{"id":"416e9cc2-5105-439a-a44f-79ae173c27ec","entityType":"agent","slug":"clawhub-fortunto2-solo-humanize","name":"Humanize","canonicalUrl":"https://www.xpersona.co/agent/clawhub-fortunto2-solo-humanize","canonicalPath":"/agent/clawhub-fortunto2-solo-humanize","generatedAt":"2026-10-12T14:23:44.013Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T23:30:57.363Z","emptyReason":null},"description":"Strip AI writing patterns from text — em dashes, stock phrases, promotional inflation, performed authenticity, rule-of-three lists. Use when user says \"human... Skill: Humanize Owner: fortunto2 Summary: Strip AI writing patterns from text — em dashes, stock phrases, promotional inflation, performed authenticity, rule-of-three lists. Use when user says \"human... Tags: latest:1.0.1 Version history: v1.0.1 | 2026-02-21T22:06:27.737Z | user Universalize: remove project-specific references, add SearXNG recommendation v1.0.0 | 2026-02-20T19:35:11.712Z | user Initial publish Archiv","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 976 downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s17ccp4nxta4tm3ahx4kexjbq5885bd3:solo-humanize","sourceUrl":"https://clawhub.ai/fortunto2/solo-humanize","homepage":"https://clawhub.ai/fortunto2/skills/solo-humanize","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/fortunto2/solo-humanize","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/fortunto2/skills/solo-humanize","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Strip AI writing patterns from text — em dashes, stock phrases, promotional inflation, performed authenticity, rule-of-three lists. Use when user says \"human..."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T23:30:57.363Z","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":"2026-10-11T23:30:57.363Z","emptyReason":null},"stars":null,"forks":null,"downloads":976,"likes":null,"task":null,"library":null,"packageName":null,"latestVersion":"1.0.1","tractionLabel":"976 downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T23:30:57.208Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T23:30:57.363Z","lastCrawledAt":"2026-10-11T23:30:57.208Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T23:30:57.208Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.1","createdAt":"2026-02-21T22:06:27.737Z","changelog":"Universalize: remove project-specific references, add SearXNG recommendation","fileCount":2,"zipByteSize":3204},{"version":"1.0.0","createdAt":"2026-02-20T19:35:11.712Z","changelog":"Initial publish","fileCount":2,"zipByteSize":3204}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17ccp4nxta4tm3ahx4kexjbq5885bd3:solo-humanize","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-fortunto2-solo-humanize/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-fortunto2-solo-humanize/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-fortunto2-solo-humanize/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-fortunto2-solo-humanize/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-fortunto2-solo-humanize/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-fortunto2-solo-humanize/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-12T14:23:44.013Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-fortunto2-solo-humanize/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-fortunto2-solo-humanize/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-fortunto2-solo-humanize/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-fortunto2-solo-humanize/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":"2026-10-11T23:30:57.363Z","emptyReason":null},"readme":"Skill: Humanize\n\nOwner: fortunto2\n\nSummary: Strip AI writing patterns from text — em dashes, stock phrases, promotional inflation, performed authenticity, rule-of-three lists. Use when user says \"human...\n\nTags: latest:1.0.1\n\nVersion history:\n\nv1.0.1 | 2026-02-21T22:06:27.737Z | user\n\nUniversalize: remove project-specific references, add SearXNG recommendation\n\nv1.0.0 | 2026-02-20T19:35:11.712Z | user\n\nInitial publish\n\nArchive index:\n\nArchive v1.0.1: 2 files, 3204 bytes\n\nFiles: SKILL.md (5907b), _meta.json (132b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: solo-humanize\ndescription: Strip AI writing patterns from text — em dashes, stock phrases, promotional inflation, performed authenticity, rule-of-three lists. Use when user says \"humanize this\", \"make it sound human\", \"strip AI patterns\", \"clean up the copy\", or after /content-gen or /landing-gen produces output.