[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77X0WH9PJ8TKS3EX9K91P3M":3,"skill-same:01M77X0WH9PJ8TKS3EX9K91P3M":168},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":29,"commitSha":30,"skillDirectory":31,"forksCount":32,"repositoryHtmlUrl":33,"repositoryHomepageUrl":34,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":36,"install":37,"resources":49},"01M77X0WH9PJ8TKS3EX9K91P3M","code-slop",null,"Detect AI-generated code patterns (\"slop\") in PHP\u002FLaravel and TypeScript\u002FReact source — comment narration, generic naming, premature interfaces, defensive overdose, mock-everything tests, and the absence of human \"scars\". Use when reviewing AI-assisted PRs, auditing code for taste\u002Fquality (not metrics — that's technical-debt), or hardening a code-review checklist. Triggers on \"review for AI slop\", \"find AI patterns\", \"check code feels human\", \"audit code-quality taste\".","StartupBros-com\u002Fhov-stack","StartupBros-com","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F262958016?v=4","01M77WY8AH50FY939DTGZYHVE9","StartupBros.com","01M77WY8B5Q2D7VSS0P6Y0JX6E",1,"MIT","https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fhov-stack\u002Fskills\u002Fcode-slop\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fhov-stack\u002Fskills\u002Fcode-slop\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: code-slop\ndisable-model-invocation: true\ndescription: Detect AI-generated code patterns (\"slop\") in PHP\u002FLaravel and TypeScript\u002FReact source — comment narration, generic naming, premature interfaces, defensive overdose, mock-everything tests, and the absence of human \"scars\". Use when reviewing AI-assisted PRs, auditing code for taste\u002Fquality (not metrics — that's technical-debt), or hardening a code-review checklist. Triggers on \"review for AI slop\", \"find AI patterns\", \"check code feels human\", \"audit code-quality taste\".\nlicense: MIT\nmetadata:\n  author: agent-skills\n  version: \"1.0.0\"\n---\n\n\u003C!-- LOCAL NOTE (this copy, see UPSTREAM.md): invoke-only here.\n     Rules style-no-hack-scars and style-hyper-consistent are provenance heuristics, not\n     quality defects: never add fake HACK markers or formatting drift to satisfy them, and\n     never report their absence as a finding on a diff. -->\n\n# Code Slop Detection\n\nTaste-level review of code for AI-generated patterns. Contains 24 rules across 6 categories covering comments, naming, over-engineering, defensive overdose, test slop, and style fingerprints. Where [`technical-debt`](..\u002Ftechnical-debt) measures *quantitative* code debt (complexity, duplication, CVEs), this skill measures the *qualitative* failure mode: code that passes every metric but reads like a tutorial blog post, not like a human wrote it.\n\n## Metadata\n\n- **Version:** 1.0.0\n- **Scope:** PHP \u002F Laravel + TypeScript \u002F React (Node)\n- **Rule Count:** 24 rules across 6 categories\n- **License:** MIT\n\n## Why this skill exists\n\nIndustry data on AI-assisted code (GitClear 2025, cURL bug-bounty shutdown 2025, arXiv 2510.03029):\n\n- **Refactoring collapsed** from 25% to \u003C10% of changes\n- **Copy-paste surged** 8.3% → 12.3%; code duplication rose ~8x\n- **Code-smell rates +42–85%** over human baselines\n- **82% of AI PRs** use generic catch blocks that don't distinguish error types\n- **76% miss timeouts** on external calls\n\nNone of this fails a typical CI lint. It just makes the codebase slowly unmaintainable. This skill is the lens for catching it before it ships.\n\nThe core insight: **reading cost > writing cost now**. The cost of writing code collapsed; the cost of reading it didn't. Code you can't quickly understand is slop, even if it works.\n\n## How to Audit\n\nWhen the user asks \"review for AI slop\", \"audit code-quality taste\", or \"find AI patterns\" — run through this skill's rules as a checklist against the changed files (PR diff) or full repo.\n\n### Audit Step 1: Determine Scope\n\n- If a PR diff is provided: audit only files changed in the diff\n- If files are named: audit those\n- If no scope: audit the whole repo, prioritized by recently-touched files (most likely AI output)\n\n### Audit Step 2: Detect Stack\n\n| Signal | Stack |\n|--------|-------|\n| `composer.json` + `artisan` | PHP \u002F Laravel |\n| `package.json` (with TypeScript\u002FReact deps) | Node \u002F TypeScript \u002F React |\n| Both present | Laravel + Inertia + React |\n\n### Audit Step 3: Run the Slop Checklist\n\nFor each item below, output:\n- **CLEAN** — pattern not present (brief confirmation)\n- **SUSPICIOUS** — present in small amounts; flag and discuss\n- **INFLATED** — present extensively; verbose-but-functional; remediation recommended\n- **CRITICAL** — extensive AI-fingerprint presence; full review needed before merge\n\n#### Comments\n- [ ] No comments that just narrate the code (`\u002F\u002F create user` above `User::create(...)