[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74F3HBADPC873XCKK171NNX":3,"skill-same:01M74F3HBADPC873XCKK171NNX":46},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M74F3HBADPC873XCKK171NNX","gsd-quick",null,"Execute a quick task with GSD guarantees (atomic commits, state tracking) but skip optional agents","tamarillo-ai\u002Ftheta","tamarillo-ai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F264659913?v=4","01M732W8TW61PS979NJ2W4Z6XZ","tamarillo.ai","01M732W8VRBBGT4F0Q3B2HNGTQ",15,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Ftamarillo-ai\u002Ftheta\u002Fblob\u002Fmain\u002Ftest\u002Fcast-fixtures\u002Fcodex-cli\u002Fregression\u002Fscrimflow\u002F.codex\u002Fskills\u002Fgsd-quick\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: \"gsd-quick\"\ndescription: \"Execute a quick task with GSD guarantees (atomic commits, state tracking) but skip optional agents\"\nmetadata:\n  short-description: \"Execute a quick task with GSD guarantees (atomic commits, state tracking) but skip optional agents\"\n---\n\n\u003Ccodex_skill_adapter>\n## A. Skill Invocation\n- This skill is invoked by mentioning `$gsd-quick`.\n- Treat all user text after `$gsd-quick` as `{{GSD_ARGS}}`.\n- If no arguments are present, treat `{{GSD_ARGS}}` as empty.\n\n## B. AskUserQuestion → request_user_input Mapping\nGSD workflows use `AskUserQuestion` (Claude Code syntax). Translate to Codex `request_user_input`:\n\nParameter mapping:\n- `header` → `header`\n- `question` → `question`\n- Options formatted as `\"Label\" — description` → `{label: \"Label\", description: \"description\"}`\n- Generate `id` from header: lowercase, replace spaces with underscores\n\nBatched calls:\n- `AskUserQuestion([q1, q2])` → single `request_user_input` with multiple entries in `questions[]`\n\nMulti-select workaround:\n- Codex has no `multiSelect`. Use sequential single-selects, or present a numbered freeform list asking the user to enter comma-separated numbers.\n\nExecute mode fallback:\n- When `request_user_input` is rejected (Execute mode), present a plain-text numbered list and pick a reasonable default.\n\n## C. Task() → spawn_agent Mapping\nGSD workflows use `Task(...)` (Claude Code syntax). Translate to Codex collaboration tools:\n\nDirect mapping:\n- `Task(subagent_type=\"X\", prompt=\"Y\")` → `spawn_agent(agent_type=\"X\", message=\"Y\")`\n- `Task(model=\"...\")` → omit. `spawn_agent` has no inline `model` parameter;\n  GSD embeds the resolved per-agent model directly into each agent's `.toml`\n  at install time so `model_overrides` from `.planning\u002Fconfig.json` and\n  `~\u002F.gsd\u002Fdefaults.json` are honored automatically by Codex's agent router.\n- `fork_context: false` by default — GSD agents load their own context via `\u003Cfiles_to_read>` blocks\n\nSpawn restriction:\n- Codex restricts `spawn_agent` to cases where the user has explicitly\n  requested sub-agents. When automatic spawning is not permitted, do the\n  work inline in the current agent rather than attempting to force a spawn.\n\nParallel fan-out:\n- Spawn multiple agents → collect agent IDs → `wait(ids)` for all to complete\n\nResult parsing:\n- Look for structured markers in agent output: `CHECKPOINT`, `PLAN COMPLETE`, `SUMMARY`, etc.\n- `close_agent(id)` after collecting results from each agent\n\u003C\u002Fcodex_skill_adapter>\n\n\u003Cobjective>\nExecute small, ad-hoc tasks with GSD guarantees (atomic commits, STATE.md tracking).