\nlicense: MIT\nmetadata:\n  author: fortunto2\n  version: \"1.0.1\"\n  openclaw:\n    emoji: \"✍️\"\nallowed-tools: Read, Write, Edit, Glob, Grep\nargument-hint: \"[file-path or paste text]\"\n---\n\n# /humanize\n\nStrip AI writing patterns from user-facing text. Takes a file or pasted text and rewrites it to read like a human wrote it, without losing meaning or structure.\n\n## Why this exists\n\nLLM output has recognizable tells — em dashes, stock phrases, promotional inflation, performed authenticity. Readers (and Google) notice. This skill catches those patterns and rewrites them.\n\n## When to use\n\n- After `/content-gen`, `/landing-gen`, `/video-promo` — polish the output\n- Before publishing any user-facing prose (blog posts, landing pages, emails)\n- When editing CLAUDE.md or docs that will be read by humans\n- Standalone: `/humanize path/to/file.md`\n\n## Input\n\n- **File path** from `$ARGUMENTS` — reads and rewrites in place\n- **No argument** — asks to paste text, outputs cleaned version\n- Works on `.md`, `.txt`, and text content in `.tsx`/`.html` (string literals only)\n\n## Pattern Catalog\n\n### 1. Em Dash Overuse (—)\n\nThe most obvious AI tell. Replace with commas, periods, colons, or restructure the sentence.\n\n| Before | After |\n|--------|-------|\n| \"The tool — which is free — works great\" | \"The tool (which is free) works great\" |\n| \"Three features — speed, security, simplicity\" | \"Three features: speed, security, simplicity\" |\n| \"We built this — and it changed everything\" | \"We built this. It changed everything.\" |\n\n**Rule:** Max 1 em dash per 500 words. Zero is better.\n\n### 2. Stock Phrases\n\nPhrases that signal \"AI wrote this.\" Remove or replace with specific language.\n\n**Filler phrases (delete entirely):**\n- \"it's worth noting that\" → (just state the thing)\n- \"at the end of the day\" → (cut)\n- \"in today's world\" / \"in the modern landscape\" → (cut)\n- \"without further ado\" → (cut)\n- \"let's dive in\" / \"let's explore\" → (cut)\n\n**Promotional inflation (replace with specifics):**\n- \"game-changer\" → what specifically changed?\n- \"revolutionary\" → what's actually new?\n- \"cutting-edge\" → describe the technology\n- \"seamless\" → \"works without configuration\" (or whatever it actually does)\n- \"leverage\" → \"use\"\n- \"robust\" → \"handles X edge cases\" (specific)\n- \"streamline\" → \"cut steps from N to M\"\n- \"empower\" → what can the user now do?\n- \"unlock\" → what's the actual capability?\n\n**Performed authenticity (rewrite):**\n- \"to be honest\" → (if you need to say this, the rest wasn't honest?)\n- \"let me be frank\" → (just be frank)\n- \"I have to say\" → (just say it)\n- \"honestly\" → (cut)\n- \"the truth is\" → (cut, state the truth directly)\n\n### 3. Rule of Three\n\nAI loves triplets: \"fast, secure, and scalable.\" Real writing varies list length.\n\n| Before | After |\n|--------|-------|\n| \"Fast, secure, and scalable\" | \"Fast and secure\" (if scalable isn't proven) |\n| \"Build, deploy, and iterate\" | \"Build and ship\" (if that's what you mean) |\n| Three bullet points that all say the same thing | One clear bullet |\n\n**Rule:** If you find 3+ triplet lists in one document, break at least half of them.\n\n### 4. Structural Patterns\n\n**Every section has the same shape:**\nAI tends to write: heading → one-sentence intro → 3 bullets → transition sentence. Real writing varies section length and structure.\n\n**Hedging sandwich:**\n\"While X has limitations, it offers Y, making it Z.\" → Pick a side. State it.\n\n**False balance:**\n\"On one hand X, on the other hand Y.\" → If one side is clearly better, say so.\n\n### 5. Sycophantic Openers\n\n- \"Great question!\" → (cut)\n- \"That's a fantastic idea!\" → (cut, or say what's specifically good about it)\n- \"Absolutely!\" → (cut if not genuine agreement)\n- \"I'd be happy to help!\" → (just help)\n\n### 6. Passive Voice / Weak Verbs\n\n- \"It should be noted that\" → (cut, just note it)\n- \"There are several factors that\" → name the factors\n- \"It is important to\" → say why\n- \"This can be achieved by\" → \"Do X\"\n\n## Process\n\n1. **Read the input** — file path or pasted text.\n\n2. **Scan for patterns** — check each category above. Count violations per category.