`)\n- [ ] No empty docblocks (`\u002F** Get user *\u002F` above `getUser()`)\n- [ ] No placeholder comments left in (`\u002F\u002F TODO: implement`, `\u002F\u002F your code here`, `\u002F\u002F implementation`)\n- [ ] No closing-brace labels (`} \u002F\u002F end function`, `} \u002F\u002F end if block`)\n\n#### Naming\n- [ ] No generic placeholder names (`data`, `result`, `info`, `temp`, `helper`)\n- [ ] No over-descriptive run-on names (`theUserWhoIsCurrentlyLoggedIn`)\n- [ ] No suffix abuse (`*Helper` \u002F `*Manager` \u002F `*Util` \u002F `*Wrapper` overused without justification)\n- [ ] No type-in-name patterns (`userObject`, `resultArray`, `stringData`)\n\n#### Over-engineering\n- [ ] No interfaces with exactly one implementation (and no plan for a second)\n- [ ] No single-method classes that should be top-level functions\n- [ ] No wrapper functions called once that just delegate\n- [ ] No new dependency added when an existing one does the same job\n\n#### Defensive overdose\n- [ ] No generic `catch (e) { console.error(...) }` blocks around code that can't throw\n- [ ] No null checks for impossible nulls (after non-null assertions \u002F type-guaranteed values)\n- [ ] Real defensive concerns (timeouts on external calls, rate limits) ARE present\n\n#### Test slop\n- [ ] No tests that mock every dependency with no real behavioural assertion\n- [ ] No \"doesn't throw\" tests that just call and check for exceptions\n- [ ] No tests that mirror the implementation's logic (re-encoding rather than verifying)\n- [ ] No snapshot tests standing in for behavioural assertions\n\n#### Style fingerprints\n- [ ] Some formatting drift exists (no codebase looks like every file ran through the most aggressive linter)\n- [ ] No `as any` \u002F `@ts-ignore` \u002F `@ts-expect-error` sprinkled where inference is hard\n- [ ] Repo has some `\u002F\u002F HACK:` \u002F `\u002F\u002F XXX:` \u002F 2am comments somewhere — codebases without scars are suspect\n- [ ] No debug artifacts (`console.log`, `var_dump`, `dd()`, `dump()`) left in production code\n- [ ] No `if (x) return true; else return false` \u002F redundant type annotations on obvious literals\n\n### Audit Step 4: Build the Slop Ledger\n\nEnd the audit with a verdict table:\n\n```\n## Code Slop Ledger\n\n| File | Verdict | Top findings | Suggested action |\n|------|---------|--------------|------------------|\n| app\u002FServices\u002FUserExportService.php | INFLATED | 12 narration comments; 3 closing-brace labels; `*Helper` overuse | Strip comments; rename Helper → split into functions |\n| resources\u002Fjs\u002FPages\u002FOrders\u002FShow.tsx | CRITICAL | 4 `as any`; mock-everything tests; useless wrapper; impossible null checks | Rewrite section; remove tests; revisit type model |\n| app\u002FModels\u002FOrder.php | CLEAN | — | — |\n\n## Summary\n- CLEAN: X files\n- SUSPICIOUS: Y files\n- INFLATED: Z files (top priority: …)\n- CRITICAL: N files (rewrite before merge)\n```\n\n## When to Apply\n\nReference this skill when:\n- Reviewing an AI-assisted PR before merge\n- Auditing a repo that has accepted heavy AI-assisted contributions\n- Onboarding a codebase and assessing whether it reads as human-maintained\n- Hardening a team's code-review checklist against AI slop\n- After a \"vibe coding\" sprint, before declaring features done\n- Setting up CI gates for AI-output quality\n\n## Step 1: Detect Project Stack\n\nMost rules are stack-agnostic in concept, but examples and detection commands differ between PHP and TypeScript.\n\n| Signal | Stack | Tooling |\n|--------|-------|---------|\n| `composer.json` | PHP \u002F Laravel | `phpstan`, `phpcs`, `phpmd`, manual grep |\n| `package.json` | Node \u002F TS \u002F React | `eslint`, `tsc --noEmit`, `knip`, manual grep |\n\n## Rule Categories by Priority\n\n| Priority | Category | Impact | Prefix |\n|----------|----------|--------|--------|\n| 1 | Comments | CRITICAL | `comments-` |\n| 2 | Naming | CRITICAL | `naming-` |\n| 3 | Over-engineering | HIGH | `over-eng-` |\n| 4 | Defensive overdose | HIGH | `defensive-` |\n| 5 | Test slop | HIGH | `test-` |\n| 6 | Style fingerprints | MEDIUM | `style-` |\n\n## Quick Reference\n\n### 1. Comments (CRITICAL)\n\n- `comments-narration` — Comments that just restate the code on the next line\n- `comments-empty-docblocks` — Generic `\u002F** Get the user *\u002F` over a typed `getUser()` signature\n- `comments-placeholder` — `\u002F\u002F TODO: implement`, `\u002F\u002F your code here`, `\u002F\u002F implementation`, `\u002F\u002F helper function`\n- `comments-closing-brace-labels` — `} \u002F\u002F end function` \u002F `} \u002F\u002F end if block`\n\n### 2. Naming (CRITICAL)\n\n- `naming-generic-placeholders` — `data`, `result`, `info`, `temp`, `helper`, `value`\n- `naming-over-descriptive` — `theUserWhoIsCurrentlyLoggedIn`, `calculateTotalAmountFromItemsList`\n- `naming-suffix-abuse` — `*Helper` \u002F `*Manager` \u002F `*Util` \u002F `*Wrapper` \u002F `*Processor` overused\n- `naming-type-in-name` — `userObject`, `resultArray`, `stringData`, `listOfItems`\n\n### 3. Over-engineering (HIGH)\n\n- `over-eng-premature-interface` — Interface with exactly one implementation and no second on the roadmap\n- `over-eng-single-method-class` — Classes that exist solely to wrap one function\n- `over-eng-useless-wrapper` — Wrapper called from exactly one place, just delegating\n- `over-eng-dependency-creep` — New library when an existing dep already does the job\n\n### 4. Defensive overdose (HIGH)\n\n- `defensive-generic-catch` — `try { ... } catch (e) { console.error(\"error\") }` everywhere\n- `defensive-impossible-null` — Null checks after non-null assertions \u002F type-guaranteed values\n- `defensive-missing-real` — Defensive in the wrong places; missing timeouts\u002Frate-limits where it matters\n\n### 5. Test slop (HIGH)\n\n- `test-mock-everything` — Mock for every dep; the test re-encodes the implementation, not the behaviour\n- `test-doesnt-throw` — Tests that just call the function and assert no exception\n- `test-mirror-implementation` — Tests whose logic mirrors the production code being tested\n- `test-snapshot-abuse` — Snapshot tests replacing behavioural assertions\n\n### 6. Style fingerprints (MEDIUM)\n\n- `style-hyper-consistent` — No formatting drift anywhere; every file looks linter-perfect\n- `style-as-any-escape` — `as any` \u002F `@ts-ignore` \u002F `@ts-expect-error` sprinkled where types are hard\n- `style-no-hack-scars` — Codebase has zero `\u002F\u002F HACK:` \u002F `\u002F\u002F XXX:` markers; no \"geology\"\n- `style-debug-artifacts` — `console.log`, `var_dump`, `dd()`, `dump()` left in production paths\n- `style-trivial-boilerplate` — `if (x) return true; else return false;`, redundant TS type annotations on obvious literals\n\n## Essential Patterns\n\n### The \"would this pass code review?\" filter\n\nFor each code chunk, ask:\n1. **Could I cut a third of these comments and the code would be clearer?** → likely comment slop\n2. **Do the variable names tell me what they hold, or just what type they are?** → likely naming slop\n3. **Could this class be a function?** → likely over-engineering\n4. **Does this catch block actually handle anything, or just log?** → likely defensive overdose\n5. **Does this test fail if I break the function?** → if no, test slop\n6. **Are there any `\u002F\u002F HACK:` \u002F `\u002F\u002F XXX:` markers in the diff?** → if no, suspicious for AI\n\n### Verdict bands (matched to AI-SLOP-Detector's scoring)\n\n| Verdict | Meaning | Action |\n|---|---|---|\n| **CLEAN** | \u003C 5% of lines flagged | Ship |\n| **SUSPICIOUS** | 5–15% flagged | Review changes one more time |\n| **INFLATED** | 15–30% flagged | Strip slop, split commits |\n| **CRITICAL** | > 30% flagged | Rewrite section before merge |\n\n## How to Use\n\nRead individual rule files for detailed conventions and examples:\n\n```\nrules\u002Fcomments-narration.md\nrules\u002Fnaming-generic-placeholders.md\nrules\u002Fover-eng-premature-interface.md\nrules\u002Fdefensive-generic-catch.md\nrules\u002Ftest-mock-everything.md\nrules\u002Fstyle-hyper-consistent.md\n```\n\nEach rule file contains:\n- YAML frontmatter (title, impact, tags)\n- Brief explanation of why the pattern is AI-fingerprint\n- \"Incorrect\" example showing the slop\n- \"Correct\" example showing the human-equivalent\n- Detection guidance (grep \u002F eslint \u002F phpstan \u002F heuristic)\n- Reference link\n\n## References\n\n- GitClear — 2025 Code-Quality Trends Report (refactoring collapse, copy-paste surge)\n- [arXiv 2510.03029 — Investigating the Smells of LLM-Generated Code](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.03029)\n- Addy Osmani — Comprehension Debt (O'Reilly Radar)\n- Stack Overflow Blog — Eno Reyes Q&A on AI code quality\n\n- [hardikpandya\u002Fstop-slop](https:\u002F\u002Fgithub.com\u002Fhardikpandya\u002Fstop-slop) — sister project for prose slop\n- [flamehaven01\u002FAI-SLOP-Detector](https:\u002F\u002Fgithub.com\u002Fflamehaven01\u002FAI-SLOP-Detector) — Python AST scanner with 27 patterns\n\n## Full Compiled Document\n\nFor the complete guide with all rules expanded: `AGENTS.md`\n","\u003C!-- LOCAL NOTE (this copy, see UPSTREAM.md): invoke-only here.\n     Rules style-no-hack-scars and style-hyper-consistent are provenance heuristics, not\n     quality defects: never add fake HACK markers or formatting drift to satisfy them, and\n     never report their absence as a finding on a diff. -->\n\n# Code Slop Detection\n\nTaste-level review of code for AI-generated patterns. Contains 24 rules across 6 categories covering comments, naming, over-engineering, defensive overdose, test slop, and style fingerprints. Where [`technical-debt`](..