[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CQBK9SQQWEFM1YK5RAZNCT":3,"skill-same:01M7CQBK9SQQWEFM1YK5RAZNCT":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},"01M7CQBK9SQQWEFM1YK5RAZNCT","init",null,"Use when .local\u002F is missing in this workspace, or to re-check your role, repositories and environment.","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.claude\u002Fskills\u002Finit\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: init\ndescription: Use when .local\u002F is missing in this workspace, or to re-check your role, repositories and environment.\n---\n# Init\n\nRunning `init` again is safe: it keeps existing values and only adds what is missing.\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. When you reach `\u002F` and no directory on the way had `.agents\u002Fkit.json`, stop, tell the person \"This is not a workspace: no .agents\u002Fkit.json found in this directory or above\", and do nothing else.\n2. List the roles with `ls .agents\u002Froles`. A role is a file name without `.md`, for example `backend.md` is role `backend`. If `.local\u002Frepos.json` exists, run `grep '\"role\"' .local\u002Frepos.json`. When it shows a role that is not empty and is in the list, use that role and tell the person \"Using role \u003Crole> from .local\u002Frepos.json\". Otherwise show the list, ask the person to choose one role, and wait for the answer. Never pick a role yourself.\n3. Run `mkdir -p .local\u002Fdrafts .local\u002Fhandoffs`.\n4. If `.local\u002Frepos.json` does not exist, run `cp .agents\u002Ftemplates\u002Flocal\u002Frepos.json .local\u002Frepos.json`. In every case, whether the file was just copied or already existed, open `.local\u002Frepos.json` and set the `role` line to `\"role\": \"\u003Crole>\",`. Keep `add` and `skip` as they are.\n5. Open `.agents\u002Fenv.schema.json`. Every entry of `variables` has `name`, `issued_by` and `how_to_get`.\n   - Never open `.local\u002Fenv` with a file editor, a read tool or a write tool. Reading it puts token values into your transcript, and a write tool can replace the whole file and lose values the person already filled in. Change `.local\u002Fenv` only with the `printf` commands below, and find names in it only with the `grep ... | cut -d= -f1` command below, which prints names and never values.\n   - Apostrophe rule: before you put `\u003Cissued_by>` or `\u003Chow_to_get>` into a `printf` command, replace every `'` inside them with `'\\''`. For example `the team's admin` becomes `the team'\\''s admin`.\n   - To add the variable block for one variable, run `printf '%s\\n' '# \u003Cname>: issued by \u003Cissued_by>; \u003Chow_to_get>' '\u003Cname>=' >> .local\u002Fenv`. Use `>>`, never `>`, so existing lines stay.\n   - If `.local\u002Fenv` does not exist (`test -f .local\u002Fenv` fails), run `printf '%s\\n' '# Personal tokens for this workspace. Never commit, copy or print this file.' > .local\u002Fenv` to create it with the header line. Then add the variable block for every variable, in schema order.\n   - If `.local\u002Fenv` exists, first run `test -z \"$(tail -c1 .local\u002Fenv)\" || printf '\\n' >> .local\u002Fenv`. It prints nothing and adds a final newline when the file lacks one, so an append does not glue a new line onto the last value. Then run `grep -E '^[A-Za-z_][A-Za-z0-9_]*=' .local\u002Fenv | cut -d= -f1` to list the names it already has. For every schema variable whose `name` is not in that output, add its variable block. Do not change any other line.\n6. Set the `.local\u002Fenv` permissions:\n   - If step 5 just created `.local\u002Fenv`, run `chmod 600 .local\u002Fenv` and remember \"created with 600\". Skip the rest of this step.\n   - Otherwise run `ls -l .local\u002Fenv` and look at the first 10 characters. If they are not `-rw-------`, run `chmod 600 .local\u002Fenv` and remember \"permissions fixed (were \u003Cfirst 10 characters>)\". If they are `-rw-------`, remember \"already 600\".\n7. Build the repository list. Open `repos.json`. Take every entry of `repositories` whose `roles` list contains the role. Open `.local\u002Frepos.json`. For every name in `add`, take the entry of `repos.json` with that `name`; when there is none, mark the name `failed` with \"not in repos.json\", do not clone it in step 8, and keep it for the step 10 report. 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` and `status`. Mark every entry whose `status` is `planned` as `planned`: a planned repository does not exist yet and may have no `remote`, so it is never cloned.\n8. For each repository in the list, one at a time:\n   - When it is marked `planned`, run no command and go to the next repository.\n   - Run `ls -d repos\u002F\u003Cname>`. When it exists, mark it `present` and go to the next repository.\n   - Otherwise 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.