[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CHRQ6597TMKKWSZ4K5Z0RK":3,"skill-same:01M6CHRQ6597TMKKWSZ4K5Z0RK":73},{"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":23,"publishedAt":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":46,"repositoryHtmlUrl":47,"repositoryHomepageUrl":48,"ownerHtmlUrl":49,"ownerBlogUrl":50,"ownerDescription":51,"updatedAt":52,"install":53,"resources":66},"01M6CHRQ6597TMKKWSZ4K5Z0RK","warden-skill",null,"Guide for using Warden CLI locally to analyze code changes. Use when running warden commands, configuring warden.toml, creating custom skills, understanding triggers, or troubleshooting analysis issues. Triggers on \"run warden\", \"warden config\", \"warden.toml\", \"create warden skill\", \"add trigger\", or any Warden-related local development task.","getsentry\u002Fdotagents","getsentry","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1396951?v=4","01M6CHRN2S1A588Q46ASWA5335","Sentry","01M6CHRN76EFH6MTTP534R9KJK",263,"MIT","https:\u002F\u002Fgithub.com\u002Fgetsentry\u002Fdotagents\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwarden-skill\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37],"warden skill","cli","config","development","create","run","code","issues","analysis","analyze","troubleshooting","guide","use","task","2026-11-10 10:12:30",false,"---\nname: warden-skill\ndescription: Guide for using Warden CLI locally to analyze code changes. Use when running warden commands, configuring warden.toml, creating custom skills, understanding triggers, or troubleshooting analysis issues. Triggers on \"run warden\", \"warden config\", \"warden.toml\", \"create warden skill\", \"add trigger\", or any Warden-related local development task.\n---\n\n# Warden Usage\n\nWarden is an event-driven AI agent that analyzes code changes and executes configurable skills to produce structured reports with findings.\n\n## Quick Start\n\n```bash\n# Set API key\nexport WARDEN_ANTHROPIC_API_KEY=sk-ant-...\n\n# Analyze uncommitted changes (uses warden.toml triggers)\nwarden\n\n# Run specific skill on uncommitted changes\nwarden --skill find-bugs\n\n# Analyze specific files\nwarden src\u002Fauth.ts src\u002Fdatabase.ts\n\n# Analyze changes from git ref\nwarden main..HEAD\nwarden HEAD~3\n```\n\n## CLI Reference\n\n```\nwarden [command] [targets...] [options]\n```\n\n**Commands:**\n- `(default)` - Run analysis\n- `init` - Initialize warden.toml and GitHub workflow\n- `add [skill]` - Add skill trigger to warden.toml\n- `sync [repo]` - Update cached remote skills to latest\n- `setup-app` - Create GitHub App via manifest flow\n\n**Targets:**\n- `\u003Cfiles>` - Specific files (e.g., `src\u002Fauth.ts`)\n- `\u003Cglob>` - Pattern match (e.g., `src\u002F**\u002F*.ts`)\n- `\u003Cgit-ref>` - Git range (e.g., `main..HEAD`, `HEAD~3`)\n- `(none)` - Uncommitted changes\n\n**Key Options:**\n| Option | Description |\n|--------|-------------|\n| `--skill \u003Cname>` | Run only this skill |\n| `--config \u003Cpath>` | Path to warden.toml (default: .\u002Fwarden.toml) |\n| `-m, --model \u003Cmodel>` | Model to use |\n| `--json` | Output as JSON |\n| `-o, --output \u003Cpath>` | Write output to JSONL file |\n| `--fail-on \u003Cseverity>` | Exit 1 if findings >= severity |\n| `--comment-on \u003Cseverity>` | Show findings >= severity |\n| `--fix` | Auto-apply suggested fixes |\n| `--parallel \u003Cn>` | Concurrent executions (default: 4) |\n| `--offline` | Use cached remote skills only |\n| `-q, --quiet` | Errors and summary only |\n| `-v, --verbose` | Show real-time findings |\n| `-vv` | Debug info (tokens, latency) |\n\n**Severity levels:** `critical`, `high`, `medium`, `low`, `info`, `off`\n\n## Configuration (warden.toml)\n\nSee [references\u002Fconfig-schema.md](references\u002Fconfig-schema.md) for complete schema.