{"id":"2eec44aa-6336-4fd8-80cb-b1cb739f3700","entityType":"agent","slug":"clawhub-clarezoe-linuxdo-application","name":"linuxdo-application","canonicalUrl":"https://www.xpersona.co/agent/clawhub-clarezoe-linuxdo-application","canonicalPath":"/agent/clawhub-clarezoe-linuxdo-application","generatedAt":"2026-10-11T20:56:02.563Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T16:26:13.040Z","emptyReason":null},"description":"Craft high-pass-rate, de-AI'd Chinese applications (小作文) for Linux.do registration. Conducts an adaptive survey to learn the applicant's real background, then generates natural, rule-compliant plain text ready to paste. All user interactions in Chinese. Skill: linuxdo-application Owner: clarezoe Summary: Craft high-pass-rate, de-AI'd Chinese applications (小作文) for Linux.do registration. Conducts an adaptive survey to learn the applicant's real background, then generates natural, rule-compliant plain text ready to paste. All user interactions in Chinese. Tags: chinese:1.0.0, latest:1.0.1, linuxdo:1.0.0 Version history: v1.0.1 | 2026-06-09T13:08:53.250Z | user Normali","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s178sk484g47vwcbvvfcjpftfx8461fz:linuxdo-application","sourceUrl":"https://clawhub.ai/clarezoe/linuxdo-application","homepage":"https://clawhub.ai/clarezoe/skills/linuxdo-application","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/clarezoe/linuxdo-application","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/clarezoe/skills/linuxdo-application","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Craft high-pass-rate, de-AI'd Chinese applications (小作文) for Linux.do registration. Conducts an adaptive survey to learn the applicant's real background, then g"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T16:26:13.040Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T16:26:13.040Z","emptyReason":null},"stars":null,"forks":null,"downloads":1028,"packageName":null,"latestVersion":"1.0.1","tractionLabel":"1K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T16:26:12.969Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T16:26:13.040Z","lastCrawledAt":"2026-10-11T16:26:12.969Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T16:26:12.969Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.1","createdAt":"2026-06-09T13:08:53.250Z","changelog":"Normalize SKILL.md frontmatter for OpenClaw, Hermes, and Claude compatibility","fileCount":6,"zipByteSize":9878},{"version":"1.0.0","createdAt":"2026-04-16T11:40:15.081Z","changelog":"Initial release: adaptive survey + de-AI'd Chinese application generator for Linux.do registration","fileCount":6,"zipByteSize":9558}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s178sk484g47vwcbvvfcjpftfx8461fz:linuxdo-application","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-clarezoe-linuxdo-application/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-clarezoe-linuxdo-application/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-clarezoe-linuxdo-application/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-clarezoe-linuxdo-application/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-clarezoe-linuxdo-application/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-clarezoe-linuxdo-application/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-11T20:56:02.562Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-clarezoe-linuxdo-application/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-clarezoe-linuxdo-application/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-clarezoe-linuxdo-application/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-clarezoe-linuxdo-application/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-11T16:26:13.040Z","emptyReason":null},"readme":"Skill: linuxdo-application\n\nOwner: clarezoe\n\nSummary: Craft high-pass-rate, de-AI'd Chinese applications (小作文) for Linux.do registration. Conducts an adaptive survey to learn the applicant's real background, then generates natural, rule-compliant plain text ready to paste. All user interactions in Chinese.\n\nTags: chinese:1.0.0, latest:1.0.1, linuxdo:1.0.0\n\nVersion history:\n\nv1.0.1 | 2026-06-09T13:08:53.250Z | user\n\nNormalize SKILL.md frontmatter for OpenClaw, Hermes, and Claude compatibility\n\nv1.0.0 | 2026-04-16T11:40:15.081Z | user\n\nInitial release: adaptive survey + de-AI'd Chinese application generator for Linux.do registration\n\nArchive index:\n\nArchive v1.0.1: 6 files, 9878 bytes\n\nFiles: README.md (1547b), references/de-ai-checklist.md (2968b), references/linuxdo-rules.md (4067b), skill-card.md (2545b), SKILL.md (6308b), _meta.json (138b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: \"linuxdo-application\"\ndescription: \"Craft high-pass-rate, de-AI'd Chinese applications (小作文) for Linux.do registration. Conducts an adaptive survey to learn the applicant's real background, then generates natural, rule-compliant plain text ready to paste. All user interactions in Chinese.\"\nlicense: \"MIT\"\nmetadata: {\"openclaw\":{\"emoji\":\"📝\",\"homepage\":\"https://github.com/Fei2-Labs/skill-genie\"},\"version\":\"1.0.1\",\"category\":\"content-generation\",\"author\":\"Skill Genie\",\"license\":\"MIT\",\"language\":{\"backend\":\"English\",\"user-facing\":\"Chinese\"},\"tags\":[\"content-generation\",\"chinese-writing\",\"application-writing\",\"de-ai\"],\"hermes\":{\"tags\":[\"content-generation\",\"chinese-writing\",\"application-writing\",\"de-ai\"]}}\n---\n\n# Linux.do Application Writer\n\nGenerate a natural, high-pass-rate registration application for Linux.do through\nan adaptive interview followed by rule-aware, de-AI'd text generation.\n\n## Triggers\n\n- \"write linux.do application\"\n- \"linux.do 小作文\"\n- \"linux.do 注册申请\"\n- \"help me apply to linux.do\"\n\n## Quick Reference\n\n| Input | Output | Duration |\n|-------|--------|----------|\n| Answers to 5-8 survey questions | Plain text Chinese application (~80-150 chars) | 5-10 min |\n\n## Process\n\n### Phase 1: Applicant Survey\n\nConduct an adaptive interview in Chinese to collect the 4 required info blocks.\nAsk **one question at a time**. Adapt follow-ups based on answers.\n\n**Core questions (ask in Chinese, adapt order based on flow):**\n\n1. 你平时主要做什么？（工作、学习、兴趣方向）\n2. 你是怎么知道 Linux.do 的？（搜索、朋友推荐、看到某个帖子？）\n3. 你在上面浏览过哪些内容？有没有印象深的帖子或话题？\n4. 为什么现在想注册？有什么具体的需求或场景吗？\n5. 注册之后你打算怎么用？（潜水、回帖、关注某类话题、分享经验？）\n\n**Adaptive rules:**\n- If an answer is vague (e.g., \"想学习交流\"), probe deeper: \"具体想学什么？在哪看到过相关讨论？