\n\nQuick mode is the same system with a shorter path:\n- Spawns gsd-planner (quick mode) + gsd-executor(s)\n- Quick tasks live in `.planning\u002Fquick\u002F` separate from planned phases\n- Updates STATE.md \"Quick Tasks Completed\" table (NOT ROADMAP.md)\n\n**Default:** Skips research, discussion, plan-checker, verifier. Use when you know exactly what to do.\n\n**`--discuss` flag:** Lightweight discussion phase before planning. Surfaces assumptions, clarifies gray areas, captures decisions in CONTEXT.md. Use when the task has ambiguity worth resolving upfront.\n\n**`--full` flag:** Enables the complete quality pipeline — discussion + research + plan-checking + verification. One flag for everything.\n\n**`--validate` flag:** Enables plan-checking (max 2 iterations) and post-execution verification only. Use when you want quality guarantees without discussion or research.\n\n**`--research` flag:** Spawns a focused research agent before planning. Investigates implementation approaches, library options, and pitfalls for the task. Use when you're unsure of the best approach.\n\nGranular flags are composable: `--discuss --research --validate` gives the same result as `--full`.\n\n**Subcommands:**\n- `list` — List all quick tasks with status\n- `status \u003Cslug>` — Show status of a specific quick task\n- `resume \u003Cslug>` — Resume a specific quick task by slug\n\u003C\u002Fobjective>\n\n\u003Cexecution_context>\n@C:\u002FUsers\u002Fsimon\u002FDocuments\u002FGitHub\u002Fscrimflow\u002F.codex\u002Fget-shit-done\u002Fworkflows\u002Fquick.md\n\u003C\u002Fexecution_context>\n\n\u003Ccontext>\n{{GSD_ARGS}}\n\nContext files are resolved inside the workflow (`init quick`) and delegated via `\u003Cfiles_to_read>` blocks.\n\u003C\u002Fcontext>\n\n\u003Cprocess>\n\n**Parse {{GSD_ARGS}} for subcommands FIRST:**\n\n- If {{GSD_ARGS}} starts with \"list\": SUBCMD=list\n- If {{GSD_ARGS}} starts with \"status \": SUBCMD=status, SLUG=remainder (strip whitespace, sanitize)\n- If {{GSD_ARGS}} starts with \"resume \": SUBCMD=resume, SLUG=remainder (strip whitespace, sanitize)\n- Otherwise: SUBCMD=run, pass full {{GSD_ARGS}} to the quick workflow as-is\n\n**Slug sanitization (for status and resume):** Strip any characters not matching `[a-z0-9-]`. Reject slugs longer than 60 chars or containing `..` or `\u002F`. If invalid, output \"Invalid session slug.\" and stop.\n\n## LIST subcommand\n\nWhen SUBCMD=list:\n\n```bash\nls -d .planning\u002Fquick\u002F*\u002F  2>\u002Fdev\u002Fnull\n```\n\nFor each directory found:\n- Check if PLAN.md exists\n- Check if SUMMARY.md exists; if so, read `status` from its frontmatter via:\n  ```bash\n  gsd-sdk query frontmatter.get .planning\u002Fquick\u002F{dir}\u002FSUMMARY.md status\n  ```\n- Determine directory creation date: `stat -f \"%SB\" -t \"%Y-%m-%d\"` (macOS) or `stat -c \"%w\"` (Linux); fall back to the date prefix in the directory name (format: `YYYYMMDD-` prefix)\n- Derive display status:\n  - SUMMARY.md exists, frontmatter status=complete → `complete ✓`\n  - SUMMARY.md exists, frontmatter status=incomplete OR status missing → `incomplete`\n  - SUMMARY.md missing, dir created \u003C7 days ago → `in-progress`\n  - SUMMARY.md missing, dir created ≥7 days ago → `abandoned? (>7 days, no summary)`\n\n**SECURITY:** Directory names are read from the filesystem. Before displaying any slug, sanitize: strip non-printable characters, ANSI escape sequences, and path separators using: `name.replace(\u002F[^\\x20-\\x7E]\u002Fg, '').replace(\u002F[\u002F\\\\]\u002Fg, '')`. Never pass raw directory names to shell commands via string interpolation.