\u002Ftechnical-debt) measures *quantitative* code debt (complexity, duplication, CVEs), this skill measures the *qualitative* failure mode: code that passes every metric but reads like a tutorial blog post, not like a human wrote it.\n\n## Metadata\n\n- **Version:** 1.0.0\n- **Scope:** PHP \u002F Laravel + TypeScript \u002F React (Node)\n- **Rule Count:** 24 rules across 6 categories\n- **License:** MIT\n\n## Why this skill exists\n\nIndustry data on AI-assisted code (GitClear 2025, cURL bug-bounty shutdown 2025, arXiv 2510.03029):\n\n- **Refactoring collapsed** from 25% to \u003C10% of changes\n- **Copy-paste surged** 8.3% → 12.3%; code duplication rose ~8x\n- **Code-smell rates +42–85%** over human baselines\n- **82% of AI PRs** use generic catch blocks that don't distinguish error types\n- **76% miss timeouts** on external calls\n\nNone of this fails a typical CI lint. It just makes the codebase slowly unmaintainable. This skill is the lens for catching it before it ships.\n\nThe core insight: **reading cost > writing cost now**. The cost of writing code collapsed; the cost of reading it didn't. Code you can't quickly understand is slop, even if it works.\n\n## How to Audit\n\nWhen the user asks \"review for AI slop\", \"audit code-quality taste\", or \"find AI patterns\" — run through this skill's rules as a checklist against the changed files (PR diff) or full repo.\n\n### Audit Step 1: Determine Scope\n\n- If a PR diff is provided: audit only files changed in the diff\n- If files are named: audit those\n- If no scope: audit the whole repo, prioritized by recently-touched files (most likely AI output)\n\n### Audit Step 2: Detect Stack\n\n| Signal | Stack |\n|--------|-------|\n| `composer.json` + `artisan` | PHP \u002F Laravel |\n| `package.json` (with TypeScript\u002FReact deps) | Node \u002F TypeScript \u002F React |\n| Both present | Laravel + Inertia + React |\n\n### Audit Step 3: Run the Slop Checklist\n\nFor each item below, output:\n- **CLEAN** — pattern not present (brief confirmation)\n- **SUSPICIOUS** — present in small amounts; flag and discuss\n- **INFLATED** — present extensively; verbose-but-functional; remediation recommended\n- **CRITICAL** — extensive AI-fingerprint presence; full review needed before merge\n\n#### Comments\n- [ ] No comments that just narrate the code (`\u002F\u002F create user` above `User::create(...)`)\n- [ ] No empty docblocks (`\u002F** Get user *\u002F` above `getUser()`)\n- [ ] No placeholder comments left in (`\u002F\u002F TODO: implement`, `\u002F\u002F your code here`, `\u002F\u002F implementation`)\n- [ ] No closing-brace labels (`} \u002F\u002F end function`, `} \u002F\u002F end if block`)\n\n#### Naming\n- [ ] No generic placeholder names (`data`, `result`, `info`, `temp`, `helper`)\n- [ ] No over-descriptive run-on names (`theUserWhoIsCurrentlyLoggedIn`)\n- [ ] No suffix abuse (`*Helper` \u002F `*Manager` \u002F `*Util` \u002F `*Wrapper` overused without justification)\n- [ ] No type-in-name patterns (`userObject`, `resultArray`, `stringData`)\n\n#### Over-engineering\n- [ ] No interfaces with exactly one implementation (and no plan for a second)\n- [ ] No single-method classes that should be top-level functions\n- [ ] No wrapper functions called once that just delegate\n- [ ] No new dependency added when an existing one does the same job\n\n#### Defensive overdose\n- [ ] No generic `catch (e) { console.error(...) }` blocks around code that can't throw\n- [ ] No null checks for impossible nulls (after non-null assertions \u002F type-guaranteed values)\n- [ ] Real defensive concerns (timeouts on external calls, rate limits) ARE present\n\n#### Test slop\n- [ ] No tests that mock every dependency with no real behavioural assertion\n- [ ] No \"doesn't throw\" tests that just call and check for exceptions\n- [ ] No tests that mirror the implementation's logic (re-encoding rather than verifying)\n- [ ] No snapshot tests standing in for behavioural assertions\n\n#### Style fingerprints\n- [ ] Some formatting drift exists (no codebase looks like every file ran through the most aggressive linter)\n- [ ] No `as any` \u002F `@ts-ignore` \u002F `@ts-expect-error` sprinkled where inference is hard\n- [ ] Repo has some `\u002F\u002F HACK:` \u002F `\u002F\u002F XXX:` \u002F 2am comments somewhere — codebases without scars are suspect\n- [ ] No debug artifacts (`console.log`, `var_dump`, `dd()`, `dump()`) left in production code\n- [ ] No `if (x) return true; else return false` \u002F redundant type annotations on obvious literals\n\n### Audit Step 4: Build the Slop Ledger\n\nEnd the audit with a verdict table:\n\n```\n## Code Slop Ledger\n\n| File | Verdict | Top findings | Suggested action |\n|------|---------|--------------|------------------|\n| app\u002FServices\u002FUserExportService.php | INFLATED | 12 narration comments; 3 closing-brace labels; `*Helper` overuse | Strip comments; rename Helper → split into functions |\n| resources\u002Fjs\u002FPages\u002FOrders\u002FShow.tsx | CRITICAL | 4 `as any`; mock-everything tests; useless wrapper; impossible null checks | Rewrite section; remove tests; revisit type model |\n| app\u002FModels\u002FOrder.php | CLEAN | — | — |\n\n## Summary\n- CLEAN: X files\n- SUSPICIOUS: Y files\n- INFLATED: Z files (top priority: …)\n- CRITICAL: N files (rewrite before merge)\n```\n\n## When to Apply\n\nReference this skill when:\n- Reviewing an AI-assisted PR before merge\n- Auditing a repo that has accepted heavy AI-assisted contributions\n- Onboarding a codebase and assessing whether it reads as human-maintained\n- Hardening a team's code-review checklist against AI slop\n- After a \"vibe coding\" sprint, before declaring features done\n- Setting up CI gates for AI-output quality\n\n## Step 1: Detect Project Stack\n\nMost rules are stack-agnostic in concept, but examples and detection commands differ between PHP and TypeScript.\n\n| Signal | Stack | Tooling |\n|--------|-------|---------|\n| `composer.json` | PHP \u002F Laravel | `phpstan`, `phpcs`, `phpmd`, manual grep |\n| `package.json` | Node \u002F TS \u002F React | `eslint`, `tsc --noEmit`, `knip`, manual grep |\n\n## Rule Categories by Priority\n\n| Priority | Category | Impact | Prefix |\n|----------|----------|--------|--------|\n| 1 | Comments | CRITICAL | `comments-` |\n| 2 | Naming | CRITICAL | `naming-` |\n| 3 | Over-engineering | HIGH | `over-eng-` |\n| 4 | Defensive overdose | HIGH | `defensive-` |\n| 5 | Test slop | HIGH | `test-` |\n| 6 | Style fingerprints | MEDIUM | `style-` |\n\n## Quick Reference\n\n### 1. Comments (CRITICAL)\n\n- `comments-narration` — Comments that just restate the code on the next line\n- `comments-empty-docblocks` — Generic `\u002F** Get the user *\u002F` over a typed `getUser()` signature\n- `comments-placeholder` — `\u002F\u002F TODO: implement`, `\u002F\u002F your code here`, `\u002F\u002F implementation`, `\u002F\u002F helper function`\n- `comments-closing-brace-labels` — `} \u002F\u002F end function` \u002F `} \u002F\u002F end if block`\n\n### 2. Naming (CRITICAL)\n\n- `naming-generic-placeholders` — `data`, `result`, `info`, `temp`, `helper`, `value`\n- `naming-over-descriptive` — `theUserWhoIsCurrentlyLoggedIn`, `calculateTotalAmountFromItemsList`\n- `naming-suffix-abuse` — `*Helper` \u002F `*Manager` \u002F `*Util` \u002F `*Wrapper` \u002F `*Processor` overused\n- `naming-type-in-name` — `userObject`, `resultArray`, `stringData`, `listOfItems`\n\n### 3. Over-engineering (HIGH)\n\n- `over-eng-premature-interface` — Interface with exactly one implementation and no second on the roadmap\n- `over-eng-single-method-class` — Classes that exist solely to wrap one function\n- `over-eng-useless-wrapper` — Wrapper called from exactly one place, just delegating\n- `over-eng-dependency-creep` — New library when an existing dep already does the job\n\n### 4. Defensive overdose (HIGH)\n\n- `defensive-generic-catch` — `try { ... } catch (e) { console.error(\"error\") }` everywhere\n- `defensive-impossible-null` — Null checks after non-null assertions \u002F type-guaranteed values\n- `defensive-missing-real` — Defensive in the wrong places; missing timeouts\u002Frate-limits where it matters\n\n### 5. Test slop (HIGH)\n\n- `test-mock-everything` — Mock for every dep; the test re-encodes the implementation, not the behaviour\n- `test-doesnt-throw` — Tests that just call the function and assert no exception\n- `test-mirror-implementation` — Tests whose logic mirrors the production code being tested\n- `test-snapshot-abuse` — Snapshot tests replacing behavioural assertions\n\n### 6. Style fingerprints (MEDIUM)\n\n- `style-hyper-consistent` — No formatting drift anywhere; every file looks linter-perfect\n- `style-as-any-escape` — `as any` \u002F `@ts-ignore` \u002F `@ts-expect-error` sprinkled where types are hard\n- `style-no-hack-scars` — Codebase has zero `\u002F\u002F HACK:` \u002F `\u002F\u002F XXX:` markers; no \"geology\"\n- `style-debug-artifacts` — `console.log`, `var_dump`, `dd()`, `dump()` left in production paths\n- `style-trivial-boilerplate` — `if (x) return true; else return false;`, redundant TS type annotations on obvious literals\n\n## Essential Patterns\n\n### The \"would this pass code review?\" filter\n\nFor each code chunk, ask:\n1. **Could I cut a third of these comments and the code would be clearer?** → likely comment slop\n2. **Do the variable names tell me what they hold, or just what type they are?** → likely naming slop\n3. **Could this class be a function?** → likely over-engineering\n4. **Does this catch block actually handle anything, or just log?