\"\n- If an answer already covers multiple blocks, skip redundant questions\n- If the applicant mentions a specific post/topic, ask them to elaborate — this is gold\n- Stop when all 4 info blocks are covered (see references/linuxdo-rules.md)\n\n**Verification:** Before moving to Phase 2, confirm internally:\n- [ ] Background covered (what they do/follow)\n- [ ] Discovery path covered (how they found the site)\n- [ ] Join reason covered (why register now, specific scenario)\n- [ ] Usage plan covered (what they'll do with the account)\n\nIf any block is missing, ask one more targeted question.\n\n### Phase 2: Draft Generation + Risk Check\n\nGenerate the application draft using collected info.\n\n**Generation rules:**\n1. Write in first person, casual Chinese — like telling a friend why you signed up\n2. Target 80-150 characters. Not too short (looks lazy), not too long (looks try-hard)\n3. Weave all 4 info blocks naturally — do NOT use a 4-paragraph structure\n4. Use the applicant's own words and phrasing where possible\n5. No greetings, no sign-offs, no \"你好\" or \"谢谢\" — just the substance\n6. Allow sentence fragments, colloquialisms, and imperfect grammar\n7. Vary sentence length: mix short punchy lines with longer ones\n\n**Risk check — scan the draft against these (see references/linuxdo-rules.md):**\n\n| Risk Level | Check |\n|------------|-------|\n| HIGH | Does it mention background? Discovery path? Join reason? |\n| HIGH | Is there any concrete fact, or is it all fluff? |\n| HIGH | Does it look like a template that could apply to anyone? |\n| MEDIUM | Is it only admiration/flattery without substance? |\n| MEDIUM | Is it only \"I can contribute X\" without explaining why here? |\n| MEDIUM | Is info density too low for the character count? |\n\nIf any HIGH risk is triggered, rewrite before proceeding.\n\n### Phase 3: De-AI Polish + Final Output\n\nRun the draft through the full de-AI checklist (see references/de-ai-checklist.md).\n\n**Audit steps:**\n1. Check all 12 AI markers — flag and rewrite any matches\n2. Read the text as if you're a human reviewer — does it smell like AI?\n3. Apply the 3-question smell test:\n - Could you swap details and reuse this for someone else? → too generic\n - Does every sentence add new information? → cut filler\n - Would you text this to a friend? → loosen if too formal\n\n**Output:** Present the final application as plain text in a code block.\nTell the user in Chinese: \"这是你的申请文，可以直接复制粘贴到注册页面。\"\n\nIf the user wants changes, revise and re-run Phase 3 checks.\n\n## Anti-Patterns\n\n| Avoid | Why | Instead |\n|-------|-----|---------|\n| Parallel structures (我喜欢X，我热爱Y) | AI marker #1 | Vary grammar patterns |\n| 三段式 (首先/其次/最后) | AI marker #2 | Drop scaffolding |\n| AI vocab (赋能/深耕/沉淀/赛道) | AI marker #5 | Use plain spoken Chinese |\n| Flattery (久仰大名/慕名而来) | High-risk per rules | Replace with real discovery story |\n| Generic motivation (想学习交流) | Medium-risk per rules | State specific use case |\n| Press-release tone | AI marker #9 | Add 吧/嘛/其实/反正 |\n\n## Verification\n\nAfter final output, confirm:\n\n- [ ] All 4 info blocks present\n- [ ] 80-150 characters\n- [ ] Zero high-risk patterns\n- [ ] Passes all 12 de-AI markers\n- [ ] Reads like a real person wrote it\n- [ ] Plain text, no formatting\n\n## Extension Points\n\n1. **Rule updates:** When Linux.do changes registration rules, update `references/linuxdo-rules.md`\n2. **New AI markers:** As AI detection evolves, add markers to `references/de-ai-checklist.md`\n3. **Multi-community:** Adapt the survey + rule framework for other invite-only communities\n\n## References\n\n- [Linux.do Rules & Signals](references/linuxdo-rules.md) — official rules + community patterns\n- [De-AI Checklist](references/de-ai-checklist.md) — 12 AI markers to detect and fix\n\n## Related Skills\n\n| Skill | Use When |\n|-------|----------|\n| humanizer-zh | Additional de-AI processing for Chinese text |\n| psychology-master | Deeper user profiling during survey |\n| wechat-compliance-check | Need to check Chinese content for platform compliance |\n\n**Always run `openskills list` before starting** to discover and load any relevant skills that can enhance the application writing process.\n\nFile v1.0.1:README.md\n\n# Linux.do Application Writer\n\nCraft high-pass-rate, de-AI'd Chinese applications (小作文) for Linux.do registration through an adaptive survey and rule-aware text generation.\n\n## Install\n\n**OpenClaw / ClawHub:**\n```bash\nclawhub install linuxdo-application\n```\n\n**Manual:**\n```bash\ngit clone https://github.com/Fei2-Labs/skill-genie.git\ncp -r skill-genie/linuxdo-application ~/.openclaw/skills/linuxdo-application\n```\n\n## Usage\n\nTrigger the skill with any of these phrases:\n- \"write linux.do application\"\n- \"linux.do 小作文\"\n- \"linux.do 注册申请\"\n- \"help me apply to linux.do\"\n\nThe agent will:\n1. Conduct an adaptive Chinese-language survey (5-8 questions, one at a time)\n2. Generate a draft application covering all 4 required info blocks\n3. Run a risk check and de-AI polish pass before outputting plain text\n\n## Compatibility\n\n| Agent | Compatible |\n|-------|-----------|\n| OpenClaw | Yes |\n| Hermes | Yes |\n| Claude Code | Yes |\n| Other SKILL.md agents | Yes |\n\nNo scripts or external dependencies — pure SKILL.md workflow.\n\n## File Structure\n\n```\nlinuxdo-application/\n├── SKILL.md # Main workflow\n├── README.md # This file\n└── references/\n ├── linuxdo-rules.md # Official rules + community signals\n └── de-ai-checklist.md # 12 AI markers to detect and fix\n```\n\n## License\n\nMIT\n\n---\n\n**Source**: [github.com/Fei2-Labs/skill-genie](https://github.com/Fei2-Labs/skill-genie)\n**Author**: [@clarezoe](https://x.com/clarezoe)\n\nFile v1.0.1:_meta.json\n\n{\n \"ownerId\": \"kn71ntcwxg33gv53ryabqt0vw981g9my\",\n \"slug\": \"linuxdo-application\",\n \"version\": \"1.0.1\",\n \"publishedAt\": 1781010533250\n}\n\nFile v1.0.1:references/de-ai-checklist.md\n\n# De-AI Checklist\n\n12 markers that make Chinese text sound AI-generated. The agent must audit every draft\nagainst these markers and rewrite any flagged sentences.\n\n## Detection Markers\n\n### Structural Markers\n\n| # | Marker | Example | Fix |\n|---|--------|---------|-----|\n| 1 | **Parallel sentence structures** — 3+ sentences with identical grammar pattern | 我喜欢X，我热爱Y，我追求Z | Break the pattern; vary grammar |\n| 2 | **Three-part formula (三段式)** — intro-body-conclusion with clear transitions | 首先...其次...