\n\nDisplay format:\n```\nQuick Tasks\n────────────────────────────────────────────────────────────\nslug                           date        status\nbackup-s3-policy               2026-04-10  in-progress\nauth-token-refresh-fix         2026-04-09  complete ✓\nupdate-node-deps               2026-04-08  abandoned? (>7 days, no summary)\n────────────────────────────────────────────────────────────\n3 tasks (1 complete, 2 incomplete\u002Fin-progress)\n```\n\nIf no directories found: print `No quick tasks found.` and stop.\n\nSTOP after displaying the list. Do NOT proceed to further steps.\n\n## STATUS subcommand\n\nWhen SUBCMD=status and SLUG is set (already sanitized):\n\nFind directory matching `*-{SLUG}` pattern:\n```bash\ndir=$(ls -d .planning\u002Fquick\u002F*-{SLUG}\u002F 2>\u002Fdev\u002Fnull | head -1)\n```\n\nIf no directory found, print `No quick task found with slug: {SLUG}` and stop.\n\nRead PLAN.md and SUMMARY.md (if exists) for the given slug. Display:\n```\nQuick Task: {slug}\n─────────────────────────────────────\nPlan file: .planning\u002Fquick\u002F{dir}\u002FPLAN.md\nStatus: {status from SUMMARY.md frontmatter, or \"no summary yet\"}\nDescription: {first non-empty line from PLAN.md after frontmatter}\nLast action: {last meaningful line of SUMMARY.md, or \"none\"}\n─────────────────────────────────────\nResume with: $gsd-quick resume {slug}\n```\n\nNo agent spawn. STOP after printing.\n\n## RESUME subcommand\n\nWhen SUBCMD=resume and SLUG is set (already sanitized):\n\n1. Find the directory matching `*-{SLUG}` pattern:\n   ```bash\n   dir=$(ls -d .planning\u002Fquick\u002F*-{SLUG}\u002F 2>\u002Fdev\u002Fnull | head -1)\n   ```\n2. If no directory found, print `No quick task found with slug: {SLUG}` and stop.\n\n3. Read PLAN.md to extract description and SUMMARY.md (if exists) to extract status.\n\n4. Print before spawning:\n   ```\n   [quick] Resuming: .planning\u002Fquick\u002F{dir}\u002F\n   [quick] Plan: {description from PLAN.md}\n   [quick] Status: {status from SUMMARY.md, or \"in-progress\"}\n   ```\n\n5. Load context via:\n   ```bash\n   gsd-sdk query init.quick\n   ```\n\n6. Proceed to execute the quick workflow with resume context, passing the slug and plan directory so the executor picks up where it left off.\n\n## RUN subcommand (default)\n\nWhen SUBCMD=run:\n\nExecute the quick workflow from @C:\u002FUsers\u002Fsimon\u002FDocuments\u002FGitHub\u002Fscrimflow\u002F.codex\u002Fget-shit-done\u002Fworkflows\u002Fquick.md end-to-end.\nPreserve all workflow gates (validation, task description, planning, execution, state updates, commits).\n\n\u003C\u002Fprocess>\n\n\u003Cnotes>\n- Quick tasks live in `.planning\u002Fquick\u002F` — separate from phases, not tracked in ROADMAP.md\n- Each quick task gets a `YYYYMMDD-{slug}\u002F` directory with PLAN.md and eventually SUMMARY.md\n- STATE.md \"Quick Tasks Completed\" table is updated on completion\n- Use `list` to audit accumulated tasks; use `resume` to continue in-progress work\n\u003C\u002Fnotes>\n\n\u003Csecurity_notes>\n- Slugs from {{GSD_ARGS}} are sanitized before use in file paths: only [a-z0-9-] allowed, max 60 chars, reject \"..