\n\n**Minimal example:**\n\n```toml\nversion = 1\n\n[defaults]\nmodel = \"claude-sonnet-4-20250514\"\n\n[[triggers]]\nname = \"find-bugs\"\nevent = \"pull_request\"\nactions = [\"opened\", \"synchronize\"]\nskill = \"find-bugs\"\n\n[triggers.filters]\npaths = [\"src\u002F**\u002F*.ts\"]\n```\n\n**With custom output thresholds:**\n\n```toml\n[[triggers]]\nname = \"security-strict\"\nevent = \"pull_request\"\nactions = [\"opened\", \"synchronize\"]\nskill = \"security-review\"\n\n[triggers.filters]\npaths = [\"src\u002Fauth\u002F**\", \"src\u002Fpayments\u002F**\"]\n\n[triggers.output]\nfailOn = \"critical\"\ncommentOn = \"high\"\nmaxFindings = 20\n```\n\n## Creating Custom Skills\n\nSkills live in `.warden\u002Fskills\u002F`, `.agents\u002Fskills\u002F`, or `.claude\u002Fskills\u002F`.\n\n**Structure:**\n```\n.warden\u002Fskills\u002Fmy-skill\u002F\n└── SKILL.md\n```\n\n**SKILL.md format:**\n\n```markdown\n---\nname: my-skill\ndescription: What this skill analyzes\nallowed-tools: Read Grep Glob\n---\n\n[Analysis instructions for the agent]\n\n## What to Look For\n- Specific issue type 1\n- Specific issue type 2\n\n## Output Format\nReport findings with severity, location, and suggested fix.\n```\n\n**Available tools:** `Read`, `Glob`, `Grep`, `WebFetch`, `WebSearch`, `Bash`, `Write`, `Edit`\n\n## Remote Skills\n\nSkills can be fetched from GitHub repositories:\n\n```bash\n# Add a remote skill\nwarden add --remote getsentry\u002Fskills --skill security-review\n\n# Add with version pinning (recommended for reproducibility)\nwarden add --remote getsentry\u002Fskills@abc123 --skill security-review\n\n# List skills in a remote repo\nwarden add --remote getsentry\u002Fskills --list\n\n# Update all unpinned remote skills\nwarden sync\n\n# Update specific repo\nwarden sync getsentry\u002Fskills\n\n# Run with cached skills only (no network)\nwarden --offline\n```\n\n**Remote trigger in warden.toml:**\n\n```toml\n[[triggers]]\nname = \"security-review\"\nevent = \"pull_request\"\nactions = [\"opened\", \"synchronize\"]\nskill = \"security-review\"\nremote = \"getsentry\u002Fskills@abc123\"\n```\n\n**Cache location:** `~\u002F.local\u002Fwarden\u002Fskills\u002F` (override with `WARDEN_STATE_DIR`)\n\n**Cache TTL:** 24 hours for unpinned refs (override with `WARDEN_SKILL_CACHE_TTL` in seconds)\n\n## Common Patterns\n\n**Strict security on critical files:**\n```toml\n[[triggers]]\nname = \"auth-security\"\nevent = \"pull_request\"\nactions = [\"opened\", \"synchronize\"]\nskill = \"security-review\"\nmodel = \"claude-opus-4-20250514\"\nmaxTurns = 100\n\n[triggers.filters]\npaths = [\"src\u002Fauth\u002F**\", \"src\u002Fpayments\u002F**\"]\n\n[triggers.output]\nfailOn = \"critical\"\n```\n\n**Skip test files:**\n```toml\n[triggers.filters]\npaths = [\"src\u002F**\u002F*.ts\"]\nignorePaths = [\"**\u002F*.test.ts\", \"**\u002F*.spec.ts\"]\n```\n\n**Whole-file analysis for configs:**\n```toml\n[defaults.chunking.filePatterns]\npattern = \"*.config.