[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CQAT10W929KXPBNTXV3DBA":3,"skill-same:01M7CQAT10W929KXPBNTXV3DBA":43},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":13,"repositoryHtmlUrl":26,"repositoryHomepageUrl":6,"ownerHtmlUrl":27,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":28,"install":29,"resources":42},"01M7CQAT10W929KXPBNTXV3DBA","repos-sync",null,"Use to update clones of your repositories under repos\u002F and see their branch, lag and uncommitted changes.","maximk777\u002Fopencode-config","maximk777","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F205286132?v=4","01M7CQ4VVPFQ3MDCXJBFB0HPTZ","01M7CQ4VWA2GG0H2CNNREZ9AN9",0,"MIT","https:\u002F\u002Fgithub.com\u002Fmaximk777\u002Fopencode-config\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fnormalize-team\u002F.agents\u002Fskills\u002Frepos-sync\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: repos-sync\ndescription: Use to update clones of your repositories under repos\u002F and see their branch, lag and uncommitted changes.\n---\n# Repository sync\n\n## Steps\n1. Go to the workspace root: the nearest directory, walking up from where you are, where `test -f .agents\u002Fkit.json` succeeds. Run every later command in that directory.\n2. If `.local\u002Frepos.json` does not exist, stop and run the `init` skill first: follow `.agents\u002Fskills\u002Finit\u002FSKILL.md`. When `init` finishes, continue with step 3.\n3. Build the repository list. Open `repos.json`. When the person asked for the option `all`, take every entry of `repositories`. Otherwise open `.local\u002Frepos.json` and read its `role`; take every entry of `repositories` whose `roles` list contains that role. Then, still in `.local\u002Frepos.json`, for every name in `add`, take the entry of `repos.json` with that `name`; when there is none, put the name in the list anyway and mark it \"not in repos.json\". Remove every entry whose `name` is in `skip`. When a `name` appears more than once, for example a name in `add` that the role already includes, keep it once. Use each entry's `name`, `remote`, `default_branch` and `status`. An entry whose `status` is `planned` does not exist yet and may have no `remote`, so it is never cloned or fetched.\n4. An error line below is the first output line that starts with `fatal:` or `error:`. Lines such as `Cloning into` are not the error. When no line starts with `fatal:` or `error:`, the error line is the last non-empty output line.\n5. For each repository in the list, one at a time, do these sub-steps in order. Collect each row for the final table in step 6; do not print rows yet. When a sub-step says \"next repository\", record the row for the table and start sub-step a for the next repository.\n   - a. When the name is marked \"not in repos.json\", the action is `not in repos.json`, write `-` for branch, behind default and dirty, run no git command, and go to the next repository. When the entry's `status` is `planned`, the action is `planned`, write `-` for branch, behind default and dirty, run no git command, and go to the next repository. Otherwise run `ls -d repos\u002F\u003Cname>`. When it exists, go to sub-step c.\n   - b. Run `GIT_TERMINAL_PROMPT=0 git clone \u003Cremote> repos\u002F\u003Cname>`. `GIT_TERMINAL_PROMPT=0` makes a clone that needs a password fail instead of waiting for input. When it succeeds, the action is `cloned`; go to sub-step d. When it fails, the action is `clone failed: \u003Cerror line>`, write `-` for branch, behind default and dirty, and go to the next repository.\n   - c. Run `GIT_TERMINAL_PROMPT=0 git -C repos\u002F\u003Cname> fetch --prune`. When it fails, remember `fetch failed: \u003Cerror line>` and continue with sub-step d.\n   - d. Run `git -C repos\u002F\u003Cname> rev-parse --abbrev-ref HEAD`; its output is the branch. Run `git -C repos\u002F\u003Cname> status --porcelain`; any output means dirty `yes`, no output means dirty `no`.\n   - e. When sub-step c failed, the action is `fetch failed: \u003Cerror line>`, write `-` for behind default, and go to the next repository. The branch and dirty values from sub-step d stay in the row.\n   - f. Run `git -C repos\u002F\u003Cname> rev-parse --verify --quiet origin\u002F\u003Cdefault_branch>`. When it prints nothing, the action is `no origin\u002F\u003Cdefault_branch>`, write `-` for behind default, and go to the next repository. Do not merge.\n   - g. Run `git -C repos\u002F\u003Cname> rev-list --count HEAD..origin\u002F\u003Cdefault_branch>`. The number is behind default. Remember it before any merge.\n   - h. When the action is `cloned`, keep it and go to the next repository.