\n   - When the command succeeds, mark it `cloned`. When it fails, mark it `failed` with the first output line that starts with `fatal:` or `error:` (the `Cloning into` line is not the error). When no line starts with `fatal:` or `error:`, use the last non-empty output line instead. Then continue with the next repository.\n9. Collect the environment, one command each:\n   - `git --version`.\n   - `command -v glab`: output means `installed`, no output means `missing`.\n   - `command -v gh`: output means `installed`, no output means `missing`.\n   - `command -v python3`: output means `installed`, no output means `missing`.\n   - `grep -E '^[A-Za-z_][A-Za-z0-9_]*=$' .local\u002Fenv | cut -d= -f1`: the names of empty variables. This command prints only names. Never run `cat .local\u002Fenv` and never print a value.\n10. Report to the person, in this order: role; each repository from step 8 with `cloned`, `present`, `planned` or `failed` and its error, and each `add` name from step 7 that is not in `repos.json` as `\u003Cname>: failed: not in repos.json`; git version; glab, gh and python3 as `installed` or `missing`; empty variables by name, or `none`; the `.local\u002Fenv` permissions note from step 6.\n11. Do not create a branch and do not commit. `init` changes only `.local\u002F` and `repos\u002F`, which git ignores.\n\n## Example\nSchema `.agents\u002Fenv.schema.json`:\n\n```json\n{\n  \"variables\": [\n    {\"name\": \"TRACKER_TOKEN\", \"issued_by\": \"the tracker admin\", \"how_to_get\": \"request it in the access portal\"}\n  ]\n}\n```\n\nNew `.local\u002Fenv`:\n\n```\n# Personal tokens for this workspace. Never commit, copy or print this file.\n# TRACKER_TOKEN: issued by the tracker admin; request it in the access portal\nTRACKER_TOKEN=\n```\n\nReport:\n\n```\nRole: backend\nRepositories:\n- payments: cloned\n- ledger: present\n- risks-front: planned\n- billing-legacy: failed: fatal: could not read Username for 'https:\u002F\u002Fgit.example.com': terminal prompts disabled\ngit: git version 2.43.0\nglab: installed\ngh: missing\npython3: installed\nEmpty variables: TRACKER_TOKEN\n.local\u002Fenv: created with 600\n```\n\n## Without Python\nThis skill needs no Python: every step uses shell commands and git. When `command -v python3` prints nothing, the report lists `python3: missing`.\n","# Init\n\nRunning `init` again is safe: it keeps existing values and only adds what is missing.\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. When you reach `\u002F` and no directory on the way had `.agents\u002Fkit.json`, stop, tell the person \"This is not a workspace: no .agents\u002Fkit.json found in this directory or above\", and do nothing else.\n2. List the roles with `ls .agents\u002Froles`. A role is a file name without `.md`, for example `backend.md` is role `backend`. If `.local\u002Frepos.json` exists, run `grep '\"role\"' .local\u002Frepos.json`. When it shows a role that is not empty and is in the list, use that role and tell the person \"Using role \u003Crole> from .local\u002Frepos.json\". Otherwise show the list, ask the person to choose one role, and wait for the answer. Never pick a role yourself.\n3. Run `mkdir -p .local\u002Fdrafts .local\u002Fhandoffs`.\n4. If `.local\u002Frepos.json` does not exist, run `cp .agents\u002Ftemplates\u002Flocal\u002Frepos.json .local\u002Frepos.json`. In every case, whether the file was just copied or already existed, open `.local\u002Frepos.json` and set the `role` line to `\"role\": \"\u003Crole>\",`. Keep `add` and `skip` as they are.\n5. Open `.agents\u002Fenv.schema.json`. Every entry of `variables` has `name`, `issued_by` and `how_to_get`.\n   - Never open `.local\u002Fenv` with a file editor, a read tool or a write tool. Reading it puts token values into your transcript, and a write tool can replace the whole file and lose values the person already filled in. Change `.local\u002Fenv` only with the `printf` commands below, and find names in it only with the `grep ... | cut -d= -f1` command below, which prints names and never values.\n   - Apostrophe rule: before you put `\u003Cissued_by>` or `\u003Chow_to_get>` into a `printf` command, replace every `'` inside them with `'\\''`. For example `the team's admin` becomes `the team'\\''s admin`.\n   - To add the variable block for one variable, run `printf '%s\\n' '# \u003Cname>: issued by \u003Cissued_by>; \u003Chow_to_get>' '\u003Cname>=' >> .local\u002Fenv`. Use `>>`, never `>`, so existing lines stay.\n   - If `.local\u002Fenv` does not exist (`test -f .local\u002Fenv` fails), run `printf '%s\\n' '# Personal tokens for this workspace. Never commit, copy or print this file.' > .local\u002Fenv` to create it with the header line. Then add the variable block for every variable, in schema order.\n   - If `.local\u002Fenv` exists, first run `test -z \"$(tail -c1 .local\u002Fenv)\" || printf '\\n' >> .local\u002Fenv`. It prints nothing and adds a final newline when the file lacks one, so an append does not glue a new line onto the last value. Then run `grep -E '^[A-Za-z_][A-Za-z0-9_]*=' .local\u002Fenv | cut -d= -f1` to list the names it already has. For every schema variable whose `name` is not in that output, add its variable block. Do not change any other line.