*\"\nmode = \"whole-file\"\n```\n\n## Troubleshooting\n\n**No findings reported:**\n- Check `--comment-on` threshold (default shows all)\n- Verify skill matches file types in `filters.paths`\n- Use `-v` to see which files are being analyzed\n\n**Files being skipped:**\n- Built-in skip patterns: lock files, minified, `node_modules\u002F`, `dist\u002F`\n- Check `ignorePaths` in config\n- Use `-vv` to see skip reasons\n\n**Token\u002Fcost issues:**\n- Reduce `maxTurns` (default: 50)\n- Use chunking settings to control chunk size\n- Filter to relevant files with `paths`\n","# Warden Usage\n\nWarden is an event-driven AI agent that analyzes code changes and executes configurable skills to produce structured reports with findings.\n\n## Quick Start\n\n```bash\n# Set API key\nexport WARDEN_ANTHROPIC_API_KEY=sk-ant-...\n\n# Analyze uncommitted changes (uses warden.toml triggers)\nwarden\n\n# Run specific skill on uncommitted changes\nwarden --skill find-bugs\n\n# Analyze specific files\nwarden src\u002Fauth.ts src\u002Fdatabase.ts\n\n# Analyze changes from git ref\nwarden main..HEAD\nwarden HEAD~3\n```\n\n## CLI Reference\n\n```\nwarden [command] [targets...] [options]\n```\n\n**Commands:**\n- `(default)` - Run analysis\n- `init` - Initialize warden.toml and GitHub workflow\n- `add [skill]` - Add skill trigger to warden.toml\n- `sync [repo]` - Update cached remote skills to latest\n- `setup-app` - Create GitHub App via manifest flow\n\n**Targets:**\n- `\u003Cfiles>` - Specific files (e.g., `src\u002Fauth.ts`)\n- `\u003Cglob>` - Pattern match (e.g., `src\u002F**\u002F*.ts`)\n- `\u003Cgit-ref>` - Git range (e.g., `main..HEAD`, `HEAD~3`)\n- `(none)` - Uncommitted changes\n\n**Key Options:**\n| Option | Description |\n|--------|-------------|\n| `--skill \u003Cname>` | Run only this skill |\n| `--config \u003Cpath>` | Path to warden.toml (default: .\u002Fwarden.toml) |\n| `-m, --model \u003Cmodel>` | Model to use |\n| `--json` | Output as JSON |\n| `-o, --output \u003Cpath>` | Write output to JSONL file |\n| `--fail-on \u003Cseverity>` | Exit 1 if findings >= severity |\n| `--comment-on \u003Cseverity>` | Show findings >= severity |\n| `--fix` | Auto-apply suggested fixes |\n| `--parallel \u003Cn>` | Concurrent executions (default: 4) |\n| `--offline` | Use cached remote skills only |\n| `-q, --quiet` | Errors and summary only |\n| `-v, --verbose` | Show real-time findings |\n| `-vv` | Debug info (tokens, latency) |\n\n**Severity levels:** `critical`, `high`, `medium`, `low`, `info`, `off`\n\n## Configuration (warden.toml)\n\nSee [references\u002Fconfig-schema.md](references\u002Fconfig-schema.md) for complete schema.\n\n**Minimal example:**\n\n```toml\nversion = 1\n\n[defaults]\nmodel = \"claude-sonnet-4-20250514\"\n\n[[triggers]]\nname = \"find-bugs\"\nevent = \"pull_request\"\nactions = [\"opened\", \"synchronize\"]\nskill = \"find-bugs\"\n\n[triggers.filters]\npaths = [\"src\u002F**\u002F*.ts\"]\n```\n\n**With custom output thresholds:**\n\n```toml\n[[triggers]]\nname = \"security-strict\"\nevent = \"pull_request\"\nactions = [\"opened\", \"synchronize\"]\nskill = \"security-review\"\n\n[triggers.filters]\npaths = [\"src\u002Fauth\u002F**\", \"src\u002Fpayments\u002F**\"]\n\n[triggers.output]\nfailOn = \"critical\"\ncommentOn = \"high\"\nmaxFindings = 20\n```\n\n## Creating Custom Skills\n\nSkills live in `.warden\u002Fskills\u002F`, `.agents\u002Fskills\u002F`, or `.claude\u002Fskills\u002F`.