[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EJ7NBAV9N8T2TC3ZMRHTPR":3,"skill-same:01M7EJ7NBAV9N8T2TC3ZMRHTPR":46},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":14,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":45},"01M7EJ7NBAV9N8T2TC3ZMRHTPR","unslop",null,"Rules for prose others read: artifact shapes, document rules and the catalog of AI-writing tells.","MustaMohamed\u002Fkern","MustaMohamed","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F15794995?v=4","01M7EJ6B5WMZ90S24CP66DFA3E","Mustafa Mohamed","01M7EJ6B6D2C3Y50VM9NK4ZB2W",0,"MIT","https:\u002F\u002Fgithub.com\u002FMustaMohamed\u002Fkern\u002Fblob\u002Fmain\u002Fskills\u002Funslop\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: unslop\ndescription: \"Rules for prose others read: artifact shapes, document rules and the catalog of AI-writing tells.\"\ndisable-model-invocation: true\n---\n\n# Unslop\n\nThe output contract. Chat replies follow the active kern voice first. Everything else composed for a reader follows this file: subagent returns, review records, plans, specs, PR bodies, issue text, commit messages, docs. Code and config files match their surroundings instead.\n\n## Shape\n\nForm is the limit, not a word count. Each artifact has a shape; content that does not fit the shape is cut, not appended.\n\n| Artifact | Shape | Past it |\n|---|---|---|\n| Chat reply | The answer first, then only what changes the reader's next action | Reasoning only when it was asked for |\n| Subagent return | Verdict and deltas | Anything more goes in a file; return the path |\n| One review finding | `path:line`, the failing scenario, the smallest fix | Anything else is a second finding or padding |\n| One review round | Findings, one-line clean classes, verdict | Needs sections to stay navigable: the task is too big, split it |\n| Plan | A step is one row: file, change, test | Re-describing what sits at a cited line makes it a spec; split the task |\n| Spec | Contracts and tables, not narrative | A fact stated twice: cut one. Still growing: split the scope |\n\nA project may add artifact types or tighten shapes in its own instructions. It may not loosen them silently.\n\n## Document rules\n\n1. **Lead with the answer.** A direct question gets its answer in the first sentence and may end there.\n2. **Evidence, not defence of evidence.** Write `parseAmount, 14 call sites`. Never \"measured rather than assumed\", \"not inferred\", \"confirmed rather than asserted\", \"measured, not read\". If a number needs defending, the defence is the command, in backticks, on the same line. Self-check: grep your own records for these phrases; the count must not grow.\n3. **Negative results are one line.** `auth regression, absent: grep -rn setToken src\u002F returns nothing`. No preamble about why the absence is worth reporting.\n4. **Never narrate the search.** Not \"I expected X and went looking for it\", not \"Recording that because\", not \"What I checked and found clean\" as a heading over a page of prose.\n5. **Say a fact once per artifact, and once per head.** A known-flaky CI failure is derived once per SHA, not once per round. A round on an unchanged head repeats nothing: `head unchanged at \u003Csha>, see round N`.\n6. **No-finding sections get one line, not a heading.** `drift, membership, escapes: clean`. Headings are for categories that found something.\n7. **Cut:** restating the request, narrating tool calls, re-explaining what was already said, process commentary, and any sentence whose job is to show that work was done.\n\n## Process\n\n1. Scan for the patterns below.\n2. Rewrite. Preserve meaning, match intended tone.\n3. Add soul (human-facing prose only; see next section).\n4. Self-audit: \"What makes this obviously AI generated?\" Fix remaining tells.\n\n## Adding soul\n\nFor human-facing prose: docs, announcements, articles. Engineering records get density, not personality.\n\n- **Have opinions.** React to facts instead of neutrally listing pros and cons.\n- **Vary rhythm.** Short sentences. Then longer ones that take their time. Mix it up.\n- **Acknowledge complexity.** \"Impressive but also kind of unsettling\" beats \"impressive.\"\n- **Use \"I\" when it fits.** First person isn't unprofessional.\n- **Let some mess in.** Perfect structure looks machine-made.\n- **Be specific.