\n6. Set the `.local\u002Fenv` permissions:\n   - If step 5 just created `.local\u002Fenv`, run `chmod 600 .local\u002Fenv` and remember \"created with 600\". Skip the rest of this step.\n   - Otherwise run `ls -l .local\u002Fenv` and look at the first 10 characters. If they are not `-rw-------`, run `chmod 600 .local\u002Fenv` and remember \"permissions fixed (were \u003Cfirst 10 characters>)\". If they are `-rw-------`, remember \"already 600\".\n7. Build the repository list. Open `repos.json`. Take every entry of `repositories` whose `roles` list contains the role. Open `.local\u002Frepos.json`. For every name in `add`, take the entry of `repos.json` with that `name`; when there is none, mark the name `failed` with \"not in repos.json\", do not clone it in step 8, and keep it for the step 10 report. 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` and `status`. Mark every entry whose `status` is `planned` as `planned`: a planned repository does not exist yet and may have no `remote`, so it is never cloned.\n8. For each repository in the list, one at a time:\n   - When it is marked `planned`, run no command and go to the next repository.\n   - Run `ls -d repos\u002F\u003Cname>`. When it exists, mark it `present` and go to the next repository.\n   - Otherwise 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.\n   - When the command succeeds, mark it `cloned`. When it fails, mark it `failed` with the first output line that starts with `fatal:` or `error:` (the `Cloning into` line is not the error). When no line starts with `fatal:` or `error:`, use the last non-empty output line instead. Then continue with the next repository.\n9. Collect the environment, one command each:\n   - `git --version`.\n   - `command -v glab`: output means `installed`, no output means `missing`.\n   - `command -v gh`: output means `installed`, no output means `missing`.\n   - `command -v python3`: output means `installed`, no output means `missing`.\n   - `grep -E '^[A-Za-z_][A-Za-z0-9_]*=$' .local\u002Fenv | cut -d= -f1`: the names of empty variables. This command prints only names. Never run `cat .local\u002Fenv` and never print a value.\n10. Report to the person, in this order: role; each repository from step 8 with `cloned`, `present`, `planned` or `failed` and its error, and each `add` name from step 7 that is not in `repos.json` as `\u003Cname>: failed: not in repos.json`; git version; glab, gh and python3 as `installed` or `missing`; empty variables by name, or `none`; the `.local\u002Fenv` permissions note from step 6.\n11. Do not create a branch and do not commit. `init` changes only `.local\u002F` and `repos\u002F`, which git ignores.\n\n## Example\nSchema `.agents\u002Fenv.schema.json`:\n\n```json\n{\n  \"variables\": [\n    {\"name\": \"TRACKER_TOKEN\", \"issued_by\": \"the tracker admin\", \"how_to_get\": \"request it in the access portal\"}\n  ]\n}\n```\n\nNew `.local\u002Fenv`:\n\n```\n# Personal tokens for this workspace. Never commit, copy or print this file.\n# TRACKER_TOKEN: issued by the tracker admin; request it in the access portal\nTRACKER_TOKEN=\n```\n\nReport:\n\n```\nRole: backend\nRepositories:\n- payments: cloned\n- ledger: present\n- risks-front: planned\n- billing-legacy: failed: fatal: could not read Username for 'https:\u002F\u002Fgit.example.com': terminal prompts disabled\ngit: git version 2.43.0\nglab: installed\ngh: missing\npython3: installed\nEmpty variables: TRACKER_TOKEN\n.local\u002Fenv: created with 600\n```\n\n## Without Python\nThis skill needs no Python: every step uses shell commands and git. When `command -v python3` prints nothing, the report lists `python3: missing`.\n",{"name":5,"description":7},"main","84be7f584d7d6998f014342de57ee511e9596cd2","tests\u002Ffixtures\u002Fnormalize-team\u002F.claude\u002Fskills\u002Finit","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 init",{"tool":35,"command":36},"bunx","bunx skills add maximk777\u002Fopencode-config --skill init",{"tool":38,"command":39},"pnpm","pnpm dlx skills add maximk777\u002Fopencode-config --skill init","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmaximk777\u002Fopencode-config\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fnormalize-team\u002F.claude\u002Fskills\u002Finit\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":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M7CQC1Q2YECCM2N9TPJAAJQA","repos-sync","Use to update clones of your repositories under repos\u002F and see their branch, lag and uncommitted changes.","https:\u002F\u002Fgithub.com\u002Fmaximk777\u002Fopencode-config\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fnormalize-team\u002F.claude\u002Fskills\u002Frepos-sync\u002FSKILL.md",[],[]]