** → likely defensive overdose\n5. **Does this test fail if I break the function?** → if no, test slop\n6. **Are there any `\u002F\u002F HACK:` \u002F `\u002F\u002F XXX:` markers in the diff?** → if no, suspicious for AI\n\n### Verdict bands (matched to AI-SLOP-Detector's scoring)\n\n| Verdict | Meaning | Action |\n|---|---|---|\n| **CLEAN** | \u003C 5% of lines flagged | Ship |\n| **SUSPICIOUS** | 5–15% flagged | Review changes one more time |\n| **INFLATED** | 15–30% flagged | Strip slop, split commits |\n| **CRITICAL** | > 30% flagged | Rewrite section before merge |\n\n## How to Use\n\nRead individual rule files for detailed conventions and examples:\n\n```\nrules\u002Fcomments-narration.md\nrules\u002Fnaming-generic-placeholders.md\nrules\u002Fover-eng-premature-interface.md\nrules\u002Fdefensive-generic-catch.md\nrules\u002Ftest-mock-everything.md\nrules\u002Fstyle-hyper-consistent.md\n```\n\nEach rule file contains:\n- YAML frontmatter (title, impact, tags)\n- Brief explanation of why the pattern is AI-fingerprint\n- \"Incorrect\" example showing the slop\n- \"Correct\" example showing the human-equivalent\n- Detection guidance (grep \u002F eslint \u002F phpstan \u002F heuristic)\n- Reference link\n\n## References\n\n- GitClear — 2025 Code-Quality Trends Report (refactoring collapse, copy-paste surge)\n- [arXiv 2510.03029 — Investigating the Smells of LLM-Generated Code](https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.03029)\n- Addy Osmani — Comprehension Debt (O'Reilly Radar)\n- Stack Overflow Blog — Eno Reyes Q&A on AI code quality\n\n- [hardikpandya\u002Fstop-slop](https:\u002F\u002Fgithub.com\u002Fhardikpandya\u002Fstop-slop) — sister project for prose slop\n- [flamehaven01\u002FAI-SLOP-Detector](https:\u002F\u002Fgithub.com\u002Fflamehaven01\u002FAI-SLOP-Detector) — Python AST scanner with 27 patterns\n\n## Full Compiled Document\n\nFor the complete guide with all rules expanded: `AGENTS.md`\n",{"name":5,"license":15,"metadata":25,"description":7,"disable-model-invocation":28},{"author":26,"version":27},"agent-skills","1.0.0",true,"main","5889e24531cb4e925523afbc48cbe1f42b5e4cd7","plugins\u002Fhov-stack\u002Fskills\u002Fcode-slop",0,"https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack","https:\u002F\u002Fhouseofvibe.ai","https:\u002F\u002Fgithub.com\u002FStartupBros-com","2026-11-15 05:18:00",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":28},[39,42,45],{"tool":40,"command":41},"npx","npx skills add StartupBros-com\u002Fhov-stack --skill code-slop",{"tool":43,"command":44},"bunx","bunx skills add StartupBros-com\u002Fhov-stack --skill code-slop",{"tool":46,"command":47},"pnpm","pnpm dlx skills add StartupBros-com\u002Fhov-stack --skill code-slop","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fhov-stack\u002Fskills\u002Fcode-slop\u002FSKILL.md",[50,54,60,64,68,72,76,80,84,88,92,96,100,104,108,112,116,120,124,128,132,136,140,144,148,152,156,160,164],{"path":51,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":16},"LICENSE","许可证",1070,{"path":55,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":58,"sourceHtmlUrl":59},"metadata.json","REFERENCE","参考文档",3105,"https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fhov-stack\u002Fskills\u002Fcode-slop\u002Fmetadata.json",{"path":61,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":62,"sourceHtmlUrl":63},"rules\u002F_sections.md",2454,"https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fhov-stack\u002Fskills\u002Fcode-slop\u002Frules\u002F_sections.md",{"path":65,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":66,"sourceHtmlUrl":67},"rules\u002F_template.md",670,"https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fhov-stack\u002Fskills\u002Fcode-slop\u002Frules\u002F_template.md",{"path":69,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":70,"sourceHtmlUrl":71},"rules\u002Fcomments-closing-brace-labels.md",3552,"https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fhov-stack\u002Fskills\u002Fcode-slop\u002Frules\u002Fcomments-closing-brace-labels.md",{"path":73,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":74,"sourceHtmlUrl":75},"rules\u002Fcomments-empty-docblocks.md",3884,"https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fhov-stack\u002Fskills\u002Fcode-slop\u002Frules\u002Fcomments-empty-docblocks.md",{"path":77,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":78,"sourceHtmlUrl":79},"rules\u002Fcomments-narration.md",4317,"https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fhov-stack\u002Fskills\u002Fcode-slop\u002Frules\u002Fcomments-narration.md",{"path":81,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":82,"sourceHtmlUrl":83},"rules\u002Fcomments-placeholder.md",4132,"https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fhov-stack\u002Fskills\u002Fcode-slop\u002Frules\u002Fcomments-placeholder.md",{"path":85,