** Not \"this is concerning\" but \"there's something unsettling about agents churning away at 3am.\"\n\n## Patterns to detect and fix\n\n### Content\n\n1. **Puffery.** \"pivotal moment\", \"testament to\", \"evolving landscape\", \"setting the stage for\", \"indelible mark\", \"deeply rooted\". Cut puffery, state what happened.\n2. **Name-dropping.** Listing media outlets without context. Pick one, say what was said.\n3. **Superficial -ing phrases.** \"highlighting...\", \"ensuring...\", \"reflecting...\", \"showcasing...\", \"fostering...\". Delete or expand with real sources.\n4. **Promotional language.** \"nestled\", \"vibrant\", \"breathtaking\", \"groundbreaking\", \"renowned\", \"stunning\", \"must-visit\". Use neutral descriptions.\n5. **Vague attributions.** \"Experts believe\", \"Industry reports suggest\", \"Some critics argue\". Name the source or delete.\n6. **Formulaic challenges.** \"Despite challenges... continues to thrive.\" Replace with specific facts.\n\n### Language\n\n7. **AI vocabulary.** Additionally, crucial, delve, enduring, enhance, fostering, garner, interplay, intricate, landscape (abstract), pivotal, showcase, tapestry (abstract), testament, underscore, vibrant. Replace with plain words.\n8. **Fancy ways to say \"is\".** \"serves as\", \"stands as\", \"boasts\", \"features\". Just say \"is\" or \"has\".\n9. **\"Not just X, but Y.\"** State the point directly instead. The inverted form is the same tell: \"not merely X\", \"not simply X\".\n10. **Rule of three.** Forcing ideas into groups of three. Use the natural number.\n11. **Synonym cycling.** Protagonist, main character, central figure, hero all in one paragraph. Pick one, repeat it. This includes headings: the same section is not \"What I checked\" in one round and \"What I verified\" in the next.\n12. **False ranges.** \"from X to Y\" where X and Y aren't on a meaningful scale. List topics directly.\n\n### Style\n\n13. **Em dash overuse.** Avoid em dashes entirely. Use periods or commas only (no parentheses, no en dashes, no hyphen-as-dash substitutes). Em dashes are an AI tell, and reaching for parentheses instead just trades one tell for another. If a thought needs separation, end the sentence or use a comma.\n14. **Colon overuse.** Colons are fine before a list or example. Not as mid-sentence connectors. Rewrite to let the point stand on its own.\n15. **Boldface overuse.** Don't bold every proper noun or acronym.\n16. **Inline-header lists.** The tell is a bold label and colon that restates the line: \"**Performance:** Performance improved...\". Convert those to prose. A bold lead-in that ends in a period, names the item, and is followed by genuinely new detail (\"**Schema in TypeScript.** Tables live in one file.\") is fine, not a tell.\n17. **Title case headings.** Use sentence case.\n18. **Decorative emojis.** Remove from headings and bullets.\n19. **Curly quotes.** Replace with straight quotes.\n\n### Communication artifacts\n\n20. **Chatbot phrases.** \"I hope this helps!\", \"Let me know if...\", \"Of course!\", \"Certainly!\", \"Found the smoking gun!\" Remove.\n21. **Cutoff disclaimers.** \"While specific details are limited...\" Find sources or remove.\n22. **Sycophantic tone.** \"Great question! You're absolutely right!\" Respond directly.\n\n### Filler\n\n23. **Filler phrases.** \"In order to\" becomes \"To\". \"Due to the fact that\" becomes \"Because\". \"It is important to note that\" gets deleted.\n24. **Excessive hedging.** \"could potentially possibly be argued that it might\" becomes \"may\".\n25. **Generic conclusions.** \"The future looks bright.\" State specific plans or facts.\n\n### Jargon\n\n26. **Abstract metaphor nouns.** Substrate, wedge, vector, locus, vantage, nexus, primitive (as noun), harness (as metaphor), surface (as in \"API surface\"), bedrock, scaffolding (as metaphor), modality, paradigm, gold-plating, ratchet (as metaphor), evacuate (for moving code), endgame, north star, flywheel. Pick the concrete word. Exempt a word where it is the domain's established name for the thing (a UI library's \"primitive\", a repo's \"harness\" directory); the ban is on metaphor, not vocabulary. A project may list its exempt terms in its own instructions.\n\n### Plain speech\n\n27. **Say what it does, not how it feels.