最后 | Drop the scaffolding; just say it |\n| 3 | **Uniform sentence length** — all sentences roughly the same character count | Every sentence 15-20 chars | Mix short (5-8) with medium (15-25) |\n| 4 | **Bullet-point prose** — text reads like a formatted list without the bullets | Point 1. Point 2. Point 3. | Merge ideas into flowing text |\n\n### Vocabulary Markers\n\n| # | Marker | Example | Fix |\n|---|--------|---------|-----|\n| 5 | **AI cliché words** — 赋能、助力、深耕、沉淀、拥抱、赛道、底层逻辑、认知 | 深耕技术领域多年 | Use plain words: 做了好几年 |\n| 6 | **Excessive connectives** — 此外、与此同时、不仅如此、值得一提的是 | 此外，我还关注了... | Drop the connector; start directly |\n| 7 | **Grandiose metaphors** — 灯塔、宝藏、殿堂、星辰大海 | Linux.do 是技术人的灯塔 | Just say what it is plainly |\n| 8 | **Negation-based emphasis** — 不是X而是Y pattern repeated | 不是简单的学习，而是深度的交流 | State it directly without the contrast |\n\n### Tone Markers\n\n| # | Marker | Example | Fix |\n|---|--------|---------|-----|\n| 9 | **Over-polished tone** — no colloquialisms, no casual markers | Reads like a press release | Add 吧、嘛、其实、反正、就是 |\n| 10 | **Propaganda tone** — 共同进步、携手前行、共建生态 | 希望和大家共同进步 | Say what you'll actually do |\n| 11 | **Perfect grammar throughout** — no fragments, no run-ons | Every sentence is grammatically flawless | Allow natural imperfections |\n| 12 | **Flattery without substance** — 久仰大名、慕名而来、心向往之 | 久仰 Linux.do 大名 | Replace with how you actually found it |\n\n## Audit Process\n\n1. Read the draft sentence by sentence\n2. Flag any sentence matching 1+ markers above\n3. For each flagged sentence, rewrite using the \"Fix\" column guidance\n4. Re-read the full text aloud — does it sound like someone talking, not writing an essay?\n5. Final check: would a human reviewer think \"this person actually wrote this\"?\n\n## Quick Smell Test\n\nAsk these 3 questions about the final draft:\n- **Could you swap the applicant's details and reuse this for someone else?** If yes → too generic, rewrite.\n- **Does every sentence add new information?** If any sentence is pure filler → cut it.\n- **Would you text this to a friend?** If it feels too formal → loosen the tone.\n\nFile v1.0.1:references/linuxdo-rules.md\n\n# Linux.do Application Rules & Signals\n\nComprehensive rule set for crafting high-pass-rate Linux.do registration applications.\nSources: official announcements, FAQ, and public community experience posts.\n\n## Hard Rules (Official — Pass/Fail)\n\n### 1. Read FAQ/Guidelines First\nApplicants must read the FAQ before registering. The registration page requires checking \"已读\".\nReviewers specifically flag applications that show the applicant didn't read the rules.\n\n### 2. Self-Written Application\nThe application must be a ~50-character self-written text covering your background and why you want to join.\n\"Randomly filled\" or \"AI-generated\" applications will not pass in principle.\n\n### 3. Invited Users Are Also Reviewed\nEven with an invitation link, the same application content is required and reviewed by admins.\n\n### 4. Content Is Archived\nApplication content is not publicly displayed but is archived for future reference.\nThis means: don't treat it as throwaway text.\n\n## Content Characteristics That Increase Pass Rate\n\n### 1. Specificity > Enthusiasm\nEasy-pass applications are concrete: what you tinker with, how you found Linux.do,\nwhich topics you browsed, why you need an account, what you plan to participate in.\nFacts + path + scenario = looks like a real person.\n\n### 2. Site-Aligned Motivation\nGeneric phrases like \"want to learn\", \"want to meet experts\", \"want to grow together\"\ncarry zero information. Users report failing twice before rewriting with specific\nsite-related reasons and use cases.\n\n### 3. Show You Know What the Site Is\nIf the application reveals you don't know what's discussed on Linux.do, or you treat it\nas a generic \"resource group / tech group / beginner site\", pass rate drops.\nThis aligns with the official emphasis on \"read the intro and rules first\".\n\n### 4. \"How I'll Participate\" Is a Bonus\nCommon pattern in successful applications: not just \"I want to look around\" but\n\"I've encountered similar problems\", \"I've seen solutions on the site\",\n\"I want to reply, document, discuss X topic\". This reads like a long-term user.\n\n## Required Information Blocks (4 Blocks)\n\nEvery application should contain these 4 pieces:\n\n| Block | What to Include |\n|-------|----------------|\n| **Real Background** | What you do, what fields you follow. Doesn't need to be complete. |\n| **Discovery Path** | How you found Linux.do — search, friend, specific post, long-time lurker. |\n| **Why Register Now** | Not abstract \"want to join\" but concrete: participate in X, reply to Y, follow Z. |\n| **Account Usage Plan** | Read-only? Occasional replies? Follow specific topics? Be real and specific. |\n\n## High-Risk Patterns (Likely Rejection)\n\n| Pattern | Why It Fails |\n|---------|-------------|\n| No background/experience mentioned | Missing required info block |\n| No explanation of how you found the site | Looks random |\n| No reason for joining | Missing required info block |\n| All fluff, no concrete facts | Template-like |\n| Overly neat, uniform tone | Looks batch-generated |\n| Clearly didn't read rules | Explicitly flagged by reviewers |\n\n## Medium-Risk Patterns (Weak Signal)\n\n| Pattern | Why It's Weak |\n|---------|--------------|\n| Only admiration/thanks/praise | Zero information density |\n| Only listing your skills/contributions | Missing motivation |\n| Only learning intent, no use case | Too vague |\n| Barely over 50 chars, extremely low info density | Looks like minimum effort |\n\n## Bonus Signals (Increase Pass Rate)\n\n| Signal | Why It Helps |\n|--------|-------------|\n| Can describe how you encountered site content | Proves real exposure |\n| Mentions real topics or participation plans | Shows genuine interest |\n| Shows awareness of community rules and positioning | Aligned with official requirement |\n| Natural, non-template expression | Passes the \"human\" smell test |\n\n## Target Specs\n\n- Length: 80-150 Chinese characters (sweet spot: enough detail, not rambling)\n- Tone: casual, natural, like telling a friend why you signed up\n- Language: Chinese (Simplified)\n- Format: plain text, no markdown, no formatting\n\nFile v1.0.1:skill-card.md\n\n## Description:
\nCraft high-pass-rate, de-AI'd Chinese applications (小作文) for Linux.do registration through an adaptive survey and rule-aware text generation.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[clarezoe](https://clawhub.ai/user/clarezoe)
\n\n### License/Terms of Use:
\nMIT
\n\n\n## Use Case:
\nExternal users use this skill to answer a Chinese-language adaptive survey and draft a concise Linux.do registration application based on their real background, discovery path, reason for joining, and intended account use.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: The skill can make AI-assisted registration text appear self-written for an access-controlled community.