\n   - i. When the branch is not `default_branch`, the action is `skipped: on branch \u003Cbranch>`; go to the next repository. When dirty is `yes`, the action is `skipped: uncommitted changes`; go to the next repository.\n   - j. When behind default is `0`, the action is `up to date`; go to the next repository.\n   - k. Run `git -C repos\u002F\u003Cname> merge --ff-only origin\u002F\u003Cdefault_branch>`. When it succeeds, the action is `fast-forwarded` and behind default becomes `0`. When it fails, the action is `diverged, not changed` and behind default keeps the number from sub-step g.\n6. Report a table with one row per repository, in list order:\n    ```\n    | Repository | Branch | Behind default | Dirty | Action |\n    |---|---|---|---|---|\n    | \u003Cname> | \u003Cbranch> | \u003Ccount> | \u003Cyes or no> | \u003Caction> |\n    ```\n\n## Never\n- `git checkout`\n- `git switch`\n- `git stash`\n- `git reset`\n- `git clean`\n- `git pull`, with merge or with rebase\n- deleting files in `repos\u002F`\n\n## Without Python\nThis skill needs no Python. It changes only clones under `repos\u002F`, which git ignores, so there is nothing to check.\n","# Repository sync\n\n## Steps\n1. Go to the workspace root: the nearest directory, walking up from where you are, where `test -f .agents\u002Fkit.json` succeeds. Run every later command in that directory.\n2. If `.local\u002Frepos.json` does not exist, stop and run the `init` skill first: follow `.agents\u002Fskills\u002Finit\u002FSKILL.md`. When `init` finishes, continue with step 3.\n3. Build the repository list. Open `repos.json`. When the person asked for the option `all`, take every entry of `repositories`. Otherwise open `.local\u002Frepos.json` and read its `role`; take every entry of `repositories` whose `roles` list contains that role. Then, still in `.local\u002Frepos.json`, for every name in `add`, take the entry of `repos.json` with that `name`; when there is none, put the name in the list anyway and mark it \"not in repos.json\". Remove every entry whose `name` is in `skip`. When a `name` appears more than once, for example a name in `add` that the role already includes, keep it once. Use each entry's `name`, `remote`, `default_branch` and `status`. An entry whose `status` is `planned` does not exist yet and may have no `remote`, so it is never cloned or fetched.\n4. An error line below is the first output line that starts with `fatal:` or `error:`. Lines such as `Cloning into` are not the error. When no line starts with `fatal:` or `error:`, the error line is the last non-empty output line.\n5. For each repository in the list, one at a time, do these sub-steps in order. Collect each row for the final table in step 6; do not print rows yet. When a sub-step says \"next repository\", record the row for the table and start sub-step a for the next repository.\n   - a. When the name is marked \"not in repos.json\", the action is `not in repos.json`, write `-` for branch, behind default and dirty, run no git command, and go to the next repository. When the entry's `status` is `planned`, the action is `planned`, write `-` for branch, behind default and dirty, run no git command, and go to the next repository. Otherwise run `ls -d repos\u002F\u003Cname>`. When it exists, go to sub-step c.\n   - b. Run `GIT_TERMINAL_PROMPT=0 git clone \u003Cremote> repos\u002F\u003Cname>`. `GIT_TERMINAL_PROMPT=0` makes a clone that needs a password fail instead of waiting for input. When it succeeds, the action is `cloned`; go to sub-step d. When it fails, the action is `clone failed: \u003Cerror line>`, write `-` for branch, behind default and dirty, and go to the next repository.\n   - c. Run `GIT_TERMINAL_PROMPT=0 git -C repos\u002F\u003Cname> fetch --prune`. When it fails, remember `fetch failed: \u003Cerror line>` and continue with sub-step d.\n   - d. Run `git -C repos\u002F\u003Cname> rev-parse --abbrev-ref HEAD`; its output is the branch. Run `git -C repos\u002F\u003Cname> status --porcelain`; any output means dirty `yes`, no output means dirty `no`.\n   - e. When sub-step c failed, the action is `fetch failed: \u003Cerror line>`, write `-` for behind default, and go to the next repository. The branch and dirty values from sub-step d stay in the row.\n   - f. Run `git -C repos\u002F\u003Cname> rev-parse --verify --quiet origin\u002F\u003Cdefault_branch>`. When it prints nothing, the action is `no origin\u002F\u003Cdefault_branch>`, write `-` for behind default, and go to the next repository. Do not merge.\n   - g. Run `git -C repos\u002F\u003Cname> rev-list --count HEAD..origin\u002F\u003Cdefault_branch>`. The number is behind default. Remember it before any merge.