** \"the database stays close at hand\", \"SQL you can read\" name a feeling. The fix names the mechanism or a number: \"`.toSQL()` returns the exact string sent to the database\". If you can't restate it as a concrete instruction, fact, or number, cut it. If the sentence could appear unchanged in another project's docs, it says nothing about this one. Cut it.\n28. **Shorten or split dense sentences.** If the reader has to backtrack to parse a sentence, break it in two or drop clauses. One idea per sentence.\n29. **Active voice.** Prefer it. Catch \"is\u002Fare\u002Fwas\u002Fwere + past participle\" and name the actor: \"queries are validated\" becomes \"the compiler validates queries\". Passive is fine only when the actor is unknown or genuinely doesn't matter.\n30. **Cut adverbs, or use a stronger verb.** \"runs quickly\" becomes \"is fast\" or the number. \"significantly improves\" becomes the measured delta.\n31. **Prefer the plain word.** \"utilize\" becomes \"use\", \"leverage\" becomes \"use\", \"facilitate\" becomes \"help\", \"numerous\" becomes \"many\", \"in the event that\" becomes \"if\".\n","# Unslop\n\nThe output contract. Chat replies follow the active kern voice first. Everything else composed for a reader follows this file: subagent returns, review records, plans, specs, PR bodies, issue text, commit messages, docs. Code and config files match their surroundings instead.\n\n## Shape\n\nForm is the limit, not a word count. Each artifact has a shape; content that does not fit the shape is cut, not appended.\n\n| Artifact | Shape | Past it |\n|---|---|---|\n| Chat reply | The answer first, then only what changes the reader's next action | Reasoning only when it was asked for |\n| Subagent return | Verdict and deltas | Anything more goes in a file; return the path |\n| One review finding | `path:line`, the failing scenario, the smallest fix | Anything else is a second finding or padding |\n| One review round | Findings, one-line clean classes, verdict | Needs sections to stay navigable: the task is too big, split it |\n| Plan | A step is one row: file, change, test | Re-describing what sits at a cited line makes it a spec; split the task |\n| Spec | Contracts and tables, not narrative | A fact stated twice: cut one. Still growing: split the scope |\n\nA project may add artifact types or tighten shapes in its own instructions. It may not loosen them silently.\n\n## Document rules\n\n1. **Lead with the answer.** A direct question gets its answer in the first sentence and may end there.\n2. **Evidence, not defence of evidence.** Write `parseAmount, 14 call sites`. Never \"measured rather than assumed\", \"not inferred\", \"confirmed rather than asserted\", \"measured, not read\". If a number needs defending, the defence is the command, in backticks, on the same line. Self-check: grep your own records for these phrases; the count must not grow.\n3. **Negative results are one line.** `auth regression, absent: grep -rn setToken src\u002F returns nothing`. No preamble about why the absence is worth reporting.\n4. **Never narrate the search.** Not \"I expected X and went looking for it\", not \"Recording that because\", not \"What I checked and found clean\" as a heading over a page of prose.\n5. **Say a fact once per artifact, and once per head.** A known-flaky CI failure is derived once per SHA, not once per round. A round on an unchanged head repeats nothing: `head unchanged at \u003Csha>, see round N`.\n6. **No-finding sections get one line, not a heading.** `drift, membership, escapes: clean`. Headings are for categories that found something.\n7. **Cut:** restating the request, narrating tool calls, re-explaining what was already said, process commentary, and any sentence whose job is to show that work was done.\n\n## Process\n\n1. Scan for the patterns below.\n2. Rewrite. Preserve meaning, match intended tone.\n3. Add soul (human-facing prose only; see next section).\n4. Self-audit: \"What makes this obviously AI generated?\" Fix remaining tells.\n\n## Adding soul\n\nFor human-facing prose: docs, announcements, articles. Engineering records get density, not personality.\n\n- **Have opinions.** React to facts instead of neutrally listing pros and cons.\n- **Vary rhythm.** Short sentences. Then longer ones that take their time. Mix it up.\n- **Acknowledge complexity.** \"Impressive but also kind of unsettling\" beats \"impressive.