\nMitigation: Use it only when AI assistance is allowed by the community, and disclose or avoid AI assistance when the registration process expects unaided self-written text.
\nRisk: The generated application could include fabricated or over-polished personal background details.
\nMitigation: Base answers only on the applicant's truthful background, discovery path, join reason, and intended account use; remove any invented claims before submission.
\nRisk: The workflow asks for personal background and account-intent details.
\nMitigation: Provide only minimal information needed for the application and avoid sensitive personal data.
\n\n\n## Reference(s):
\n- [ClawHub skill page](https://clawhub.ai/clarezoe/linuxdo-application)
\n- [Publisher profile](https://clawhub.ai/user/clarezoe)
\n- [Project homepage](https://github.com/Fei2-Labs/skill-genie)
\n- [Linux.do Rules & Signals](references/linuxdo-rules.md)
\n- [De-AI Checklist](references/de-ai-checklist.md)
\n\n\n## Skill Output:
\n**Output Type(s):** [Text, Markdown, Guidance]
\n**Output Format:** [Chinese plain text application draft in a Markdown code block, with brief Chinese user-facing guidance]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [Targets an 80-150 Chinese character application after survey, risk check, and de-AI review.]
\n\n## Skill Version(s):
\n1.0.1 (source: frontmatter and server release metadata)
\n\n## Ethical Considerations:
\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.
\n\nArchive v1.0.0: 6 files, 9558 bytes\n\nFiles: README.md (1403b), references/de-ai-checklist.md (2968b), references/linuxdo-rules.md (4067b), skill-card.md (2178b), SKILL.md (6002b), _meta.json (138b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: linuxdo-application\ndescription: >\n Craft high-pass-rate, de-AI'd Chinese applications (小作文) for Linux.do registration.\n Conducts an adaptive survey to learn the applicant's real background, then generates\n natural, rule-compliant plain text ready to paste. All user interactions in Chinese.\nmetadata:\n openclaw:\n emoji: \"📝\"\n homepage: \"https://github.com/Fei2-Labs/skill-genie\"\n version: \"1.0.0\"\n category: \"content-generation\"\n author: \"Skill Genie\"\n license: \"MIT\"\n language:\n backend: English\n user-facing: Chinese\n---\n\n# Linux.do Application Writer\n\nGenerate a natural, high-pass-rate registration application for Linux.do through\nan adaptive interview followed by rule-aware, de-AI'd text generation.\n\n## Triggers\n\n- \"write linux.do application\"\n- \"linux.do 小作文\"\n- \"linux.do 注册申请\"\n- \"help me apply to linux.do\"\n\n## Quick Reference\n\n| Input | Output | Duration |\n|-------|--------|----------|\n| Answers to 5-8 survey questions | Plain text Chinese application (~80-150 chars) | 5-10 min |\n\n## Process\n\n### Phase 1: Applicant Survey\n\nConduct an adaptive interview in Chinese to collect the 4 required info blocks.\nAsk **one question at a time**. Adapt follow-ups based on answers.\n\n**Core questions (ask in Chinese, adapt order based on flow):**\n\n1. 你平时主要做什么？（工作、学习、兴趣方向）\n2. 你是怎么知道 Linux.do 的？（搜索、朋友推荐、看到某个帖子？）\n3. 你在上面浏览过哪些内容？有没有印象深的帖子或话题？\n4. 为什么现在想注册？有什么具体的需求或场景吗？\n5. 注册之后你打算怎么用？（潜水、回帖、关注某类话题、分享经验？）\n\n**Adaptive rules:**\n- If an answer is vague (e.g., \"想学习交流\"), probe deeper: \"具体想学什么？在哪看到过相关讨论？\"\n- If an answer already covers multiple blocks, skip redundant questions\n- If the applicant mentions a specific post/topic, ask them to elaborate — this is gold\n- Stop when all 4 info blocks are covered (see references/linuxdo-rules.md)\n\n**Verification:** Before moving to Phase 2, confirm internally:\n- [ ] Background covered (what they do/follow)\n- [ ] Discovery path covered (how they found the site)\n- [ ] Join reason covered (why register now, specific scenario)\n- [ ] Usage plan covered (what they'll do with the account)\n\nIf any block is missing, ask one more targeted question.\n\n### Phase 2: Draft Generation + Risk Check\n\nGenerate the application draft using collected info.\n\n**Generation rules:**\n1. Write in first person, casual Chinese — like telling a friend why you signed up\n2. Target 80-150 characters. Not too short (looks lazy), not too long (looks try-hard)\n3. Weave all 4 info blocks naturally — do NOT use a 4-paragraph structure\n4. Use the applicant's own words and phrasing where possible\n5. No greetings, no sign-offs, no \"你好\" or \"谢谢\" — just the substance\n6. Allow sentence fragments, colloquialisms, and imperfect grammar\n7. Vary sentence length: mix short punchy lines with longer ones\n\n**Risk check — scan the draft against these (see references/linuxdo-rules.md):**\n\n| Risk Level | Check |\n|------------|-------|\n| HIGH | Does it mention background? Discovery path? Join reason? |\n| HIGH | Is there any concrete fact, or is it all fluff? |\n| HIGH | Does it look like a template that could apply to anyone? |\n| MEDIUM | Is it only admiration/flattery without substance? |\n| MEDIUM | Is it only \"I can contribute X\" without explaining why here? |\n| MEDIUM | Is info density too low for the character count? |\n\nIf any HIGH risk is triggered, rewrite before proceeding.\n\n### Phase 3: De-AI Polish + Final Output\n\nRun the draft through the full de-AI checklist (see references/de-ai-checklist.md).\n\n**Audit steps:**\n1. Check all 12 AI markers — flag and rewrite any matches\n2. Read the text as if you're a human reviewer — does it smell like AI?\n3. Apply the 3-question smell test:\n - Could you swap details and reuse this for someone else? → too generic\n - Does every sentence add new information? → cut filler\n - Would you text this to a friend? → loosen if too formal\n\n**Output:** Present the final application as plain text in a code block.\nTell the user in Chinese: \"这是你的申请文，可以直接复制粘贴到注册页面。\"\n\nIf the user wants changes, revise and re-run Phase 3 checks.