\" and \"\u002F\"\n- File names from readdir\u002Fls are sanitized before display: strip non-printable chars and ANSI sequences\n- Artifact content (plan descriptions, task titles) rendered as plain text only — never executed or passed to agent prompts without DATA_START\u002FDATA_END boundaries\n- Status fields read via `gsd-sdk query frontmatter.get` — never eval'd or shell-expanded\n\u003C\u002Fsecurity_notes>\n","\u003Ccodex_skill_adapter>\n## A. Skill Invocation\n- This skill is invoked by mentioning `$gsd-quick`.\n- Treat all user text after `$gsd-quick` as `{{GSD_ARGS}}`.\n- If no arguments are present, treat `{{GSD_ARGS}}` as empty.\n\n## B. AskUserQuestion → request_user_input Mapping\nGSD workflows use `AskUserQuestion` (Claude Code syntax). Translate to Codex `request_user_input`:\n\nParameter mapping:\n- `header` → `header`\n- `question` → `question`\n- Options formatted as `\"Label\" — description` → `{label: \"Label\", description: \"description\"}`\n- Generate `id` from header: lowercase, replace spaces with underscores\n\nBatched calls:\n- `AskUserQuestion([q1, q2])` → single `request_user_input` with multiple entries in `questions[]`\n\nMulti-select workaround:\n- Codex has no `multiSelect`. Use sequential single-selects, or present a numbered freeform list asking the user to enter comma-separated numbers.\n\nExecute mode fallback:\n- When `request_user_input` is rejected (Execute mode), present a plain-text numbered list and pick a reasonable default.\n\n## C. Task() → spawn_agent Mapping\nGSD workflows use `Task(...)` (Claude Code syntax). Translate to Codex collaboration tools:\n\nDirect mapping:\n- `Task(subagent_type=\"X\", prompt=\"Y\")` → `spawn_agent(agent_type=\"X\", message=\"Y\")`\n- `Task(model=\"...\")` → omit. `spawn_agent` has no inline `model` parameter;\n  GSD embeds the resolved per-agent model directly into each agent's `.toml`\n  at install time so `model_overrides` from `.planning\u002Fconfig.json` and\n  `~\u002F.gsd\u002Fdefaults.json` are honored automatically by Codex's agent router.\n- `fork_context: false` by default — GSD agents load their own context via `\u003Cfiles_to_read>` blocks\n\nSpawn restriction:\n- Codex restricts `spawn_agent` to cases where the user has explicitly\n  requested sub-agents. When automatic spawning is not permitted, do the\n  work inline in the current agent rather than attempting to force a spawn.\n\nParallel fan-out:\n- Spawn multiple agents → collect agent IDs → `wait(ids)` for all to complete\n\nResult parsing:\n- Look for structured markers in agent output: `CHECKPOINT`, `PLAN COMPLETE`, `SUMMARY`, etc.\n- `close_agent(id)` after collecting results from each agent\n\u003C\u002Fcodex_skill_adapter>\n\n\u003Cobjective>\nExecute small, ad-hoc tasks with GSD guarantees (atomic commits, STATE.md tracking).\n\nQuick mode is the same system with a shorter path:\n- Spawns gsd-planner (quick mode) + gsd-executor(s)\n- Quick tasks live in `.planning\u002Fquick\u002F` separate from planned phases\n- Updates STATE.md \"Quick Tasks Completed\" table (NOT ROADMAP.md)\n\n**Default:** Skips research, discussion, plan-checker, verifier. Use when you know exactly what to do.