[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79Y4ATSWQ2W59C8TVA7EW92":3,"skill-same:01M79Y4ATSWQ2W59C8TVA7EW92":47},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M79Y4ATSWQ2W59C8TVA7EW92","dotnet-slopwatch",null,"Use Slopwatch to detect LLM reward hacking in .NET code changes. Run after every code modification to catch disabled tests, suppressed warnings, empty catch blocks, and other shortcuts that mask real problems.","Blind-Striker\u002Fagent-skills-and-plugins","Blind-Striker","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1965259?v=4","01M79WFXTE5PH0C1VB7B54ANMN","Deniz İrgin","01M79WFXV5KZ5GST1K8G035DM5",1,"MIT","https:\u002F\u002Fgithub.com\u002FBlind-Striker\u002Fagent-skills-and-plugins\u002Fblob\u002Fmaster\u002Fplugins\u002Fdeniz-dotnet-general\u002Fskills\u002Fdotnet-slopwatch\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: dotnet-slopwatch\ndescription: Use Slopwatch to detect LLM reward hacking in .NET code changes.\n  Run after every code modification to catch disabled tests, suppressed\n  warnings, empty catch blocks, and other shortcuts that mask real problems.\n---\n\n# Slopwatch: LLM Anti-Cheat for .NET\n\n## When to Use This Skill\n\n**Use this skill constantly.** Every time an LLM (including Claude) makes changes to:\n- C# source files (.cs)\n- Project files (.csproj)\n- Props files (Directory.Build.props, Directory.Packages.props)\n- Test files\n\nRun slopwatch to validate the changes don't introduce \"slop.\"\n\n## What is Slop?\n\n\"Slop\" refers to shortcuts LLMs take that make tests pass or builds succeed without actually solving the underlying problem. These are reward hacking behaviors - the LLM optimizes for apparent success rather than real fixes.\n\n### Common Slop Patterns\n\n| Pattern | Example | Why It's Bad |\n|---------|---------|--------------|\n| Disabled tests | `[Fact(Skip=\"flaky\")]` | Hides failures instead of fixing them |\n| Warning suppression | `#pragma warning disable CS8618` | Silences compiler without fixing issue |\n| Empty catch blocks | `catch (Exception) { }` | Swallows errors, hides bugs |\n| Arbitrary delays | `await Task.Delay(1000);` | Masks race conditions, makes tests slow |\n| Project-level suppression | `\u003CNoWarn>CS1591\u003C\u002FNoWarn>` | Disables warnings project-wide |\n| CPM bypass | `Version=\"1.0.0\"` inline | Undermines central package management |\n\n**Never accept these patterns.** If an LLM introduces slop, reject the change and require a proper fix.\n\n---\n\n## Installation\n\nAsk the user before you install slopwatch, create or update its baseline, or commit the baseline or\nthe tool manifest: each changes the repository or the machine. When the tool or the baseline is\nmissing, say so and wait for the answer; running `slopwatch analyze` against an existing setup needs\nno question.\n\n### As a Local Tool (Recommended)\n\nAdd to `.config\u002Fdotnet-tools.json`:\n\n```json\n{\n  \"version\": 1,\n  \"isRoot\": true,\n  \"tools\": {\n    \"slopwatch.cmd\": {\n      \"version\": \"0.4.2\",\n      \"commands\": [\"slopwatch\"],\n      \"rollForward\": false\n    }\n  }\n}\n```\n\nThen restore:\n```bash\ndotnet tool restore\n```\n\n### As a Global Tool\n\n```bash\ndotnet tool install --global Slopwatch.Cmd\n```\n\n---\n\n## First-Time Setup: Establish a Baseline\n\nBefore using slopwatch on an existing project, create a baseline of current issues:\n\n```bash\n# Initialize baseline from existing code\nslopwatch init\n\n# This creates .slopwatch\u002Fbaseline.json\ngit add .slopwatch\u002Fbaseline.json\ngit commit -m \"Add slopwatch baseline\"\n```\n\n**Why baseline?** Legacy code may have existing issues. The baseline ensures slopwatch only catches **new** slop being introduced, not pre-existing technical debt.