\n   - h. When the action is `cloned`, keep it and go to the next repository.\n   - i. When the branch is not `default_branch`, the action is `skipped: on branch \u003Cbranch>`; go to the next repository. When dirty is `yes`, the action is `skipped: uncommitted changes`; go to the next repository.\n   - j. When behind default is `0`, the action is `up to date`; go to the next repository.\n   - k. Run `git -C repos\u002F\u003Cname> merge --ff-only origin\u002F\u003Cdefault_branch>`. When it succeeds, the action is `fast-forwarded` and behind default becomes `0`. When it fails, the action is `diverged, not changed` and behind default keeps the number from sub-step g.\n6. Report a table with one row per repository, in list order:\n    ```\n    | Repository | Branch | Behind default | Dirty | Action |\n    |---|---|---|---|---|\n    | \u003Cname> | \u003Cbranch> | \u003Ccount> | \u003Cyes or no> | \u003Caction> |\n    ```\n\n## Never\n- `git checkout`\n- `git switch`\n- `git stash`\n- `git reset`\n- `git clean`\n- `git pull`, with merge or with rebase\n- deleting files in `repos\u002F`\n\n## Without Python\nThis skill needs no Python. It changes only clones under `repos\u002F`, which git ignores, so there is nothing to check.\n",{"name":5,"description":7},"main","84be7f584d7d6998f014342de57ee511e9596cd2","tests\u002Ffixtures\u002Fnormalize-team\u002F.agents\u002Fskills\u002Frepos-sync","https:\u002F\u002Fgithub.com\u002Fmaximk777\u002Fopencode-config","https:\u002F\u002Fgithub.com\u002Fmaximk777","2026-10-30 20:22:07",{"source":8,"skillName":5,"commands":30,"prompt":40,"zipAvailable":41},[31,34,37],{"tool":32,"command":33},"npx","npx skills add maximk777\u002Fopencode-config --skill repos-sync",{"tool":35,"command":36},"bunx","bunx skills add maximk777\u002Fopencode-config --skill repos-sync",{"tool":38,"command":39},"pnpm","pnpm dlx skills add maximk777\u002Fopencode-config --skill repos-sync","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmaximk777\u002Fopencode-config\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fnormalize-team\u002F.agents\u002Fskills\u002Frepos-sync\u002FSKILL.md",true,[],[44,51,58,65,72,79],{"skillNo":45,"name":46,"nameZh":6,"description":47,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":48,"categories":49,"keywords":50,"publishedAt":18},"01M7CQCJ5WYEQM6E1T0RDVKWAY","verify","Use when a change in __SERVICE__ must be checked before review","https:\u002F\u002Fgithub.com\u002Fmaximk777\u002Fopencode-config\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fworkspace-repo-kits\u002Fkit-1.1.0\u002Ffiles\u002Fskills\u002Fverify\u002FSKILL.md",[],[],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":18},"01M7CQCG5MCSNDNS98TGAGXP7E","work-record","Use when you finished work on a tracker task and it must be recorded in the workspace through a merge request.","https:\u002F\u002Fgithub.com\u002Fmaximk777\u002Fopencode-config\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fnormalize-team\u002F.claude\u002Fskills\u002Fwork-record\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":18},"01M7CQCDGQBT2GXCKQAC1B5R0R","task-new","Use to create one story in a stream from the stream profile's story template, link it from its scope screens and open a merge request.","https:\u002F\u002Fgithub.com\u002Fmaximk777\u002Fopencode-config\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fnormalize-team\u002F.claude\u002Fskills\u002Ftask-new\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":18},"01M7CQC93WN986EY48RFPZHZM7","task-decompose","Use to split a stream at the decomposition stage into stories - list scope screens without a story, create the accepted stories and close the stage through a merge request.","https:\u002F\u002Fgithub.com\u002Fmaximk777\u002Fopencode-config\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fnormalize-team\u002F.claude\u002Fskills\u002Ftask-decompose\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M7CQC5FZQWPTBK0J0FHWS513","task-context","Use to gather the context of a story key or a tracker id - its story, stream stage, scope screens, repositories, decisions, mockups and work records.","https:\u002F\u002Fgithub.com\u002Fmaximk777\u002Fopencode-config\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fnormalize-team\u002F.claude\u002Fskills\u002Ftask-context\u002FSKILL.md",[],[],{"skillNo":80,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":18},"01M7CQC1Q2YECCM2N9TPJAAJQA","https:\u002F\u002Fgithub.com\u002Fmaximk777\u002Fopencode-config\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fnormalize-team\u002F.claude\u002Fskills\u002Frepos-sync\u002FSKILL.md",[],[]]