\n\n## Anti-Patterns\n\n| Avoid | Why | Instead |\n|-------|-----|---------|\n| Parallel structures (我喜欢X，我热爱Y) | AI marker #1 | Vary grammar patterns |\n| 三段式 (首先/其次/最后) | AI marker #2 | Drop scaffolding |\n| AI vocab (赋能/深耕/沉淀/赛道) | AI marker #5 | Use plain spoken Chinese |\n| Flattery (久仰大名/慕名而来) | High-risk per rules | Replace with real discovery story |\n| Generic motivation (想学习交流) | Medium-risk per rules | State specific use case |\n| Press-release tone | AI marker #9 | Add 吧/嘛/其实/反正 |\n\n## Verification\n\nAfter final output, confirm:\n\n- [ ] All 4 info blocks present\n- [ ] 80-150 characters\n- [ ] Zero high-risk patterns\n- [ ] Passes all 12 de-AI markers\n- [ ] Reads like a real person wrote it\n- [ ] Plain text, no formatting\n\n## Extension Points\n\n1. **Rule updates:** When Linux.do changes registration rules, update `references/linuxdo-rules.md`\n2. **New AI markers:** As AI detection evolves, add markers to `references/de-ai-checklist.md`\n3. **Multi-community:** Adapt the survey + rule framework for other invite-only communities\n\n## References\n\n- [Linux.do Rules & Signals](references/linuxdo-rules.md) — official rules + community patterns\n- [De-AI Checklist](references/de-ai-checklist.md) — 12 AI markers to detect and fix\n\n## Related Skills\n\n| Skill | Use When |\n|-------|----------|\n| wechat-compliance-check | Need to check Chinese content for platform compliance |\n| psychology-master | Need deeper user profiling during survey |\n| humanizer-zh | Additional de-AI processing for Chinese text |\n\nFile v1.0.0:README.md\n\n# Linux.do Application Writer\n\nCraft high-pass-rate, de-AI'd Chinese applications (小作文) for Linux.do registration through an adaptive survey and rule-aware text generation.\n\n## Install\n\n**OpenClaw / ClawHub:**\n```bash\nclawhub install linuxdo-application\n```\n\n**Manual:**\n```bash\ngit clone https://github.com/Fei2-Labs/skill-genie.git\ncp -r skill-genie/linuxdo-application ~/.openclaw/skills/linuxdo-application\n```\n\n## Usage\n\nTrigger the skill with any of these phrases:\n- \"write linux.do application\"\n- \"linux.do 小作文\"\n- \"linux.do 注册申请\"\n- \"help me apply to linux.do\"\n\nThe agent will:\n1. Conduct an adaptive Chinese-language survey (5-8 questions, one at a time)\n2. Generate a draft application covering all 4 required info blocks\n3. Run a risk check and de-AI polish pass before outputting plain text\n\n## Compatibility\n\n| Agent | Compatible |\n|-------|-----------|\n| OpenClaw | Yes |\n| Hermes | Yes |\n| Claude Code | Yes |\n| Other SKILL.md agents | Yes |\n\nNo scripts or external dependencies — pure SKILL.md workflow.\n\n## File Structure\n\n```\nlinuxdo-application/\n├── SKILL.md # Main workflow\n├── README.md # This file\n└── references/\n ├── linuxdo-rules.md # Official rules + community signals\n └── de-ai-checklist.md # 12 AI markers to detect and fix\n```\n\n## License\n\nMIT\n\nFile v1.0.0:_meta.json\n\n{\n \"ownerId\": \"kn71ntcwxg33gv53ryabqt0vw981g9my\",\n \"slug\": \"linuxdo-application\",\n \"version\": \"1.0.0\",\n \"publishedAt\": 1776339615081\n}\n\nFile v1.0.0:references/de-ai-checklist.md\n\n# De-AI Checklist\n\n12 markers that make Chinese text sound AI-generated. The agent must audit every draft\nagainst these markers and rewrite any flagged sentences.\n\n## Detection Markers\n\n### Structural Markers\n\n| # | Marker | Example | Fix |\n|---|--------|---------|-----|\n| 1 | **Parallel sentence structures** — 3+ sentences with identical grammar pattern | 我喜欢X，我热爱Y，我追求Z | Break the pattern; vary grammar |\n| 2 | **Three-part formula (三段式)** — intro-body-conclusion with clear transitions | 首先...其次...最后 | Drop the scaffolding; just say it |\n| 3 | **Uniform sentence length** — all sentences roughly the same character count | Every sentence 15-20 chars | Mix short (5-8) with medium (15-25) |\n| 4 | **Bullet-point prose** — text reads like a formatted list without the bullets | Point 1. Point 2. Point 3. | Merge ideas into flowing text |\n\n### Vocabulary Markers\n\n| # | Marker | Example | Fix |\n|---|--------|---------|-----|\n| 5 | **AI cliché words** — 赋能、助力、深耕、沉淀、拥抱、赛道、底层逻辑、认知 | 深耕技术领域多年 | Use plain words: 做了好几年 |\n| 6 | **Excessive connectives** — 此外、与此同时、不仅如此、值得一提的是 | 此外，我还关注了... | Drop the connector; start directly |\n| 7 | **Grandiose metaphors** — 灯塔、宝藏、殿堂、星辰大海 | Linux.do 是技术人的灯塔 | Just say what it is plainly |\n| 8 | **Negation-based emphasis** — 不是X而是Y pattern repeated | 不是简单的学习，而是深度的交流 | State it directly without the contrast |\n\n### Tone Markers\n\n| # | Marker | Example | Fix |\n|---|--------|---------|-----|\n| 9 | **Over-polished tone** — no colloquialisms, no casual markers | Reads like a press release | Add 吧、嘛、其实、反正、就是 |\n| 10 | **Propaganda tone** — 共同进步、携手前行、共建生态 | 希望和大家共同进步 | Say what you'll actually do |\n| 11 | **Perfect grammar throughout** — no fragments, no run-ons | Every sentence is grammatically flawless | Allow natural imperfections |\n| 12 | **Flattery without substance** — 久仰大名、慕名而来、心向往之 | 久仰 Linux.do 大名 | Replace with how you actually found it |\n\n## Audit Process\n\n1. Read the draft sentence by sentence\n2. Flag any sentence matching 1+ markers above\n3. For each flagged sentence, rewrite using the \"Fix\" column guidance\n4. Re-read the full text aloud — does it sound like someone talking, not writing an essay?\n5. Final check: would a human reviewer think \"this person actually wrote this\"?\n\n## Quick Smell Test\n\nAsk these 3 questions about the final draft:\n- **Could you swap the applicant's details and reuse this for someone else?** If yes → too generic, rewrite.\n- **Does every sentence add new information?** If any sentence is pure filler → cut it.\n- **Would you text this to a friend?** If it feels too formal → loosen the tone.\n\nFile v1.0.0:references/linuxdo-rules.md\n\n# Linux.do Application Rules & Signals\n\nComprehensive rule set for crafting high-pass-rate Linux.do registration applications.