\"\n- **Use \"I\" when it fits.** First person isn't unprofessional.\n- **Let some mess in.** Perfect structure looks machine-made.\n- **Be specific.** Not \"this is concerning\" but \"there's something unsettling about agents churning away at 3am.\"\n\n## Patterns to detect and fix\n\n### Content\n\n1. **Puffery.** \"pivotal moment\", \"testament to\", \"evolving landscape\", \"setting the stage for\", \"indelible mark\", \"deeply rooted\". Cut puffery, state what happened.\n2. **Name-dropping.** Listing media outlets without context. Pick one, say what was said.\n3. **Superficial -ing phrases.** \"highlighting...\", \"ensuring...\", \"reflecting...\", \"showcasing...\", \"fostering...\". Delete or expand with real sources.\n4. **Promotional language.** \"nestled\", \"vibrant\", \"breathtaking\", \"groundbreaking\", \"renowned\", \"stunning\", \"must-visit\". Use neutral descriptions.\n5. **Vague attributions.** \"Experts believe\", \"Industry reports suggest\", \"Some critics argue\". Name the source or delete.\n6. **Formulaic challenges.** \"Despite challenges... continues to thrive.\" Replace with specific facts.\n\n### Language\n\n7. **AI vocabulary.** Additionally, crucial, delve, enduring, enhance, fostering, garner, interplay, intricate, landscape (abstract), pivotal, showcase, tapestry (abstract), testament, underscore, vibrant. Replace with plain words.\n8. **Fancy ways to say \"is\".** \"serves as\", \"stands as\", \"boasts\", \"features\". Just say \"is\" or \"has\".\n9. **\"Not just X, but Y.\"** State the point directly instead. The inverted form is the same tell: \"not merely X\", \"not simply X\".\n10. **Rule of three.** Forcing ideas into groups of three. Use the natural number.\n11. **Synonym cycling.** Protagonist, main character, central figure, hero all in one paragraph. Pick one, repeat it. This includes headings: the same section is not \"What I checked\" in one round and \"What I verified\" in the next.\n12. **False ranges.** \"from X to Y\" where X and Y aren't on a meaningful scale. List topics directly.\n\n### Style\n\n13. **Em dash overuse.** Avoid em dashes entirely. Use periods or commas only (no parentheses, no en dashes, no hyphen-as-dash substitutes). Em dashes are an AI tell, and reaching for parentheses instead just trades one tell for another. If a thought needs separation, end the sentence or use a comma.\n14. **Colon overuse.** Colons are fine before a list or example. Not as mid-sentence connectors. Rewrite to let the point stand on its own.\n15. **Boldface overuse.** Don't bold every proper noun or acronym.\n16. **Inline-header lists.** The tell is a bold label and colon that restates the line: \"**Performance:** Performance improved...\". Convert those to prose. A bold lead-in that ends in a period, names the item, and is followed by genuinely new detail (\"**Schema in TypeScript.** Tables live in one file.\") is fine, not a tell.\n17. **Title case headings.** Use sentence case.\n18. **Decorative emojis.** Remove from headings and bullets.\n19. **Curly quotes.** Replace with straight quotes.\n\n### Communication artifacts\n\n20. **Chatbot phrases.** \"I hope this helps!\", \"Let me know if...\", \"Of course!\", \"Certainly!\", \"Found the smoking gun!\" Remove.\n21. **Cutoff disclaimers.** \"While specific details are limited...\" Find sources or remove.\n22. **Sycophantic tone.** \"Great question! You're absolutely right!\" Respond directly.\n\n### Filler\n\n23. **Filler phrases.** \"In order to\" becomes \"To\". \"Due to the fact that\" becomes \"Because\". \"It is important to note that\" gets deleted.\n24. **Excessive hedging.** \"could potentially possibly be argued that it might\" becomes \"may\".\n25. **Generic conclusions.** \"The future looks bright.\" State specific plans or facts.\n\n### Jargon\n\n26. **Abstract metaphor nouns.** Substrate, wedge, vector, locus, vantage, nexus, primitive (as noun), harness (as metaphor), surface (as in \"API surface\"), bedrock, scaffolding (as metaphor), modality, paradigm, gold-plating, ratchet (as metaphor), evacuate (for moving code), endgame, north star, flywheel. Pick the concrete word. Exempt a word where it is the domain's established name for the thing (a UI library's \"primitive\", a repo's \"harness\" directory); the ban is on metaphor, not vocabulary. A project may list its exempt terms in its own instructions.