\n\n**Structure:**\n```\n.warden\u002Fskills\u002Fmy-skill\u002F\n└── SKILL.md\n```\n\n**SKILL.md format:**\n\n```markdown\n---\nname: my-skill\ndescription: What this skill analyzes\nallowed-tools: Read Grep Glob\n---\n\n[Analysis instructions for the agent]\n\n## What to Look For\n- Specific issue type 1\n- Specific issue type 2\n\n## Output Format\nReport findings with severity, location, and suggested fix.\n```\n\n**Available tools:** `Read`, `Glob`, `Grep`, `WebFetch`, `WebSearch`, `Bash`, `Write`, `Edit`\n\n## Remote Skills\n\nSkills can be fetched from GitHub repositories:\n\n```bash\n# Add a remote skill\nwarden add --remote getsentry\u002Fskills --skill security-review\n\n# Add with version pinning (recommended for reproducibility)\nwarden add --remote getsentry\u002Fskills@abc123 --skill security-review\n\n# List skills in a remote repo\nwarden add --remote getsentry\u002Fskills --list\n\n# Update all unpinned remote skills\nwarden sync\n\n# Update specific repo\nwarden sync getsentry\u002Fskills\n\n# Run with cached skills only (no network)\nwarden --offline\n```\n\n**Remote trigger in warden.toml:**\n\n```toml\n[[triggers]]\nname = \"security-review\"\nevent = \"pull_request\"\nactions = [\"opened\", \"synchronize\"]\nskill = \"security-review\"\nremote = \"getsentry\u002Fskills@abc123\"\n```\n\n**Cache location:** `~\u002F.local\u002Fwarden\u002Fskills\u002F` (override with `WARDEN_STATE_DIR`)\n\n**Cache TTL:** 24 hours for unpinned refs (override with `WARDEN_SKILL_CACHE_TTL` in seconds)\n\n## Common Patterns\n\n**Strict security on critical files:**\n```toml\n[[triggers]]\nname = \"auth-security\"\nevent = \"pull_request\"\nactions = [\"opened\", \"synchronize\"]\nskill = \"security-review\"\nmodel = \"claude-opus-4-20250514\"\nmaxTurns = 100\n\n[triggers.filters]\npaths = [\"src\u002Fauth\u002F**\", \"src\u002Fpayments\u002F**\"]\n\n[triggers.output]\nfailOn = \"critical\"\n```\n\n**Skip test files:**\n```toml\n[triggers.filters]\npaths = [\"src\u002F**\u002F*.ts\"]\nignorePaths = [\"**\u002F*.test.ts\", \"**\u002F*.spec.ts\"]\n```\n\n**Whole-file analysis for configs:**\n```toml\n[defaults.chunking.filePatterns]\npattern = \"*.config.*\"\nmode = \"whole-file\"\n```\n\n## Troubleshooting\n\n**No findings reported:**\n- Check `--comment-on` threshold (default shows all)\n- Verify skill matches file types in `filters.paths`\n- Use `-v` to see which files are being analyzed\n\n**Files being skipped:**\n- Built-in skip patterns: lock files, minified, `node_modules\u002F`, `dist\u002F`\n- Check `ignorePaths` in config\n- Use `-vv` to see skip reasons\n\n**Token\u002Fcost issues:**\n- Reduce `maxTurns` (default: 50)\n- Use chunking settings to control chunk size\n- Filter to relevant files with `paths`\n",{"name":5,"description":7},"main","81fa16f2bb6645dae9b8f8a5cb04297c838474fd",".agents\u002Fskills\u002Fwarden-skill",25,"https:\u002F\u002Fgithub.com\u002Fgetsentry\u002Fdotagents","https:\u002F\u002Fdotagents.sentry.dev","https:\u002F\u002Fgithub.com\u002Fgetsentry","https:\u002F\u002Fsentry.io","Real-time crash reporting for your web apps, mobile apps, and games.","2026-11-04 05:44:30",{"source":8,"skillName":5,"commands":54,"prompt":64,"zipAvailable":65},[55,58,61],{"tool":56,"command":57},"npx","npx skills add getsentry\u002Fdotagents --skill warden-skill",{"tool":59,"command":60},"bunx","bunx skills add getsentry\u002Fdotagents --skill warden-skill",{"tool":62,"command":63},"pnpm","pnpm dlx skills add