\n\n3. **Rewrite** — fix each violation while preserving:\n   - Technical accuracy (don't change code, commands, or technical terms)\n   - Structure (headings, lists, code blocks stay)\n   - Tone intent (if the original was casual, keep it casual)\n   - Length (aim for same or shorter, never longer)\n\n4. **Report what changed:**\n   ```\n   Humanized: {file or \"pasted text\"}\n\n   Changes:\n     Em dashes:  {N} removed\n     Stock phrases: {N} replaced\n     Inflation: {N} deflated\n     Triplets: {N} broken\n     Sycophancy: {N} cut\n     Total: {N} patterns fixed\n\n   Before: {word count}\n   After:  {word count}\n   ```\n\n5. **If file path:** write the cleaned version back. Show a diff summary.\n   **If pasted text:** output the cleaned version directly.\n\n## What NOT to change\n\n- Code blocks and inline code\n- Technical terms, library names, CLI commands\n- Quotes from other people (attributed quotes stay verbatim)\n- Numbers, dates, URLs\n- Headings structure (don't merge or split sections)\n- Content meaning — only rephrase, never add or remove ideas\n\n## Edge Cases\n\n- **Short text (<50 words):** just apply stock phrase filter, skip structural analysis\n- **Already clean:** report \"No AI patterns found. Text looks human.\"\n- **Code-heavy docs:** skip code blocks entirely, only process prose sections\n- **Non-English text:** apply em dash and structural rules (they're universal), skip English stock phrases\n\nFile v1.0.1:_meta.json\n\n{\n  \"ownerId\": \"kn788bveytzvxyqk3y969pg5dx81edpg\",\n  \"slug\": \"solo-humanize\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1771711587737\n}\n\nArchive v1.0.0: 2 files, 3204 bytes\n\nFiles: SKILL.md (5907b), _meta.json (132b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: solo-humanize\ndescription: Strip AI writing patterns from text — em dashes, stock phrases, promotional inflation, performed authenticity, rule-of-three lists. Use when user says \"humanize this\", \"make it sound human\", \"strip AI patterns\", \"clean up the copy\", or after /content-gen or /landing-gen produces output.\nlicense: MIT\nmetadata:\n  author: fortunto2\n  version: \"1.0.0\"\n  openclaw:\n    emoji: \"✍️\"\nallowed-tools: Read, Write, Edit, Glob, Grep\nargument-hint: \"[file-path or paste text]\"\n---\n\n# /humanize\n\nStrip AI writing patterns from user-facing text. Takes a file or pasted text and rewrites it to read like a human wrote it, without losing meaning or structure.\n\n## Why this exists\n\nLLM output has recognizable tells — em dashes, stock phrases, promotional inflation, performed authenticity. Readers (and Google) notice. This skill catches those patterns and rewrites them.\n\n## When to use\n\n- After `/content-gen`, `/landing-gen`, `/video-promo` — polish the output\n- Before publishing any user-facing prose (blog posts, landing pages, emails)\n- When editing CLAUDE.md or docs that will be read by humans\n- Standalone: `/humanize path/to/file.md`\n\n## Input\n\n- **File path** from `$ARGUMENTS` — reads and rewrites in place\n- **No argument** — asks to paste text, outputs cleaned version\n- Works on `.md`, `.txt`, and text content in `.tsx`/`.html` (string literals only)\n\n## Pattern Catalog\n\n### 1. Em Dash Overuse (—)\n\nThe most obvious AI tell. Replace with commas, periods, colons, or restructure the sentence.\n\n| Before | After |\n|--------|-------|\n| \"The tool — which is free — works great\" | \"The tool (which is free) works great\" |\n| \"Three features — speed, security, simplicity\" | \"Three features: speed, security, simplicity\" |\n| \"We built this — and it changed everything\" | \"We built this. It changed everything.\" |\n\n**Rule:** Max 1 em dash per 500 words. Zero is better.\n\n### 2. Stock Phrases\n\nPhrases that signal \"AI wrote this.\" Remove or replace with specific language.\n\n**Filler phrases (delete entirely):**\n- \"it's worth noting that\" → (just state the thing)\n- \"at the end of the day\" → (cut)\n- \"in today's world\" / \"in the modern landscape\" → (cut)\n- \"without further ado\" → (cut)\n- \"let's dive in\" / \"let's explore\" → (cut)\n\n**Promotional inflation (replace with specifics):**\n- \"game-changer\" → what specifically changed?\n- \"revolutionary\" → what's actually new?\n- \"cutting-edge\" → describe the technology\n- \"seamless\" → \"works without configuration\" (or whatever it actually does)\n- \"leverage\" → \"use\"\n- \"robust\" → \"handles X edge cases\" (specific)\n- \"streamline\" → \"cut steps from N to M\"\n- \"empower\" → what can the user now do?\n- \"unlock\" → what's the actual capability?