\nSources: official announcements, FAQ, and public community experience posts.\n\n## Hard Rules (Official — Pass/Fail)\n\n### 1. Read FAQ/Guidelines First\nApplicants must read the FAQ before registering. The registration page requires checking \"已读\".\nReviewers specifically flag applications that show the applicant didn't read the rules.\n\n### 2. Self-Written Application\nThe application must be a ~50-character self-written text covering your background and why you want to join.\n\"Randomly filled\" or \"AI-generated\" applications will not pass in principle.\n\n### 3. Invited Users Are Also Reviewed\nEven with an invitation link, the same application content is required and reviewed by admins.\n\n### 4. Content Is Archived\nApplication content is not publicly displayed but is archived for future reference.\nThis means: don't treat it as throwaway text.\n\n## Content Characteristics That Increase Pass Rate\n\n### 1. Specificity > Enthusiasm\nEasy-pass applications are concrete: what you tinker with, how you found Linux.do,\nwhich topics you browsed, why you need an account, what you plan to participate in.\nFacts + path + scenario = looks like a real person.\n\n### 2. Site-Aligned Motivation\nGeneric phrases like \"want to learn\", \"want to meet experts\", \"want to grow together\"\ncarry zero information. Users report failing twice before rewriting with specific\nsite-related reasons and use cases.\n\n### 3. Show You Know What the Site Is\nIf the application reveals you don't know what's discussed on Linux.do, or you treat it\nas a generic \"resource group / tech group / beginner site\", pass rate drops.\nThis aligns with the official emphasis on \"read the intro and rules first\".\n\n### 4. \"How I'll Participate\" Is a Bonus\nCommon pattern in successful applications: not just \"I want to look around\" but\n\"I've encountered similar problems\", \"I've seen solutions on the site\",\n\"I want to reply, document, discuss X topic\". This reads like a long-term user.\n\n## Required Information Blocks (4 Blocks)\n\nEvery application should contain these 4 pieces:\n\n| Block | What to Include |\n|-------|----------------|\n| **Real Background** | What you do, what fields you follow. Doesn't need to be complete. |\n| **Discovery Path** | How you found Linux.do — search, friend, specific post, long-time lurker. |\n| **Why Register Now** | Not abstract \"want to join\" but concrete: participate in X, reply to Y, follow Z. |\n| **Account Usage Plan** | Read-only? Occasional replies? Follow specific topics? Be real and specific. |\n\n## High-Risk Patterns (Likely Rejection)\n\n| Pattern | Why It Fails |\n|---------|-------------|\n| No background/experience mentioned | Missing required info block |\n| No explanation of how you found the site | Looks random |\n| No reason for joining | Missing required info block |\n| All fluff, no concrete facts | Template-like |\n| Overly neat, uniform tone | Looks batch-generated |\n| Clearly didn't read rules | Explicitly flagged by reviewers |\n\n## Medium-Risk Patterns (Weak Signal)\n\n| Pattern | Why It's Weak |\n|---------|--------------|\n| Only admiration/thanks/praise | Zero information density |\n| Only listing your skills/contributions | Missing motivation |\n| Only learning intent, no use case | Too vague |\n| Barely over 50 chars, extremely low info density | Looks like minimum effort |\n\n## Bonus Signals (Increase Pass Rate)\n\n| Signal | Why It Helps |\n|--------|-------------|\n| Can describe how you encountered site content | Proves real exposure |\n| Mentions real topics or participation plans | Shows genuine interest |\n| Shows awareness of community rules and positioning | Aligned with official requirement |\n| Natural, non-template expression | Passes the \"human\" smell test |\n\n## Target Specs\n\n- Length: 80-150 Chinese characters (sweet spot: enough detail, not rambling)\n- Tone: casual, natural, like telling a friend why you signed up\n- Language: Chinese (Simplified)\n- Format: plain text, no markdown, no formatting\n\nFile v1.0.0:skill-card.md\n\n## Description:
\nCrafts Chinese Linux.do registration applications by interviewing the applicant, drafting rule-aware text, and polishing it to sound self-written.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[clarezoe](https://clawhub.ai/user/clarezoe)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nExternal users use this agent skill to answer an adaptive Chinese-language survey and produce a concise Linux.do registration application based on their own background, discovery path, reason for joining, and intended account use.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: The skill may help bypass Linux.do's intended application review by generating text that appears self-written.
\nMitigation: Use only truthful applicant-provided information and do not submit AI-generated text where the site requires self-written applications.
\nRisk: The adaptive survey can collect sensitive personal background or account-use details.
\nMitigation: Share only the minimum information needed for the application and avoid sensitive personal details.
\n\n\n## Reference(s):
\n- [Linux.do Rules & Signals](references/linuxdo-rules.md)
\n- [De-AI Checklist](references/de-ai-checklist.md)
\n- [Project homepage](https://github.com/Fei2-Labs/skill-genie)
\n- [ClawHub skill page](https://clawhub.ai/clarezoe/linuxdo-application)
\n\n\n## Skill Output:
\n**Output Type(s):** [text, markdown, guidance]
\n**Output Format:** [Markdown response with final plain-text Chinese application in a code block]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [Final application target length is 80-150 Chinese characters after risk and de-AI checks.]
\n\n## Skill Version(s):
\n1.0.0 (source: release metadata and skill metadata)
\n\n## Ethical Considerations:
\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.