\n\n---\n\n## Usage During LLM Sessions\n\n### After Every Code Change\n\nRun slopwatch after any LLM-generated code modification:\n\n```bash\n# Analyze for new issues (uses baseline)\nslopwatch analyze\n\n# Use strict mode - fail on warnings too\nslopwatch analyze --fail-on warning\n```\n\n### When Slopwatch Flags an Issue\n\n**Do not ignore it.** Instead:\n\n1. **Understand why** the LLM took the shortcut\n2. **Request a proper fix** - be specific about what's wrong\n3. **Verify the fix** doesn't introduce different slop\n\n```\n# Example: LLM disabled a test\n❌ SW001 [Error]: Disabled test detected\n   File: tests\u002FMyApp.Tests\u002FOrderTests.cs:45\n   Pattern: [Fact(Skip=\"Test is flaky\")]\n\n# Correct response: Ask for actual fix\n\"This test was disabled instead of fixed. Please investigate why\nit's flaky and fix the underlying timing\u002Frace condition issue.\"\n```\n\n### Updating the Baseline (Rare)\n\nOnly update the baseline when slop is **truly justified** and documented:\n\n```bash\n# Add current detections to baseline (use sparingly!)\nslopwatch analyze --update-baseline\n```\n\n**Justification examples:**\n- Third-party library forces a pattern (e.g., must suppress specific warning)\n- Intentional delay for rate limiting (not test flakiness)\n- Generated code that can't be modified\n\nDocument why in a code comment when updating baseline.\n\n---\n\n## Claude Code Hook Integration\n\nAdd slopwatch as a hook to automatically validate every edit. Create or update `.claude\u002Fsettings.json`:\n\n```json\n{\n  \"hooks\": {\n    \"PostToolUse\": [\n      {\n        \"matcher\": \"Write|Edit|MultiEdit\",\n        \"hooks\": [\n          {\n            \"type\": \"command\",\n            \"command\": \"slopwatch analyze -d . --hook\",\n            \"timeout\": 60000\n          }\n        ]\n      }\n    ]\n  }\n}\n```\n\nThe `--hook` flag:\n- Only analyzes **git dirty files** (fast, even on large repos)\n- Outputs errors to stderr in readable format\n- Blocks the edit on warnings\u002Ferrors (exit code 2)\n- Claude sees the error and can fix it immediately\n\n---\n\n## CI\u002FCD Integration\n\nAdd slopwatch to your CI pipeline as a quality gate:\n\n### GitHub Actions\n\n```yaml\njobs:\n  slopwatch:\n    runs-on: ubuntu-latest\n    steps:\n      - uses: actions\u002Fcheckout@v4\n\n      - name: Setup .NET\n        uses: actions\u002Fsetup-dotnet@v4\n        with:\n          dotnet-version: '9.0.x'\n\n      - name: Install Slopwatch\n        run: dotnet tool install --global Slopwatch.Cmd\n\n      - name: Run Slopwatch\n        run: slopwatch analyze -d . --fail-on warning\n```\n\n### Azure Pipelines\n\n```yaml\n- task: DotNetCoreCLI@2\n  displayName: 'Install Slopwatch'\n  inputs:\n    command: 'custom'\n    custom: 'tool'\n    arguments: 'install --global Slopwatch.Cmd'\n\n- script: slopwatch analyze -d . --fail-on warning\n  displayName: 'Slopwatch Analysis'\n```\n\n---\n\n## Detection Rules\n\n| Rule | Severity | What It Catches |\n|------|----------|-----------------|\n| SW001 | Error | Disabled tests (`Skip=`, `Ignore`, `#if false`) |\n| SW002 | Warning | Warning suppression (`#pragma warning disable`, `SuppressMessage`) |\n| SW003 | Error | Empty catch blocks that swallow exceptions |\n| SW004 | Warning | Arbitrary delays in tests (`Task.Delay`, `Thread.Sleep`) |\n| SW005 | Warning | Project file slop (`NoWarn`, `TreatWarningsAsErrors=false`) |\n| SW006 | Error | CPM bypass (`VersionOverride`, inline `Version` attributes) |\n\n---\n\n## Configuration\n\nCreate `.slopwatch\u002Fconfig.json` to suppress a rule for specific paths, with a justification:\n\n```json\n{\n  \"suppressions\": [\n    {\n      \"ruleId\": \"SW002\",\n      \"pattern\": \"**\u002FGenerated\u002F**\",\n      \"justification\": \"Generated code from tooling cannot be manually changed\"\n    }\n  ],\n  \"globalSuppressions\": []\n}\n```\n\nUse `-c` or `--config` to point at a config file elsewhere, and `--exclude` to leave paths out of analysis entirely:\n\n```bash\nslopwatch analyze -d . --config path\u002Fto\u002Fconfig.json\nslopwatch analyze -d . --exclude \"**\u002FGenerated\u002F**,**\u002Fobj\u002F**,**\u002Fbin\u002F**\"\n```\n\n### Strict Mode (Recommended for LLM Sessions)\n\nFor maximum protection during LLM coding sessions, fail on warnings as well as errors:\n\n```bash\nslopwatch analyze -d . --fail-on warning\n```\n\n---\n\n## The Philosophy: Zero Tolerance for New Slop\n\n1. **Baseline captures legacy** - Existing issues are acknowledged but isolated\n2. **New slop is blocked** - Any new shortcut fails the build\u002Fedit\n3. **Exceptions require justification** - If you must update baseline, document why\n4. **LLMs are not special** - The same rules apply to human and AI-generated code\n\nThe goal is to prevent the gradual accumulation of technical debt that occurs when LLMs optimize for \"make the test pass\" rather than \"fix the actual problem.\"\n\n---\n\n## Quick Reference\n\n```bash\n# First time setup\nslopwatch init\ngit add .slopwatch\u002Fbaseline.json\n\n# After every LLM code change\nslopwatch analyze\n\n# Strict mode (recommended)\nslopwatch analyze --fail-on warning\n\n# With stats (performance debugging)\nslopwatch analyze --stats\n\n# Update baseline (rare, document why)\nslopwatch analyze --update-baseline\n\n# JSON output for tooling\nslopwatch analyze --output json\n```\n\n---\n\n## When to Override (Almost Never)\n\nThe only valid reasons to update baseline or disable a rule:\n\n| Scenario | Action | Required |\n|----------|--------|----------|\n| Third-party forces pattern | Update baseline | Code comment explaining why |\n| Generated code (not editable) | Add to exclude list | Document in config |\n| Intentional rate limiting delay | Update baseline | Code comment, not in test |\n| Legacy code cleanup | One-time baseline update | PR description |\n\n**Invalid reasons:**\n- \"The test is flaky\" → Fix the flakiness\n- \"The warning is annoying\" → Fix the code\n- \"It works on my machine\" → Fix the race condition\n- \"We'll fix it later\" → Fix it now\n","# Slopwatch: LLM Anti-Cheat for .NET\n\n## When to Use This Skill\n\n**Use this skill constantly.** Every time an LLM (including Claude) makes changes to:\n- C# source files (.cs)\n- Project files (.csproj)\n- Props files (Directory.Build.props, Directory.Packages.props)\n- Test files\n\nRun slopwatch to validate the changes don't introduce \"slop.\"\n\n## What is Slop?\n\n\"Slop\" refers to shortcuts LLMs take that make tests pass or builds succeed without actually solving the underlying problem. These are reward hacking behaviors - the LLM optimizes for apparent success rather than real fixes.\n\n### Common Slop Patterns\n\n| Pattern | Example | Why It's Bad |\n|---------|---------|--------------|\n| Disabled tests | `[Fact(Skip=\"flaky\")]` | Hides failures instead of fixing them |\n| Warning suppression | `#pragma warning disable CS8618` | Silences compiler without fixing issue |\n| Empty catch blocks | `catch (Exception) { }` | Swallows errors, hides bugs |\n| Arbitrary delays | `await Task.Delay(1000);` | Masks race conditions, makes tests slow |\n| Project-level suppression | `\u003CNoWarn>CS1591\u003C\u002FNoWarn>` | Disables warnings project-wide |\n| CPM bypass | `Version=\"1.0.0\"` inline | Undermines central package management |\n\n**Never accept these patterns.** If an LLM introduces slop, reject the change and require a proper fix.\n\n---\n\n## Installation\n\nAsk the user before you install slopwatch, create or update its baseline, or commit the baseline or\nthe tool manifest: each changes the repository or the machine. When the tool or the baseline is\nmissing, say so and wait for the answer; running `slopwatch analyze` against an existing setup needs\nno question.