\n\n**Performed authenticity (rewrite):**\n- \"to be honest\" → (if you need to say this, the rest wasn't honest?)\n- \"let me be frank\" → (just be frank)\n- \"I have to say\" → (just say it)\n- \"honestly\" → (cut)\n- \"the truth is\" → (cut, state the truth directly)\n\n### 3. Rule of Three\n\nAI loves triplets: \"fast, secure, and scalable.\" Real writing varies list length.\n\n| Before | After |\n|--------|-------|\n| \"Fast, secure, and scalable\" | \"Fast and secure\" (if scalable isn't proven) |\n| \"Build, deploy, and iterate\" | \"Build and ship\" (if that's what you mean) |\n| Three bullet points that all say the same thing | One clear bullet |\n\n**Rule:** If you find 3+ triplet lists in one document, break at least half of them.\n\n### 4. Structural Patterns\n\n**Every section has the same shape:**\nAI tends to write: heading → one-sentence intro → 3 bullets → transition sentence. Real writing varies section length and structure.\n\n**Hedging sandwich:**\n\"While X has limitations, it offers Y, making it Z.\" → Pick a side. State it.\n\n**False balance:**\n\"On one hand X, on the other hand Y.\" → If one side is clearly better, say so.\n\n### 5. Sycophantic Openers\n\n- \"Great question!\" → (cut)\n- \"That's a fantastic idea!\" → (cut, or say what's specifically good about it)\n- \"Absolutely!\" → (cut if not genuine agreement)\n- \"I'd be happy to help!\" → (just help)\n\n### 6. Passive Voice / Weak Verbs\n\n- \"It should be noted that\" → (cut, just note it)\n- \"There are several factors that\" → name the factors\n- \"It is important to\" → say why\n- \"This can be achieved by\" → \"Do X\"\n\n## Process\n\n1. **Read the input** — file path or pasted text.\n\n2. **Scan for patterns** — check each category above. Count violations per category.\n\n3. **Rewrite** — fix each violation while preserving:\n   - Technical accuracy (don't change code, commands, or technical terms)\n   - Structure (headings, lists, code blocks stay)\n   - Tone intent (if the original was casual, keep it casual)\n   - Length (aim for same or shorter, never longer)\n\n4. **Report what changed:**\n   ```\n   Humanized: {file or \"pasted text\"}\n\n   Changes:\n     Em dashes:  {N} removed\n     Stock phrases: {N} replaced\n     Inflation: {N} deflated\n     Triplets: {N} broken\n     Sycophancy: {N} cut\n     Total: {N} patterns fixed\n\n   Before: {word count}\n   After:  {word count}\n   ```\n\n5. **If file path:** write the cleaned version back. Show a diff summary.\n   **If pasted text:** output the cleaned version directly.\n\n## What NOT to change\n\n- Code blocks and inline code\n- Technical terms, library names, CLI commands\n- Quotes from other people (attributed quotes stay verbatim)\n- Numbers, dates, URLs\n- Headings structure (don't merge or split sections)\n- Content meaning — only rephrase, never add or remove ideas\n\n## Edge Cases\n\n- **Short text (<50 words):** just apply stock phrase filter, skip structural analysis\n- **Already clean:** report \"No AI patterns found. Text looks human.\"\n- **Code-heavy docs:** skip code blocks entirely, only process prose sections\n- **Non-English text:** apply em dash and structural rules (they're universal), skip English stock phrases\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn788bveytzvxyqk3y969pg5dx81edpg\",\n  \"slug\": \"solo-humanize\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1771616111712\n}","readmeExcerpt":"Skill: Humanize Owner: fortunto2 Summary: Strip AI writing patterns from text — em dashes, stock phrases, promotional inflation, performed authenticity, rule-of-three lists. Use when user says \"human... Tags: latest:1.0.1 Version history: v1.0.1 | 2026-02-21T22:06:27.737Z | user Universalize: remove project-specific references, add SearXNG recommendation v1.0.0 | 2026-02-20T19:35:11.712Z | user Initial publish Archiv","codeSnippets":[],"executableExamples":[{"language":"text","snippet":"Humanized: {file or \"pasted text\"}\n\n   Changes:\n     Em dashes:  {N} removed\n     Stock phrases: {N} replaced\n     Inflation: {N} deflated\n     Triplets: {N} broken\n     Sycophancy: {N} cut\n     Total: {N} patterns fixed\n\n   Before: {word count}\n   After:  {word count}"},{"language":"text","snippet":"Humanized: {file or \"pasted text\"}\n\n   Changes:\n     Em dashes:  {N} removed\n     Stock phrases: {N} replaced\n     Inflation: {N} deflated\n     Triplets: {N} broken\n     Sycophancy: {N} cut\n     Total: {N} patterns fixed\n\n   Before: {word count}\n   After:  {word count}"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: solo-humanize\ndescription: Strip AI writing patterns from text — em dashes, stock phrases, promotional inflation, performed authenticity, rule-of-three lists. Use when user says \"humanize this\", \"make it sound human\", \"strip AI patterns\", \"clean up the copy\", or after /content-gen or /landing-gen produces output.