","readmeExcerpt":"Skill: linuxdo-application Owner: clarezoe Summary: Craft high-pass-rate, de-AI'd Chinese applications (小作文) for Linux.do registration. Conducts an adaptive survey to learn the applicant's real background, then generates natural, rule-compliant plain text ready to paste. All user interactions in Chinese. Tags: chinese:1.0.0, latest:1.0.1, linuxdo:1.0.0 Version history: v1.0.1 | 2026-06-09T13:08:53.250Z | user Normali","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"clawhub install linuxdo-application"},{"language":"bash","snippet":"git clone https://github.com/Fei2-Labs/skill-genie.git\ncp -r skill-genie/linuxdo-application ~/.openclaw/skills/linuxdo-application"},{"language":"text","snippet":"linuxdo-application/\n├── SKILL.md # Main workflow\n├── README.md # This file\n└── references/\n ├── linuxdo-rules.md # Official rules + community signals\n └── de-ai-checklist.md # 12 AI markers to detect and fix"},{"language":"bash","snippet":"clawhub install linuxdo-application"},{"language":"bash","snippet":"git clone https://github.com/Fei2-Labs/skill-genie.git\ncp -r skill-genie/linuxdo-application ~/.openclaw/skills/linuxdo-application"},{"language":"text","snippet":"linuxdo-application/\n├── SKILL.md # Main workflow\n├── README.md # This file\n└── references/\n ├── linuxdo-rules.md # Official rules + community signals\n └── de-ai-checklist.md # 12 AI markers to detect and fix"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: \"linuxdo-application\"\ndescription: \"Craft high-pass-rate, de-AI'd Chinese applications (小作文) for Linux.do registration. Conducts an adaptive survey to learn the applicant's real background, then generates natural, rule-compliant plain text ready to paste. All user interactions in Chinese.\"\nlicense: \"MIT\"\nmetadata: {\"openclaw\":{\"emoji\":\"📝\",\"homepage\":\"https://github.com/Fei2-Labs/skill-genie\"},\"version\":\"1.0.1\",\"category\":\"content-generation\",\"author\":\"Skill Genie\",\"license\":\"MIT\",\"language\":{\"backend\":\"English\",\"user-facing\":\"Chinese\"},\"tags\":[\"content-generation\",\"chinese-writing\",\"application-writing\",\"de-ai\"],\"hermes\":{\"tags\":[\"content-generation\",\"chinese-writing\",\"application-writing\",\"de-ai\"]}}\n---\n\n# Linux.do Application Writer\n\nGenerate a natural, high-pass-rate registration application for Linux.do through\nan adaptive interview followed by rule-aware, de-AI'd text generation.\n\n## Triggers\n\n- \"write linux.do application\"\n- \"linux.do 小作文\"\n- \"linux.do 注册申请\"\n- \"help me apply to linux.do\"\n\n## Quick Reference\n\n| Input | Output | Duration |\n|-------|--------|----------|\n| Answers to 5-8 survey questions | Plain text Chinese application (~80-150 chars) | 5-10 min |\n\n## Process\n\n### Phase 1: Applicant Survey\n\nConduct an adaptive interview in Chinese to collect the 4 required info blocks.\nAsk **one question at a time**. Adapt follow-ups based on answers.\n\n**Core questions (ask in Chinese, adapt order based on flow):**\n\n1. 你平时主要做什么？（工作、学习、兴趣方向）\n2. 你是怎么知道 Linux.do 的？（搜索、朋友推荐、看到某个帖子？）\n3. 你在上面浏览过哪些内容？有没有印象深的帖子或话题？\n4. 为什么现在想注册？有什么具体的需求或场景吗？\n5. 注册之后你打算怎么用？（潜水、回帖、关注某类话题、分享经验？）\n\n**Adaptive rules:**\n- If an answer is vague (e.g., \"想学习交流\"), probe deeper: \"具体想学什么？在哪看到过相关讨论？\"\n- If an answer already covers multiple blocks, skip redundant questions\n- If the applicant mentions a specific post/topic, ask them to elaborate — this is gold\n- Stop when all 4 info blocks are covered (see references/linuxdo-rules.md)\n\n**Verification:** Before moving to Phase 2, confirm internally:\n- [ ] Background covered (what they do/follow)\n- [ ] Discovery path covered (how they found the site)\n- [ ] Join reason covered (why register now, specific scenario)\n- [ ] Usage plan covered (what they'll do with the account)\n\nIf any block is missing, ask one more targeted question.\n\n### Phase 2: Draft Generation + Risk Check\n\nGenerate the application draft using collected info.\n\n**Generation rules:**\n1. Write in first person, casual Chinese — like telling a friend why you signed up\n2. Target 80-150 characters. Not too short (looks lazy), not too long (looks try-hard)\n3. Weave all 4 info blocks naturally — do NOT use a 4-paragraph structure\n4. Use the applicant's own words and phrasing where possible\n5. No greetings, no sign-offs, no \"你好\" or \"谢谢\" — just the substance\n6. Allow sentence fragments, colloquialisms, and imperfect grammar\n7. Vary sentence length: mix short punchy lines with longer ones\n\n**Risk check — scan the draft against these (see references/linuxdo-rules.md):**\n\n| R"},{"path":"README.md","content":"# Linux.do Application Writer\n\nCraft high-pass-rate, de-AI'd Chinese applications (小作文) for Linux.do registration through an adaptive survey and rule-aware text generation.\n\n## Install\n\n**OpenClaw / ClawHub:**\n```bash\nclawhub install linuxdo-application\n```\n\n**Manual:**\n```bash\ngit clone https://github.com/Fei2-Labs/skill-genie.git\ncp -r skill-genie/linuxdo-application ~/.openclaw/skills/linuxdo-application\n```\n\n## Usage\n\nTrigger the skill with any of these phrases:\n- \"write linux.do application\"\n- \"linux.do 小作文\"\n- \"linux.do 注册申请\"\n- \"help me apply to linux.do\"\n\nThe agent will:\n1. Conduct an adaptive Chinese-language survey (5-8 questions, one at a time)\n2. Generate a draft application covering all 4 required info blocks\n3. Run a risk check and de-AI polish pass before outputting plain text\n\n## Compatibility\n\n| Agent | Compatible |\n|-------|-----------|\n| OpenClaw | Yes |\n| Hermes | Yes |\n| Claude Code | Yes |\n| Other SKILL.md agents | Yes |\n\nNo scripts or external dependencies — pure SKILL.md workflow.\n\n## File Structure\n\n```\nlinuxdo-application/\n├── SKILL.md # Main workflow\n├── README.md # This file\n└── references/\n ├── linuxdo-rules.md # Official rules + community signals\n └── de-ai-checklist.md # 12 AI markers to detect and fix\n```\n\n## License\n\nMIT\n\n---\n\n**Source**: [github.com/Fei2-Labs/skill-genie](https://github.com/Fei2-Labs/skill-genie)\n**Author**: [@clarezoe](https://x.com/clarezoe)"},{"path":"_meta.json","content":"{\n \"ownerId\": \"kn71ntcwxg33gv53ryabqt0vw981g9my\",\n \"slug\": \"linuxdo-application\",\n \"version\": \"1.0.1\",\n \"publishedAt\": 1781010533250\n}"},{"path":"references/de-ai-checklist.md","content":"# De-AI Checklist\n\n12 markers that make Chinese text sound AI-generated. The agent must audit every draft\nagainst these markers and rewrite any flagged sentences.