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":86,"sourceHtmlUrl":87},"rules\u002Fdefensive-generic-catch.md",5617,"https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fhov-stack\u002Fskills\u002Fcode-slop\u002Frules\u002Fdefensive-generic-catch.md",{"path":89,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":90,"sourceHtmlUrl":91},"rules\u002Fdefensive-impossible-null.md",5426,"https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fhov-stack\u002Fskills\u002Fcode-slop\u002Frules\u002Fdefensive-impossible-null.md",{"path":93,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":94,"sourceHtmlUrl":95},"rules\u002Fdefensive-missing-real.md",6229,"https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fhov-stack\u002Fskills\u002Fcode-slop\u002Frules\u002Fdefensive-missing-real.md",{"path":97,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":98,"sourceHtmlUrl":99},"rules\u002Fnaming-generic-placeholders.md",4015,"https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fhov-stack\u002Fskills\u002Fcode-slop\u002Frules\u002Fnaming-generic-placeholders.md",{"path":101,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":102,"sourceHtmlUrl":103},"rules\u002Fnaming-over-descriptive.md",4160,"https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fhov-stack\u002Fskills\u002Fcode-slop\u002Frules\u002Fnaming-over-descriptive.md",{"path":105,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":106,"sourceHtmlUrl":107},"rules\u002Fnaming-suffix-abuse.md",5424,"https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fhov-stack\u002Fskills\u002Fcode-slop\u002Frules\u002Fnaming-suffix-abuse.md",{"path":109,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":110,"sourceHtmlUrl":111},"rules\u002Fnaming-type-in-name.md",4068,"https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fhov-stack\u002Fskills\u002Fcode-slop\u002Frules\u002Fnaming-type-in-name.md",{"path":113,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":114,"sourceHtmlUrl":115},"rules\u002Fover-eng-dependency-creep.md",4382,"https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fhov-stack\u002Fskills\u002Fcode-slop\u002Frules\u002Fover-eng-dependency-creep.md",{"path":117,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":118,"sourceHtmlUrl":119},"rules\u002Fover-eng-premature-interface.md",5091,"https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fhov-stack\u002Fskills\u002Fcode-slop\u002Frules\u002Fover-eng-premature-interface.md",{"path":121,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":122,"sourceHtmlUrl":123},"rules\u002Fover-eng-single-method-class.md",4872,"https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fhov-stack\u002Fskills\u002Fcode-slop\u002Frules\u002Fover-eng-single-method-class.md",{"path":125,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":126,"sourceHtmlUrl":127},"rules\u002Fover-eng-useless-wrapper.md",4735,"https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fhov-stack\u002Fskills\u002Fcode-slop\u002Frules\u002Fover-eng-useless-wrapper.md",{"path":129,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":130,"sourceHtmlUrl":131},"rules\u002Fstyle-as-any-escape.md",5098,"https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fhov-stack\u002Fskills\u002Fcode-slop\u002Frules\u002Fstyle-as-any-escape.md",{"path":133,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":134,"sourceHtmlUrl":135},"rules\u002Fstyle-debug-artifacts.md",5379,"https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fhov-stack\u002Fskills\u002Fcode-slop\u002Frules\u002Fstyle-debug-artifacts.md",{"path":137,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":138,"sourceHtmlUrl":139},"rules\u002Fstyle-hyper-consistent.md",5155,"https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fhov-stack\u002Fskills\u002Fcode-slop\u002Frules\u002Fstyle-hyper-consistent.md",{"path":141,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":142,"sourceHtmlUrl":143},"rules\u002Fstyle-no-hack-scars.md",4859,"https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fhov-stack\u002Fskills\u002Fcode-slop\u002Frules\u002Fstyle-no-hack-scars.md",{"path":145,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":146,"sourceHtmlUrl":147},"rules\u002Fstyle-trivial-boilerplate.md",6009,"https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fhov-stack\u002Fskills\u002Fcode-slop\u002Frules\u002Fstyle-trivial-boilerplate.md",{"path":149,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":150,"sourceHtmlUrl":151},"rules\u002Ftest-doesnt-throw.md",4990,"https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fhov-stack\u002Fskills\u002Fcode-slop\u002Frules\u002Ftest-doesnt-throw.md",{"path":153,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":154,"sourceHtmlUrl":155},"rules\u002Ftest-mirror-implementation.md",5109,"https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