\nlicense: MIT\nmetadata:\n  author: fortunto2\n  version: \"1.0.1\"\n  openclaw:\n    emoji: \"✍️\"\nallowed-tools: Read, Write, Edit, Glob, Grep\nargument-hint: \"[file-path or paste text]\"\n---\n\n# /humanize\n\nStrip AI writing patterns from user-facing text. Takes a file or pasted text and rewrites it to read like a human wrote it, without losing meaning or structure.\n\n## Why this exists\n\nLLM output has recognizable tells — em dashes, stock phrases, promotional inflation, performed authenticity. Readers (and Google) notice. This skill catches those patterns and rewrites them.\n\n## When to use\n\n- After `/content-gen`, `/landing-gen`, `/video-promo` — polish the output\n- Before publishing any user-facing prose (blog posts, landing pages, emails)\n- When editing CLAUDE.md or docs that will be read by humans\n- Standalone: `/humanize path/to/file.md`\n\n## Input\n\n- **File path** from `$ARGUMENTS` — reads and rewrites in place\n- **No argument** — asks to paste text, outputs cleaned version\n- Works on `.md`, `.txt`, and text content in `.tsx`/`.html` (string literals only)\n\n## Pattern Catalog\n\n### 1. Em Dash Overuse (—)\n\nThe most obvious AI tell. Replace with commas, periods, colons, or restructure the sentence.\n\n| Before | After |\n|--------|-------|\n| \"The tool — which is free — works great\" | \"The tool (which is free) works great\" |\n| \"Three features — speed, security, simplicity\" | \"Three features: speed, security, simplicity\" |\n| \"We built this — and it changed everything\" | \"We built this. It changed everything.\" |\n\n**Rule:** Max 1 em dash per 500 words. Zero is better.\n\n### 2. Stock Phrases\n\nPhrases that signal \"AI wrote this.\" Remove or replace with specific language.\n\n**Filler phrases (delete entirely):**\n- \"it's worth noting that\" → (just state the thing)\n- \"at the end of the day\" → (cut)\n- \"in today's world\" / \"in the modern landscape\" → (cut)\n- \"without further ado\" → (cut)\n- \"let's dive in\" / \"let's explore\" → (cut)\n\n**Promotional inflation (replace with specifics):**\n- \"game-changer\" → what specifically changed?\n- \"revolutionary\" → what's actually new?\n- \"cutting-edge\" → describe the technology\n- \"seamless\" → \"works without configuration\" (or whatever it actually does)\n- \"leverage\" → \"use\"\n- \"robust\" → \"handles X edge cases\" (specific)\n- \"streamline\" → \"cut steps from N to M\"\n- \"empower\" → what can the user now do?\n- \"unlock\" → what's the actual capability?\n\n**Performed authenticity (rewrite):**\n- \"to be honest\" → (if you need to say this, the rest wasn't honest?)\n- \"let me be frank\" → (just be frank)\n- \"I have to say\" → (just say it)\n- \"honestly\" → (cut)\n- \"the truth is\" → (cut, state the truth directly)\n\n### 3. Rule of Three\n\nAI loves tr"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn788bveytzvxyqk3y969pg5dx81edpg\",\n  \"slug\": \"solo-humanize\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1771711587737\n}"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Strip AI writing patterns from text — em dashes, stock phrases, promotional inflation, performed authenticity, rule-of-three lists. Use when user says \"human... Skill: Humanize Owner: fortunto2 Summary: Strip AI writing patterns from text — em dashes, stock phrases, promotional inflation, performed authenticity, rule-of-three lists. Use when user says \"human... Tags: latest:1.0.1 Version history: v1.0.1 | 2026-02-21T22:06:27.737Z | user Universalize: remove project-specific references, add SearXNG recommendation v1.0.0 | 2026-02-20T19:35:11.712Z | user Initial publish Archiv","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":809,"uniquenessScore":60,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T23:30:57.363Z","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":"2026-10-11T23:30:57.363Z","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":"2026-10-12T14:23:44.013Z","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"}]}}}