\n\n**`--discuss` flag:** Lightweight discussion phase before planning. Surfaces assumptions, clarifies gray areas, captures decisions in CONTEXT.md. Use when the task has ambiguity worth resolving upfront.\n\n**`--full` flag:** Enables the complete quality pipeline — discussion + research + plan-checking + verification. One flag for everything.\n\n**`--validate` flag:** Enables plan-checking (max 2 iterations) and post-execution verification only. Use when you want quality guarantees without discussion or research.\n\n**`--research` flag:** Spawns a focused research agent before planning. Investigates implementation approaches, library options, and pitfalls for the task. Use when you're unsure of the best approach.\n\nGranular flags are composable: `--discuss --research --validate` gives the same result as `--full`.\n\n**Subcommands:**\n- `list` — List all quick tasks with status\n- `status \u003Cslug>` — Show status of a specific quick task\n- `resume \u003Cslug>` — Resume a specific quick task by slug\n\u003C\u002Fobjective>\n\n\u003Cexecution_context>\n@C:\u002FUsers\u002Fsimon\u002FDocuments\u002FGitHub\u002Fscrimflow\u002F.codex\u002Fget-shit-done\u002Fworkflows\u002Fquick.md\n\u003C\u002Fexecution_context>\n\n\u003Ccontext>\n{{GSD_ARGS}}\n\nContext files are resolved inside the workflow (`init quick`) and delegated via `\u003Cfiles_to_read>` blocks.\n\u003C\u002Fcontext>\n\n\u003Cprocess>\n\n**Parse {{GSD_ARGS}} for subcommands FIRST:**\n\n- If {{GSD_ARGS}} starts with \"list\": SUBCMD=list\n- If {{GSD_ARGS}} starts with \"status \": SUBCMD=status, SLUG=remainder (strip whitespace, sanitize)\n- If {{GSD_ARGS}} starts with \"resume \": SUBCMD=resume, SLUG=remainder (strip whitespace, sanitize)\n- Otherwise: SUBCMD=run, pass full {{GSD_ARGS}} to the quick workflow as-is\n\n**Slug sanitization (for status and resume):** Strip any characters not matching `[a-z0-9-]`. Reject slugs longer than 60 chars or containing `..` or `\u002F`. If invalid, output \"Invalid session slug.\" and stop.\n\n## LIST subcommand\n\nWhen SUBCMD=list:\n\n```bash\nls -d .planning\u002Fquick\u002F*\u002F  2>\u002Fdev\u002Fnull\n```\n\nFor each directory found:\n- Check if PLAN.md exists\n- Check if SUMMARY.md exists; if so, read `status` from its frontmatter via:\n  ```bash\n  gsd-sdk query frontmatter.get .planning\u002Fquick\u002F{dir}\u002FSUMMARY.md status\n  ```\n- Determine directory creation date: `stat -f \"%SB\" -t \"%Y-%m-%d\"` (macOS) or `stat -c \"%w\"` (Linux); fall back to the date prefix in the directory name (format: `YYYYMMDD-` prefix)\n- Derive display status:\n  - SUMMARY.md exists, frontmatter status=complete → `complete ✓`\n  - SUMMARY.md exists, frontmatter status=incomplete OR status missing → `incomplete`\n  - SUMMARY.md missing, dir created \u003C7 days ago → `in-progress`\n  - SUMMARY.md missing, dir created ≥7 days ago → `abandoned? (>7 days, no summary)`\n\n**SECURITY:** Directory names are read from the filesystem. Before displaying any slug, sanitize: strip non-printable characters, ANSI escape sequences, and path separators using: `name.replace(\u002F[^\\x20-\\x7E]\u002Fg, '').replace(\u002F[\u002F\\\\]\u002Fg, '')`. Never pass raw directory names to shell commands via string interpolation.