\n\n### Plain speech\n\n27. **Say what it does, not how it feels.** \"the database stays close at hand\", \"SQL you can read\" name a feeling. The fix names the mechanism or a number: \"`.toSQL()` returns the exact string sent to the database\". If you can't restate it as a concrete instruction, fact, or number, cut it. If the sentence could appear unchanged in another project's docs, it says nothing about this one. Cut it.\n28. **Shorten or split dense sentences.** If the reader has to backtrack to parse a sentence, break it in two or drop clauses. One idea per sentence.\n29. **Active voice.** Prefer it. Catch \"is\u002Fare\u002Fwas\u002Fwere + past participle\" and name the actor: \"queries are validated\" becomes \"the compiler validates queries\". Passive is fine only when the actor is unknown or genuinely doesn't matter.\n30. **Cut adverbs, or use a stronger verb.** \"runs quickly\" becomes \"is fast\" or the number. \"significantly improves\" becomes the measured delta.\n31. **Prefer the plain word.** \"utilize\" becomes \"use\", \"leverage\" becomes \"use\", \"facilitate\" becomes \"help\", \"numerous\" becomes \"many\", \"in the event that\" becomes \"if\".\n",{"name":5,"description":7,"disable-model-invocation":24},true,"main","566793b007864157e244f69e86c4e72712117985","skills\u002Funslop","https:\u002F\u002Fgithub.com\u002FMustaMohamed\u002Fkern","https:\u002F\u002Fgithub.com\u002FMustaMohamed","https:\u002F\u002Fmustamohamed.github.io\u002FResume\u002F","Software Engineer @MusalaSoft and ACMer. I focus on open-source technologies and projects. I'm working mainly with .Net Core, NodeJS and React.","2026-11-09 20:40:55",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":24},[35,38,41],{"tool":36,"command":37},"npx","npx skills add MustaMohamed\u002Fkern --skill unslop",{"tool":39,"command":40},"bunx","bunx skills add MustaMohamed\u002Fkern --skill unslop",{"tool":42,"command":43},"pnpm","pnpm dlx skills add MustaMohamed\u002Fkern --skill unslop","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FMustaMohamed\u002Fkern\u002Fblob\u002Fmain\u002Fskills\u002Funslop\u002FSKILL.md",[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M7EJ7HG7GGWG7BRD1D0Q6MCV","technical-writing","Write docs, PR bodies, issues and commit messages a tired engineer understands on the first read.","https:\u002F\u002Fgithub.com\u002FMustaMohamed\u002Fkern\u002Fblob\u002Fmain\u002Fskills\u002Ftechnical-writing\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7EJ7E78Z0Y0HMKQ9RYQN7E7","self-review","Check your own diff before a PR: deterministic checks, blast radius, probes, a fresh doubt pass, then a verdict.","https:\u002F\u002Fgithub.com\u002FMustaMohamed\u002Fkern\u002Fblob\u002Fmain\u002Fskills\u002Fself-review\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7EJ7A0S8CGQWG55QR0KWGX0","recall","Use when starting or resuming work and state must be rebuilt first: \"where did I leave off\", \"catch me up on X\", \"what remains\", \"I got lost in these PRs\", a session after days away, or \"recall chat\" for this thread since my last message. Not for one named session.","https:\u002F\u002Fgithub.com\u002FMustaMohamed\u002Fkern\u002Fblob\u002Fmain\u002Fskills\u002Frecall\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7EJ77EMJVXHDRZCKVZ3B94V","prove-it","Use before saying work is done, fixed, passing or verified; before a commit, push or PR; and when a subagent reports success. Runs the proving command fresh, reads all output, checks each acceptance line, and labels other claims measured, inferred or guess.","https:\u002F\u002Fgithub.com\u002FMustaMohamed\u002Fkern\u002Fblob\u002Fmain\u002Fskills\u002Fprove-it\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7EJ75P5KZG3T8D649D6N90W","plan","Turn an approved spec into ordered tasks with exact files, test-first steps, verify commands and blocking edges.","https:\u002F\u002Fgithub.com\u002FMustaMohamed\u002Fkern\u002Fblob\u002Fmain\u002Fskills\u002Fplan\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7EJ73Y7J7SY3PRKHD2W5DQ5","parallel-work","Fan out independent work: one worktree per writer, overlaps serialized, results integrated and re-tested.","https:\u002F\u002Fgithub.com\u002FMustaMohamed\u002Fkern\u002Fblob\u002Fmain\u002Fskills\u002Fparallel-work\u002FSKILL.md",[],[]]