\n\n### As a Local Tool (Recommended)\n\nAdd to `.config\u002Fdotnet-tools.json`:\n\n```json\n{\n  \"version\": 1,\n  \"isRoot\": true,\n  \"tools\": {\n    \"slopwatch.cmd\": {\n      \"version\": \"0.4.2\",\n      \"commands\": [\"slopwatch\"],\n      \"rollForward\": false\n    }\n  }\n}\n```\n\nThen restore:\n```bash\ndotnet tool restore\n```\n\n### As a Global Tool\n\n```bash\ndotnet tool install --global Slopwatch.Cmd\n```\n\n---\n\n## First-Time Setup: Establish a Baseline\n\nBefore using slopwatch on an existing project, create a baseline of current issues:\n\n```bash\n# Initialize baseline from existing code\nslopwatch init\n\n# This creates .slopwatch\u002Fbaseline.json\ngit add .slopwatch\u002Fbaseline.json\ngit commit -m \"Add slopwatch baseline\"\n```\n\n**Why baseline?** Legacy code may have existing issues. The baseline ensures slopwatch only catches **new** slop being introduced, not pre-existing technical debt.\n\n---\n\n## Usage During LLM Sessions\n\n### After Every Code Change\n\nRun slopwatch after any LLM-generated code modification:\n\n```bash\n# Analyze for new issues (uses baseline)\nslopwatch analyze\n\n# Use strict mode - fail on warnings too\nslopwatch analyze --fail-on warning\n```\n\n### When Slopwatch Flags an Issue\n\n**Do not ignore it.** Instead:\n\n1. **Understand why** the LLM took the shortcut\n2. **Request a proper fix** - be specific about what's wrong\n3. **Verify the fix** doesn't introduce different slop\n\n```\n# Example: LLM disabled a test\n❌ SW001 [Error]: Disabled test detected\n   File: tests\u002FMyApp.Tests\u002FOrderTests.cs:45\n   Pattern: [Fact(Skip=\"Test is flaky\")]\n\n# Correct response: Ask for actual fix\n\"This test was disabled instead of fixed. Please investigate why\nit's flaky and fix the underlying timing\u002Frace condition issue.\"\n```\n\n### Updating the Baseline (Rare)\n\nOnly update the baseline when slop is **truly justified** and documented:\n\n```bash\n# Add current detections to baseline (use sparingly!)\nslopwatch analyze --update-baseline\n```\n\n**Justification examples:**\n- Third-party library forces a pattern (e.g., must suppress specific warning)\n- Intentional delay for rate limiting (not test flakiness)\n- Generated code that can't be modified\n\nDocument why in a code comment when updating baseline.\n\n---\n\n## Claude Code Hook Integration\n\nAdd slopwatch as a hook to automatically validate every edit. Create or update `.claude\u002Fsettings.json`:\n\n```json\n{\n  \"hooks\": {\n    \"PostToolUse\": [\n      {\n        \"matcher\": \"Write|Edit|MultiEdit\",\n        \"hooks\": [\n          {\n            \"type\": \"command\",\n            \"command\": \"slopwatch analyze -d . --hook\",\n            \"timeout\": 60000\n          }\n        ]\n      }\n    ]\n  }\n}\n```\n\nThe `--hook` flag:\n- Only analyzes **git dirty files** (fast, even on large repos)\n- Outputs errors to stderr in readable format\n- Blocks the edit on warnings\u002Ferrors (exit code 2)\n- Claude sees the error and can fix it immediately\n\n---\n\n## CI\u002FCD Integration\n\nAdd slopwatch to your CI pipeline as a quality gate:\n\n### GitHub Actions\n\n```yaml\njobs:\n  slopwatch:\n    runs-on: ubuntu-latest\n    steps:\n      - uses: actions\u002Fcheckout@v4\n\n      - name: Setup .NET\n        uses: actions\u002Fsetup-dotnet@v4\n        with:\n          dotnet-version: '9.0.x'\n\n      - name: Install Slopwatch\n        run: dotnet tool install --global Slopwatch.Cmd\n\n      - name: Run Slopwatch\n        run: slopwatch analyze -d . --fail-on warning\n```\n\n### Azure Pipelines\n\n```yaml\n- task: DotNetCoreCLI@2\n  displayName: 'Install Slopwatch'\n  inputs:\n    command: 'custom'\n    custom: 'tool'\n    arguments: 'install --global Slopwatch.Cmd'\n\n- script: slopwatch analyze -d . --fail-on warning\n  displayName: 'Slopwatch Analysis'\n```\n\n---\n\n## Detection Rules\n\n| Rule | Severity | What It Catches |\n|------|----------|-----------------|\n| SW001 | Error | Disabled tests (`Skip=`, `Ignore`, `#if false`) |\n| SW002 | Warning | Warning suppression (`#pragma warning disable`, `SuppressMessage`) |\n| SW003 | Error | Empty catch blocks that swallow exceptions |\n| SW004 | Warning | Arbitrary delays in tests (`Task.Delay`, `Thread.Sleep`) |\n| SW005 | Warning | Project file slop (`NoWarn`, `TreatWarningsAsErrors=false`) |\n| SW006 | Error | CPM bypass (`VersionOverride`, inline `Version` attributes) |\n\n---\n\n## Configuration\n\nCreate `.slopwatch\u002Fconfig.json` to suppress a rule for specific paths, with a justification:\n\n```json\n{\n  \"suppressions\": [\n    {\n      \"ruleId\": \"SW002\",\n      \"pattern\": \"**\u002FGenerated\u002F**\",\n      \"justification\": \"Generated code from tooling cannot be manually changed\"\n    }\n  ],\n  \"globalSuppressions\": []\n}\n```\n\nUse `-c` or `--config` to point at a config file elsewhere, and `--exclude` to leave paths out of analysis entirely:\n\n```bash\nslopwatch analyze -d . --config path\u002Fto\u002Fconfig.json\nslopwatch analyze -d . --exclude \"**\u002FGenerated\u002F**,**\u002Fobj\u002F**,**\u002Fbin\u002F**\"\n```\n\n### Strict Mode (Recommended for LLM Sessions)\n\nFor maximum protection during LLM coding sessions, fail on warnings as well as errors:\n\n```bash\nslopwatch analyze -d . --fail-on warning\n```\n\n---\n\n## The Philosophy: Zero Tolerance for New Slop\n\n1. **Baseline captures legacy** - Existing issues are acknowledged but isolated\n2. **New slop is blocked** - Any new shortcut fails the build\u002Fedit\n3. **Exceptions require justification** - If you must update baseline, document why\n4. **LLMs are not special** - The same rules apply to human and AI-generated code\n\nThe goal is to prevent the gradual accumulation of technical debt that occurs when LLMs optimize for \"make the test pass\" rather than \"fix the actual problem.\"\n\n---\n\n## Quick Reference\n\n```bash\n# First time setup\nslopwatch init\ngit add .slopwatch\u002Fbaseline.json\n\n# After every LLM code change\nslopwatch analyze\n\n# Strict mode (recommended)\nslopwatch analyze --fail-on warning\n\n# With stats (performance debugging)\nslopwatch analyze --stats\n\n# Update baseline (rare, document why)\nslopwatch analyze --update-baseline\n\n# JSON output for tooling\nslopwatch analyze --output json\n```\n\n---\n\n## When to Override (Almost Never)\n\nThe only valid reasons to update baseline or disable a rule:\n\n| Scenario | Action | Required |\n|----------|--------|----------|\n| Third-party forces pattern | Update baseline | Code comment explaining why |\n| Generated code (not editable) | Add to exclude list | Document in config |\n| Intentional rate limiting delay | Update baseline | Code comment, not in test |\n| Legacy code cleanup | One-time baseline update | PR description |\n\n**Invalid reasons:**\n- \"The test is flaky\" → Fix the flakiness\n- \"The warning is annoying\" → Fix the code\n- \"It works on my machine\" → Fix the race condition\n- \"We'll fix it later\" → Fix it now\n",{"name":5,"description":7},"master","b30b1c1908dbc56a8184128f18803053d762ccb5","plugins\u002Fdeniz-dotnet-general\u002Fskills\u002Fdotnet-slopwatch",0,"https:\u002F\u002Fgithub.com\u002FBlind-Striker\u002Fagent-skills-and-plugins","https:\u002F\u002Fgithub.com\u002FBlind-Striker","denizirgin.com","VP of Engineering - \r\n@armutcom @homeruntech @prontopro\r\n |  Speaker \r\n@CodeFiction\r\n, http:\u002F\u002Fcodefiction.tech | Developer, gamer, blogger, maiden iron fan","2026-11-13 00:23:18",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add Blind-Striker\u002Fagent-skills-and-plugins --skill dotnet-slopwatch",{"tool":39,"command":40},"bunx","bunx skills add Blind-Striker\u002Fagent-skills-and-plugins --skill dotnet-slopwatch",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Blind-Striker\u002Fagent-skills-and-plugins --skill dotnet-slopwatch","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FBlind-Striker\u002Fagent-skills-and-plugins\u002Fblob\u002Fmaster\u002Fplugins\u002Fdeniz-dotnet-general\u002Fskills\u002Fdotnet-slopwatch\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M79YGWBJ52PHMSTKJ3RJ3AWR","writing-tunit-tests","Write