[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DCYHX0EBXRGAKSVTYXS96D":3,"skill-same:01M7DCYHX0EBXRGAKSVTYXS96D":58},{"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":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7DCYHX0EBXRGAKSVTYXS96D","ralph-loop",null,"Run, monitor, resume, merge, and debug Ralph loops. Use this skill whenever the user asks to operate `ralph run` or `ralph loops`, inspect loop state, recover suspended loops, analyze diagnostics, or unblock merge queue issues.","flaviomartil\u002Fralph-jev","flaviomartil","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F60192455?v=4","01M7DCWCHAAEJPMG1QM8T0ZN9F","Flávio Martil","01M7DCWCJTHN5T4YN12F3GTXGM",0,"MIT","https:\u002F\u002Fgithub.com\u002Fflaviomartil\u002Fralph-jev\u002Fblob\u002Fmain\u002Fskills\u002Fralph-loop\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: ralph-loop\ndescription: Run, monitor, resume, merge, and debug Ralph loops. Use this skill whenever the user asks to operate `ralph run` or `ralph loops`, inspect loop state, recover suspended loops, analyze diagnostics, or unblock merge queue issues.\n---\n\n# Ralph Loop\n\nUse this skill to operate Ralph loops from the outside.\n\n## Use This Skill For\n\n- Starting or continuing a Ralph run with the right `-c` and `-H` inputs\n- Inspecting loop state, worktrees, logs, history, and diffs\n- Resuming a hook-suspended loop\n- Merging or discarding completed worktree loops\n- Debugging unexpected loop behavior with current diagnostics files\n\n## Workflow\n\n1. Start with `ralph loops list` or `ralph loops list --json` to establish the\n   current state.\n2. If the user wants execution, run `ralph run ...` with the right core config\n   and hats source.\n3. If the loop is stuck or suspicious, inspect `logs`, `history`, and `diff`\n   before changing state.\n4. If the loop is suspended, read `.ralph\u002Fsuspend-state.json` and use\n   `ralph loops resume \u003Cid>`.\n5. If a loop is queued or in `needs-review`, inspect the diff first, then use\n   `merge`, `process`, `retry`, or `discard` as appropriate.\n6. Use diagnostics when you need detailed evidence about hats, events, tool\n   calls, parse errors, or performance.\n\n## Guardrails\n\n- Prefer the CLI over direct edits to `.ralph` state files.\n- Treat tasks and memories as the canonical runtime systems; do not center\n  scratchpad as the primary state model.\n- Inspect diffs before merging.\n- Only remove lock or queue artifacts when the underlying process is confirmed\n  dead.\n- Manual edits under `.ralph\u002F` are last-resort recovery steps and should be\n  called out explicitly when used.\n\n## Read These References When Needed\n\n- For command recipes and operator flows: `references\u002Fcommands.md`\n- For diagnostics files and suspend-state details: `references\u002Fdiagnostics.md`\n","# Ralph Loop\n\nUse this skill to operate Ralph loops from the outside.\n\n## Use This Skill For\n\n- Starting or continuing a Ralph run with the right `-c` and `-H` inputs\n- Inspecting loop state, worktrees, logs, history, and diffs\n- Resuming a hook-suspended loop\n- Merging or discarding completed worktree loops\n- Debugging unexpected loop behavior with current diagnostics files\n\n## Workflow\n\n1. Start with `ralph loops list` or `ralph loops list --json` to establish the\n   current state.\n2. If the user wants execution, run `ralph run ...` with the right core config\n   and hats source.\n3. If the loop is stuck or suspicious, inspect `logs`, `history`, and `diff`\n   before changing state.\n4. If the loop is suspended, read `.ralph\u002Fsuspend-state.json` and use\n   `ralph loops resume \u003Cid>`.\n5. If a loop is queued or in `needs-review`, inspect the diff first, then use\n   `merge`, `process`, `retry`, or `discard` as appropriate.\n6. Use diagnostics when you need detailed evidence about hats, events, tool\n   calls, parse errors, or performance.\n\n## Guardrails\n\n- Prefer the CLI over direct edits to `.ralph` state files.\n- Treat tasks and memories as the canonical runtime systems; do not center\n  scratchpad as the primary state model.\n- Inspect diffs before merging.\n- Only remove lock or queue artifacts when the underlying process is confirmed\n  dead.\n- Manual edits under `.ralph\u002F` are last-resort recovery steps and should be\n  called out explicitly when used.