\n\n## Detection Markers\n\n### Structural Markers\n\n| # | Marker | Example | Fix |\n|---|--------|---------|-----|\n| 1 | **Parallel sentence structures** — 3+ sentences with identical grammar pattern | 我喜欢X，我热爱Y，我追求Z | Break the pattern; vary grammar |\n| 2 | **Three-part formula (三段式)** — intro-body-conclusion with clear transitions | 首先...其次...最后 | Drop the scaffolding; just say it |\n| 3 | **Uniform sentence length** — all sentences roughly the same character count | Every sentence 15-20 chars | Mix short (5-8) with medium (15-25) |\n| 4 | **Bullet-point prose** — text reads like a formatted list without the bullets | Point 1. Point 2. Point 3. | Merge ideas into flowing text |\n\n### Vocabulary Markers\n\n| # | Marker | Example | Fix |\n|---|--------|---------|-----|\n| 5 | **AI cliché words** — 赋能、助力、深耕、沉淀、拥抱、赛道、底层逻辑、认知 | 深耕技术领域多年 | Use plain words: 做了好几年 |\n| 6 | **Excessive connectives** — 此外、与此同时、不仅如此、值得一提的是 | 此外，我还关注了... | Drop the connector; start directly |\n| 7 | **Grandiose metaphors** — 灯塔、宝藏、殿堂、星辰大海 | Linux.do 是技术人的灯塔 | Just say what it is plainly |\n| 8 | **Negation-based emphasis** — 不是X而是Y pattern repeated | 不是简单的学习，而是深度的交流 | State it directly without the contrast |\n\n### Tone Markers\n\n| # | Marker | Example | Fix |\n|---|--------|---------|-----|\n| 9 | **Over-polished tone** — no colloquialisms, no casual markers | Reads like a press release | Add 吧、嘛、其实、反正、就是 |\n| 10 | **Propaganda tone** — 共同进步、携手前行、共建生态 | 希望和大家共同进步 | Say what you'll actually do |\n| 11 | **Perfect grammar throughout** — no fragments, no run-ons | Every sentence is grammatically flawless | Allow natural imperfections |\n| 12 | **Flattery without substance** — 久仰大名、慕名而来、心向往之 | 久仰 Linux.do 大名 | Replace with how you actually found it |\n\n## Audit Process\n\n1. Read the draft sentence by sentence\n2. Flag any sentence matching 1+ markers above\n3. For each flagged sentence, rewrite using the \"Fix\" column guidance\n4. Re-read the full text aloud — does it sound like someone talking, not writing an essay?\n5. Final check: would a human reviewer think \"this person actually wrote this\"?\n\n## Quick Smell Test\n\nAsk these 3 questions about the final draft:\n- **Could you swap the applicant's details and reuse this for someone else?** If yes → too generic, rewrite.\n- **Does every sentence add new information?** If any sentence is pure filler → cut it.\n- **Would you text this to a friend?** If it feels too formal → loosen the tone."},{"path":"references/linuxdo-rules.md","content":"# Linux.do Application Rules & Signals\n\nComprehensive rule set for crafting high-pass-rate Linux.do registration applications.\nSources: official announcements, FAQ, and public community experience posts.\n\n## Hard Rules (Official — Pass/Fail)\n\n### 1. Read FAQ/Guidelines First\nApplicants must read the FAQ before registering. The registration page requires checking \"已读\".\nReviewers specifically flag applications that show the applicant didn't read the rules.\n\n### 2. Self-Written Application\nThe application must be a ~50-character self-written text covering your background and why you want to join.\n\"Randomly filled\" or \"AI-generated\" applications will not pass in principle.\n\n### 3. Invited Users Are Also Reviewed\nEven with an invitation link, the same application content is required and reviewed by admins.\n\n### 4. Content Is Archived\nApplication content is not publicly displayed but is archived for future reference.\nThis means: don't treat it as throwaway text.\n\n## Content Characteristics That Increase Pass Rate\n\n### 1. Specificity > Enthusiasm\nEasy-pass applications are concrete: what you tinker with, how you found Linux.do,\nwhich topics you browsed, why you need an account, what you plan to participate in.\nFacts + path + scenario = looks like a real person.\n\n### 2. Site-Aligned Motivation\nGeneric phrases like \"want to learn\", \"want to meet experts\", \"want to grow together\"\ncarry zero information. Users report failing twice before rewriting with specific\nsite-related reasons and use cases.\n\n### 3. Show You Know What the Site Is\nIf the application reveals you don't know what's discussed on Linux.do, or you treat it\nas a generic \"resource group / tech group / beginner site\", pass rate drops.\nThis aligns with the official emphasis on \"read the intro and rules first\".\n\n### 4. \"How I'll Participate\" Is a Bonus\nCommon pattern in successful applications: not just \"I want to look around\" but\n\"I've encountered similar problems\", \"I've seen solutions on the site\",\n\"I want to reply, document, discuss X topic\". This reads like a long-term user.\n\n## Required Information Blocks (4 Blocks)\n\nEvery application should contain these 4 pieces:\n\n| Block | What to Include |\n|-------|----------------|\n| **Real Background** | What you do, what fields you follow. Doesn't need to be complete. |\n| **Discovery Path** | How you found Linux.do — search, friend, specific post, long-time lurker. |\n| **Why Register Now** | Not abstract \"want to join\" but concrete: participate in X, reply to Y, follow Z. |\n| **Account Usage Plan** | Read-only? Occasional replies? Follow specific topics? Be real and specific. |\n\n## High-Risk Patterns (Likely Rejection)\n\n| Pattern | Why It Fails |\n|---------|-------------|\n| No background/experience mentioned | Missing required info block |\n| No explanation of how you found the site | Looks random |\n| No reason for joining | Missing required info block |\n| All fluff, no concrete facts | Template-like |\n| Overly neat, uniform tone | Looks batch-generate"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Craft high-pass-rate, de-AI'd Chinese applications (小作文) for Linux.do registration. Conducts an adaptive survey to learn the applicant's real background, then generates natural, rule-compliant plain text ready to paste. All user interactions in Chinese. Skill: linuxdo-application Owner: clarezoe Summary: Craft high-pass-rate, de-AI'd Chinese applications (小作文) for Linux.do registration. Conducts an adaptive survey to learn the applicant's real background, then generates natural, rule-compliant plain text ready to paste. All user interactions in Chinese. Tags: chinese:1.0.0, latest:1.0.1, linuxdo:1.0.0 Version history: v1.0.1 | 2026-06-09T13:08:53.250Z | user Normali","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1653,"uniquenessScore":46,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T16:26:13.040Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-11T16:26:13.040Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-11T20:56:02.563Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}