tests in TUnit — the attributes, the async assertion model, data-driven cases, lifecycle hooks, and the parallelism rules. USE FOR writing or fixing a test in a TUnit project, translating a test idea into TUnit syntax, or reviewing TUnit test code for API mistakes. DO NOT USE FOR deciding what to test, judging whether a test is any good, or running tests.","https:\u002F\u002Fgithub.com\u002FBlind-Striker\u002Fagent-skills-and-plugins\u002Fblob\u002Fmaster\u002Fskills\u002Fdeniz-dotnet-general\u002Fwriting-tunit-tests\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M79YGR3Y9RCRS6TD71D0KKP8","dotnet-walls","Walls for a .NET change in a repository without its own quality gates — pinned, ephemeral analyzer, format, clone and scanner commands for the verify step, their identity ratchet, and the build traps. Use during a walls preflight, or when a worker's verify step needs .NET quality gates.","https:\u002F\u002Fgithub.com\u002FBlind-Striker\u002Fagent-skills-and-plugins\u002Fblob\u002Fmaster\u002Fskills\u002Fdeniz-dotnet-general\u002Fdotnet-walls\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M79YGFNJBST7D803NQW3SBYM","csharp-15","Write, review and modernize C# 15 (.NET 11) code correctly. Covers every C# 15 feature - collection expression arguments (`[with(...), ...]`), union types (`union`, `[Union]`, `IUnion`, custom unions), closed class hierarchies (`closed`), extension indexers, labeled `break`\u002F`continue`, non-virtual static interface members on runtimes without default interface methods, and the preview memory-safety model (`unsafe(expr)`, `safe`, requires-unsafe members). Use when code targets net11.0 or LangVersion 15\u002Fpreview, when the user mentions any of these features, when replacing marker interfaces, OneOf-style results, `goto`\u002Fflag loop exits or capacity\u002Fcomparer boilerplate, or when the build reports CS8121, CS8509, CS8655, CS8510, CS0121\u002FCS0411 on a `with(...)` element, CS9370, CS9380 or CS9363.","https:\u002F\u002Fgithub.com\u002FBlind-Striker\u002Fagent-skills-and-plugins\u002Fblob\u002Fmaster\u002Fskills\u002Fdeniz-dotnet-general\u002Fcsharp-15\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M79YGAV031473HSX6FN87ENH","verified-waves","Run one task as verified multi-agent waves. Plans the fan-out, sends findings to fresh skeptics, keeps a ledger, and reports N of M done; small tasks stay solo.","https:\u002F\u002Fgithub.com\u002FBlind-Striker\u002Fagent-skills-and-plugins\u002Fblob\u002Fmaster\u002Fskills\u002Fdeniz-coordination\u002Fverified-waves\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M79YG6QXNND4WRPP3GATSY8J","harness","The bundled dispatch harness, which runs a task file on worker models through OpenCode or Codex, fences their writes, escalates their asks to the operator, settles each result from git and its verify commands, and records every step in a ledger. Its commands, task file, modes and write fence, configuration, runs and their recovery, ledger and exit codes.","https:\u002F\u002Fgithub.com\u002FBlind-Striker\u002Fagent-skills-and-plugins\u002Fblob\u002Fmaster\u002Fskills\u002Fdeniz-coordination\u002Fharness\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M79YG2P5S91SDTA5912XJ4FV","delegating-to-worker-models","Use when you hand off implementation, a plan, research a decision will rely on, or a review, and you brief the worker and check what comes back. A subagent that searches, reads in parallel, or keeps your context small is ordinary tool use. Covers what stays with you, the mechanism, assigning work by strength, the walls preflight, prompts without contradictions, the worker contract and model profiles, evidence from your own run, review, and the fix-up loop.","https:\u002F\u002Fgithub.com\u002FBlind-Striker\u002Fagent-skills-and-plugins\u002Fblob\u002Fmaster\u002Fskills\u002Fdeniz-coordination\u002Fdelegating-to-worker-models\u002FSKILL.md",[],[]]