fhov-stack\u002Fskills\u002Fcode-slop\u002Frules\u002Ftest-mirror-implementation.md",{"path":157,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":158,"sourceHtmlUrl":159},"rules\u002Ftest-mock-everything.md",6484,"https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fhov-stack\u002Fskills\u002Fcode-slop\u002Frules\u002Ftest-mock-everything.md",{"path":161,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":162,"sourceHtmlUrl":163},"rules\u002Ftest-snapshot-abuse.md",5322,"https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fhov-stack\u002Fskills\u002Fcode-slop\u002Frules\u002Ftest-snapshot-abuse.md",{"path":165,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":166,"sourceHtmlUrl":167},"UPSTREAM.md",3144,"https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fhov-stack\u002Fskills\u002Fcode-slop\u002FUPSTREAM.md",[169,177,185,193,198,205],{"skillNo":170,"name":171,"nameZh":6,"description":172,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":173,"sourceHtmlUrl":174,"categories":175,"keywords":176,"publishedAt":20},"01M77XGSFPK8Q1XBHYTC1TF2MV","review-adversarial-first","Operator-invoked adversarial review: 3 refute-by-default lenses plus a deterministic judge against a PR, branch, or path, then a decision on whether \u002Fce-code-review's topic fan-out runs. Off the default merge path since the 2026-10-17 merge-and-end ruling; run only when asked for by name.","https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fskills-stack\u002Freview-adversarial-first\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fskills-stack\u002Freview-adversarial-first\u002FSKILL.md",[],[],{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":181,"sourceHtmlUrl":182,"categories":183,"keywords":184,"publishedAt":20},"01M77XGNSF0ARDTK9P3EF2S4E4","memory-mine","Run one deterministic, budgeted directed-capture batch for an explicit Claude Code project store. Use manual workspace mode only when cross-agent cass sessions are intentionally in scope.","https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fskills-stack\u002Fmemory-mine\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fskills-stack\u002Fmemory-mine\u002FSKILL.md",[],[],{"skillNo":186,"name":187,"nameZh":6,"description":188,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":189,"sourceHtmlUrl":190,"categories":191,"keywords":192,"publishedAt":20},"01M77XGHB8NDSNVSDWFCN1WJBY","papers","Search preprints from arXiv, bioRxiv, and medRxiv without API keys. Supports search, lookup, extraction, citations, enrichment, and paper downloads that bundle PDFs plus linked GitHub code.","https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fskills-patches\u002Fpapers\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fskills-patches\u002Fpapers\u002FSKILL.md",[],[],{"skillNo":194,"name":187,"nameZh":6,"description":188,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":195,"categories":196,"keywords":197,"publishedAt":20},"01M77XGBC08DP018FQY16FM0X8","https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fskills-patches\u002Fpapers\u002F.base\u002FSKILL.md",[],[],{"skillNo":199,"name":200,"nameZh":6,"description":201,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":202,"categories":203,"keywords":204,"publishedAt":20},"01M77XG4P5EM9PM8NGRZSJV4CB","wsl-cdp","Drive the user's real, logged-in Windows browser (Chrome, Edge, or Brave) from a Claude Code session running inside WSL2, over the Chrome DevTools Protocol - read authenticated dashboards and consoles, take real screenshots, open and read pages with the user's sessions. Use when a task needs the user's existing web logins and the session runs in WSL2, where the Claude in Chrome extension cannot work. Not for native-Windows or macOS Claude Code (use the official Claude in Chrome extension), not for anonymous scraping or CI (use headless Playwright inside WSL), not for getting past login walls (those are handed to the human).","https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fwsl-cdp\u002Fskills\u002Fwsl-cdp\u002FSKILL.md",[],[],{"skillNo":206,"name":207,"nameZh":6,"description":208,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":209,"categories":210,"keywords":211,"publishedAt":20},"01M77XFZE48M4SQ2Y7A3GFY4RD","token-eater","[BETA] Spend a subscription's idle, about-to-expire credits on safe, machine-verified cleanup. You pick the service (Grok \u002F Codex \u002F Claude) and a token-heavy maintenance skill (de-monolithize, de-slop, simplify, dead-code); that service runs the whole skill -> gate -> self-review -> draft-PR loop on its own credits, in an isolated worktree. token-eater verifies the gate and never merges. Manual invocation only during beta.","https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Fblob\u002Fmain\u002Fplugins\u002Ftoken-eater\u002Fskills\u002Ftoken-eater\u002FSKILL.md",[],[]]