54:04",{"source":8,"skillName":5,"commands":41,"prompt":51,"zipAvailable":52},[42,45,48],{"tool":43,"command":44},"npx","npx skills add freeforall1932-design\u002Fskills-repo --skill caveman",{"tool":46,"command":47},"bunx","bunx skills add freeforall1932-design\u002Fskills-repo --skill caveman",{"tool":49,"command":50},"pnpm","pnpm dlx skills add freeforall1932-design\u002Fskills-repo --skill caveman","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ffreeforall1932-design\u002Fskills-repo\u002Fblob\u002Fmain\u002Flegacy\u002Fclaude-skills\u002Fcode\u002Fcaveman\u002FSKILL.md",true,[],[55,63,70,77,84,91],{"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":19},"01M785QNETYHDCDXFE8AV3KFH9","web-app-penetration-testing","Pentest a web app or website end to end — black-box testing of a live URL, staging environment, or local dev server that finds and exploits real vulnerabilities (auth bypass, broken access control, IDOR, injection, XSS, SSRF, business logic) and proves each one with a working proof-of-concept instead of a signature match. Runs with Strix, either the self-hosted open-source CLI or the managed app.strix.ai cloud. Use when the user asks to pentest, hack, security-test, or audit their web app, website, web application, or staging site.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Ffreeforall1932-design\u002Fskills-repo\u002Fblob\u002Fmain\u002Fone-skill\u002Fupstream\u002Fstrix\u002Fskills\u002Fweb-app-penetration-testing\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":59,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M785QFE2RMXMRHPHE0R7M3YW","penetration-testing-with-strix","Pentest a web app, API, codebase, repository, URL, domain, or IP with Strix — autonomous AI penetration testing that exploits and proves vulnerabilities (OWASP Top 10 and beyond — injection, XSS, SSRF, auth\u002Faccess-control flaws, IDOR, business logic) instead of just flagging them. Runs self-hosted with the open-source CLI or via the managed app.strix.ai cloud, and returns validated findings with proof-of-concept exploits (Markdown, JSON, CSV, SARIF). Use when the user asks to pentest, hack, security-scan, security-audit, or find vulnerabilities in an app, API, website, or repo.","https:\u002F\u002Fgithub.com\u002Ffreeforall1932-design\u002Fskills-repo\u002Fblob\u002Fmain\u002Fone-skill\u002Fupstream\u002Fstrix\u002Fskills\u002Fpenetration-testing-with-strix\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":59,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M785Q8Y2VM6W3KJ5QK5P6VF6","owasp-top-10-testing","Test an application against the OWASP Top 10 with Strix — autonomous AI agents that attempt real exploits for each category of the current OWASP Top 10:2025 (broken access control including SSRF, security misconfiguration, software supply chain failures, cryptographic failures, injection, insecure design, authentication failures, integrity failures, logging and alerting failures, mishandling of exceptional conditions) and report only what they could actually prove, mapped back to the category with a proof-of-concept. Also covers the OWASP API Security Top 10 (2023). Use when the user asks for an OWASP Top 10 assessment, OWASP compliance testing, or a security review mapped to OWASP categories.","https:\u002F\u002Fgithub.com\u002Ffreeforall1932-design\u002Fskills-repo\u002Fblob\u002Fmain\u002Fone-skill\u002Fupstream\u002Fstrix\u002Fskills\u002Fowasp-top-10-testing\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":59,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M785Q24K39ZEYMXENVAYKPME","managed-pentesting-with-strix","Run a managed pentest of a web app, API, repository, or local workspace on the app.strix.ai platform with the `strix cloud` CLI or REST API — no local Docker or LLM key needed. Safely review and upload local source, register assets, launch and poll scans, triage vulnerabilities, export SARIF, download compliance reports, start PR reviews, buy credits, and set up schedules or webhooks. Use for managed, continuous, scheduled, team-tracked, or sandboxed-agent security testing.","https:\u002F\u002Fgithub.com\u002Ffreeforall1932-design\u002Fskills-repo\u002Fblob\u002Fmain\u002Fone-skill\u002Fupstream\u002Fstrix\u002Fskills\u002Fmanaged-pentesting-with-strix\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":59,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M785PW8EPMNN5SH43RVGHFFE","fix-security-vulnerabilities-with-strix","Fix security vulnerabilities found by a Strix pentest (open-source CLI or app.strix.ai cloud) — triage by severity, patch the root cause rather than the symptom, and re-run Strix to prove each fix actually closes the exploit. Handles injection, XSS, SSRF, broken access control, IDOR, and other validated findings. Use after a Strix scan reports findings, or when the user asks to remediate, patch, or fix security issues from a strix_runs report, vulnerabilities.json, findings.sarif, or a cloud scan.","https:\u002F\u002Fgithub.com\u002Ffreeforall1932-design\u002Fskills-repo\u002Fblob\u002Fmain\u002Fone-skill\u002Fupstream\u002Fstrix\u002Fskills\u002Ffix-security-vulnerabilities-with-strix\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":59,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M785PP7C1N489KVZYX002FEM","find-security-vulnerabilities-in-code","Find security vulnerabilities in a codebase or repository with Strix — a white-box AI security review that reads your source, reasons about the actual data flow and authorization model, then exploits what it finds in a live sandbox so every reported issue has a working proof-of-concept instead of a noisy static-analysis alert. Covers injection, XSS, SSRF, broken access control and IDOR, insecure deserialization, secrets in code, unsafe dependencies, and business-logic flaws. Use when the user asks to security-scan, security-review, or audit their code, repo, or pull request for vulnerabilities.","https:\u002F\u002Fgithub.com\u002Ffreeforall1932-design\u002Fskills-repo\u002Fblob\u002Fmain\u002Fone-skill\u002Fupstream\u002Fstrix\u002Fskills\u002Ffind-security-vulnerabilities-in-code\u002FSKILL.md",[],[]]