getsentry\u002Fdotagents --skill warden-skill","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgetsentry\u002Fdotagents\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwarden-skill\u002FSKILL.md",true,[67],{"path":68,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Fconfig-schema.md","REFERENCE","参考文档",3593,"https:\u002F\u002Fgithub.com\u002Fgetsentry\u002Fdotagents\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwarden-skill\u002Freferences\u002Fconfig-schema.md",[74,100,122,130,138],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":83,"publishedAt":38},"01M6CHS3RM0F9N2K020H94X995","dotagents-qa","QA dotagents changes and published releases in Docker, including CLI lifecycles, user\u002Fglobal scope, real plugins, and Claude, Copilot, Codex, OpenCode, or Pi projections. Use when behavior, packaging, scopes, or harness integration needs runtime proof.","https:\u002F\u002Fgithub.com\u002Fgetsentry\u002Fdotagents\u002Fblob\u002Fmain\u002Fskills\u002Fdotagents-qa\u002FSKILL.md",[80],{"categoryNo":81,"categoryName":82,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署",[84,85,86,87,25,88,89,90,91,92,93,94,95,96,97,36,98,99],"dotagents qa","dotagents","qa","integration","docker","codex","copilot","harness","plugins","behavior","user","global","pi","packaging","opencode","releases",{"skillNo":101,"name":85,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":106,"publishedAt":38},"01M6CHRZKBCD84YFW68W00JRDW","Manage dotagents dependencies and runtime config. Use when asked to \"add a skill\", \"install skills\", \"remove a skill\", \"configure plugins\", \"configure subagents\", \"dotagents init\", \"agents.toml\", \"agents.lock\", \"sync skills\", \"list skills\", \"set up dotagents\", \"configure trust\", \"add MCP server\", \"add hook\", \"wildcard skills\", \"global scope\", \"project scope\", \"dotagents doctor\", or any dotagents-related task.","https:\u002F\u002Fgithub.com\u002Fgetsentry\u002Fdotagents\u002Fblob\u002Fmain\u002Fplugins\u002Fdotagents\u002Fskills\u002Fdotagents\u002FSKILL.md",[105],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[85,37,107,92,108,109,110,111,26,112,113,114,115,116,117,118,119,120,36,121],"manage","MCP","mcp server","init","sync","doctor","trust","server","list skills","SET","configure","add mcp","install","remove","up",{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":38},"01M6CHRY3Z4QYXFZDS7EB9QYC3","review","Fixture review skill.","https:\u002F\u002Fgithub.com\u002Fgetsentry\u002Fdotagents\u002Fblob\u002Fmain\u002Fexamples\u002Ffull\u002Flocal-skills\u002Freview\u002FSKILL.md",[],[124,129],"review skill",{"skillNo":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":136,"publishedAt":38},"01M6CHRWHG0K94D4C9XNPAC4J9","commit","Fixture commit skill.","https:\u002F\u002Fgithub.com\u002Fgetsentry\u002Fdotagents\u002Fblob\u002Fmain\u002Fexamples\u002Ffull\u002Flocal-skills\u002Fcommit\u002FSKILL.md",[],[132,137],"commit skill",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":144,"publishedAt":38},"01M6CHRTBR98DD17W33KTS6K8A","plugin-qa","Use this fixture skill to prove plugin skill projection in dotagents smoke tests.","https:\u002F\u002Fgithub.com\u002Fgetsentry\u002Fdotagents\u002Fblob\u002Fmain\u002Fexamples\u002Ffull\u002Flocal-plugins\u002Fqa-tools\u002Fskills\u002Fplugin-qa\u002FSKILL.md",[],[145,146,86,147,36,148,149,150],"plugin","plugin qa","smoke","smoke tests","fixture skill","plugin skill"]