\n\n## Read These References When Needed\n\n- For command recipes and operator flows: `references\u002Fcommands.md`\n- For diagnostics files and suspend-state details: `references\u002Fdiagnostics.md`\n",{"name":5,"description":7},"main","adaf7f4432d523a43d920c5d2d875271e7ec0873","skills\u002Fralph-loop","https:\u002F\u002Fgithub.com\u002Fflaviomartil\u002Fralph-jev","https:\u002F\u002Fgithub.com\u002Fflaviomartil","2026-09-26 07:24:05",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add flaviomartil\u002Fralph-jev --skill ralph-loop",{"tool":36,"command":37},"bunx","bunx skills add flaviomartil\u002Fralph-jev --skill ralph-loop",{"tool":39,"command":40},"pnpm","pnpm dlx skills add flaviomartil\u002Fralph-jev --skill ralph-loop","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fflaviomartil\u002Fralph-jev\u002Fblob\u002Fmain\u002Fskills\u002Fralph-loop\u002FSKILL.md",true,[44,50,54],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"agents\u002Fopenai.yaml","REFERENCE","参考文档",239,"https:\u002F\u002Fgithub.com\u002Fflaviomartil\u002Fralph-jev\u002Fblob\u002Fmain\u002Fskills\u002Fralph-loop\u002Fagents\u002Fopenai.yaml",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fcommands.md",1287,"https:\u002F\u002Fgithub.com\u002Fflaviomartil\u002Fralph-jev\u002Fblob\u002Fmain\u002Fskills\u002Fralph-loop\u002Freferences\u002Fcommands.md",{"path":55,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fdiagnostics.md",1896,"https:\u002F\u002Fgithub.com\u002Fflaviomartil\u002Fralph-jev\u002Fblob\u002Fmain\u002Fskills\u002Fralph-loop\u002Freferences\u002Fdiagnostics.md",[59,66,73,80,87,94],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7DCYDCFEJFYD4V5JWV7HJFS","ralph-hats","Create, inspect, validate, explain, and improve Ralph hat collections. Use this skill whenever the user asks to make or refine a `.ralph\u002Fhats\u002F*.yml` workflow, debug hat routing, explain event topology, or tune a multi-hat Ralph run.","https:\u002F\u002Fgithub.com\u002Fflaviomartil\u002Fralph-jev\u002Fblob\u002Fmain\u002Fskills\u002Fralph-hats\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7DCY5Z7EGXE9S116KQ5EFJY","ralph-docs","Introspect, explain, and improve ralph-jev using the documentation shipped in its repository. Use this skill whenever the user asks questions about Ralph's behavior, wants to understand how a Ralph internal works (event loop, completion gate, judge evidence, Jev hooks, parallel loops, configuration), debug an unfamiliar failure mode, or propose a code change to the ralph-jev repo. The skill teaches the agent to answer from the repo's docs and source before guessing, and to scope improvements through the documented architecture rather than the local checkout alone.","https:\u002F\u002Fgithub.com\u002Fflaviomartil\u002Fralph-jev\u002Fblob\u002Fmain\u002Fskills\u002Fralph-docs\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7DCY37C342859GXBPYTN5EK","complex-test-skill","A directory-style test skill for smoke testing","https:\u002F\u002Fgithub.com\u002Fflaviomartil\u002Fralph-jev\u002Fblob\u002Fmain\u002Fcrates\u002Fralph-core\u002Ftests\u002Ffixtures\u002Fskills\u002Fcomplex-test-skill\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7DCXX2582CZB0ZK7213M7B3","tui-validate","Validates Terminal User Interface (TUI) output using freeze for screenshot capture and LLM-as-judge for semantic validation. Supports both visual (PNG\u002FSVG) and text-based validation modes.","https:\u002F\u002Fgithub.com\u002Fflaviomartil\u002Fralph-jev\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftui-validate\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M7DCXSQN75KTR4QG0PF3DNVM","tui-debug-in-pane","Use when you need to reproduce or debug TUI rendering issues (garbled output, broken streaming, layout corruption) by running ralph in a tmux split pane and capturing live output.","https:\u002F\u002Fgithub.com\u002Fflaviomartil\u002Fralph-jev\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftui-debug-in-pane\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M7DCXN8GMGHBX6KTNNTE80QV","tmux-terminal","Interactive terminal control via tmux for TUI apps, prompts, and long-running CLI workflows.","https:\u002F\u002Fgithub.com\u002Fflaviomartil\u002Fralph-jev\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftmux-terminal\u002FSKILL.md",[],[]]