\n\nDisplay format:\n```\nQuick Tasks\n────────────────────────────────────────────────────────────\nslug                           date        status\nbackup-s3-policy               2026-04-10  in-progress\nauth-token-refresh-fix         2026-04-09  complete ✓\nupdate-node-deps               2026-04-08  abandoned? (>7 days, no summary)\n────────────────────────────────────────────────────────────\n3 tasks (1 complete, 2 incomplete\u002Fin-progress)\n```\n\nIf no directories found: print `No quick tasks found.` and stop.\n\nSTOP after displaying the list. Do NOT proceed to further steps.\n\n## STATUS subcommand\n\nWhen SUBCMD=status and SLUG is set (already sanitized):\n\nFind directory matching `*-{SLUG}` pattern:\n```bash\ndir=$(ls -d .planning\u002Fquick\u002F*-{SLUG}\u002F 2>\u002Fdev\u002Fnull | head -1)\n```\n\nIf no directory found, print `No quick task found with slug: {SLUG}` and stop.\n\nRead PLAN.md and SUMMARY.md (if exists) for the given slug. Display:\n```\nQuick Task: {slug}\n─────────────────────────────────────\nPlan file: .planning\u002Fquick\u002F{dir}\u002FPLAN.md\nStatus: {status from SUMMARY.md frontmatter, or \"no summary yet\"}\nDescription: {first non-empty line from PLAN.md after frontmatter}\nLast action: {last meaningful line of SUMMARY.md, or \"none\"}\n─────────────────────────────────────\nResume with: $gsd-quick resume {slug}\n```\n\nNo agent spawn. STOP after printing.\n\n## RESUME subcommand\n\nWhen SUBCMD=resume and SLUG is set (already sanitized):\n\n1. Find the directory matching `*-{SLUG}` pattern:\n   ```bash\n   dir=$(ls -d .planning\u002Fquick\u002F*-{SLUG}\u002F 2>\u002Fdev\u002Fnull | head -1)\n   ```\n2. If no directory found, print `No quick task found with slug: {SLUG}` and stop.\n\n3. Read PLAN.md to extract description and SUMMARY.md (if exists) to extract status.\n\n4. Print before spawning:\n   ```\n   [quick] Resuming: .planning\u002Fquick\u002F{dir}\u002F\n   [quick] Plan: {description from PLAN.md}\n   [quick] Status: {status from SUMMARY.md, or \"in-progress\"}\n   ```\n\n5. Load context via:\n   ```bash\n   gsd-sdk query init.quick\n   ```\n\n6. Proceed to execute the quick workflow with resume context, passing the slug and plan directory so the executor picks up where it left off.\n\n## RUN subcommand (default)\n\nWhen SUBCMD=run:\n\nExecute the quick workflow from @C:\u002FUsers\u002Fsimon\u002FDocuments\u002FGitHub\u002Fscrimflow\u002F.codex\u002Fget-shit-done\u002Fworkflows\u002Fquick.md end-to-end.\nPreserve all workflow gates (validation, task description, planning, execution, state updates, commits).\n\n\u003C\u002Fprocess>\n\n\u003Cnotes>\n- Quick tasks live in `.planning\u002Fquick\u002F` — separate from phases, not tracked in ROADMAP.md\n- Each quick task gets a `YYYYMMDD-{slug}\u002F` directory with PLAN.md and eventually SUMMARY.md\n- STATE.md \"Quick Tasks Completed\" table is updated on completion\n- Use `list` to audit accumulated tasks; use `resume` to continue in-progress work\n\u003C\u002Fnotes>\n\n\u003Csecurity_notes>\n- Slugs from {{GSD_ARGS}} are sanitized before use in file paths: only [a-z0-9-] allowed, max 60 chars, reject \"..\" and \"\u002F\"\n- File names from readdir\u002Fls are sanitized before display: strip non-printable chars and ANSI sequences\n- Artifact content (plan descriptions, task titles) rendered as plain text only — never executed or passed to agent prompts without DATA_START\u002FDATA_END boundaries\n- Status fields read via `gsd-sdk query frontmatter.get` — never eval'd or shell-expanded\n\u003C\u002Fsecurity_notes>\n",{"name":5,"metadata":24,"description":7},{"short-description":7},"main","08c084f718b2b842cd53622ce0b1a1fb2888ccef","test\u002Fcast-fixtures\u002Fcodex-cli\u002Fregression\u002Fscrimflow\u002F.codex\u002Fskills\u002Fgsd-quick",1,"https:\u002F\u002Fgithub.com\u002Ftamarillo-ai\u002Ftheta","https:\u002F\u002Fgithub.com\u002Ftamarillo-ai","2026-07-15 23:48:12",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add tamarillo-ai\u002Ftheta --skill gsd-quick",{"tool":38,"command":39},"bunx","bunx skills add tamarillo-ai\u002Ftheta --skill gsd-quick",{"tool":41,"command":42},"pnpm","pnpm dlx skills add tamarillo-ai\u002Ftheta --skill gsd-quick","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftamarillo-ai\u002Ftheta\u002Fblob\u002Fmain\u002Ftest\u002Fcast-fixtures\u002Fcodex-cli\u002Fregression\u002Fscrimflow\u002F.codex\u002Fskills\u002Fgsd-quick\u002FSKILL.md",true,[],[47,54,61,69,76,83],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M74FCAJ0RRFRJRQES26329E7","deploy-app","Deploy the application to staging or production environments.","https:\u002F\u002Fgithub.com\u002Ftamarillo-ai\u002Ftheta\u002Fblob\u002Fmain\u002Ftest\u002Fcast-fixtures\u002Fcursor\u002Fskills\u002Fbasic\u002F.cursor\u002Fskills\u002Fdeploy-app\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M74FC8GPJGCS0KTGKS1CJZZS","deploy","Deploy the application to environments.","https:\u002F\u002Fgithub.com\u002Ftamarillo-ai\u002Ftheta\u002Fblob\u002Fmain\u002Ftest\u002Fcast-fixtures\u002Fcursor\u002Fcombined\u002Ffull-config\u002F.cursor\u002Fskills\u002Fdeploy\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M74FC5RT3VTNZEK1F7NX5380","building-native-ui","Complete guide for building beautiful apps with Expo Router. Covers fundamentals, styling, components, navigation, animations, patterns, and native tabs.","MIT","https:\u002F\u002Fgithub.com\u002Ftamarillo-ai\u002Ftheta\u002Fblob\u002Fmain\u002Ftest\u002Fcast-fixtures\u002Fcopilot\u002Fskills\u002Fwith-references\u002F.github\u002Fskills\u002Fbuilding-native-ui\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},"01M74FC1ZGP5R44HPGWWSW6P3B","create-section","Use when creating a new section for the AI Workshop presentation. Guides through title slide setup, layout choices, and content gathering. Activates when user wants to add a new topic section to the slideshow.","https:\u002F\u002Fgithub.com\u002Ftamarillo-ai\u002Ftheta\u002Fblob\u002Fmain\u002Ftest\u002Fcast-fixtures\u002Fcopilot\u002Fskills\u002Fbasic\u002F.github\u002Fskills\u002Fcreate-section\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},"01M74FBZXSZ7GVP0HCGNR1BVNH","ship-checker","Run a full pre-ship review for this repo. Use when asked if a change is ready to deploy, publish, or ship.","https:\u002F\u002Fgithub.com\u002Ftamarillo-ai\u002Ftheta\u002Fblob\u002Fmain\u002Ftest\u002Fcast-fixtures\u002Fcopilot\u002Fcombined\u002Feverything\u002F.github\u002Fskills\u002Fship-checker\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},"01M74FBY4N2E3ZERWBRM4S3DE6","lint-check","Run repository linters and report failures.","https:\u002F\u002Fgithub.com\u002Ftamarillo-ai\u002Ftheta\u002Fblob\u002Fmain\u002Ftest\u002Fcast-fixtures\u002Fcodex-cli\u002Fskills\u002Fagents-path\u002F.agents\u002Fskills\u002Flint-check\u002FSKILL.md",[],[]]