[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CCDSDPYYNEDERHP01N30PT":3,"skill-same:01M6CCDSDPYYNEDERHP01N30PT":86},{"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":27,"linkOnly":28,"markdownContent":29,"markdownBody":30,"frontMatter":31,"refName":33,"commitSha":34,"skillDirectory":35,"forksCount":14,"repositoryHtmlUrl":36,"repositoryHomepageUrl":37,"ownerHtmlUrl":38,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":39,"install":40,"resources":53},"01M6CCDSDPYYNEDERHP01N30PT","gsd:milestone-sprint",null,"Run entire milestone autonomously with Codex validation. Auto-detects current milestone, executes all phases, and runs audit.","baisharg\u002FASTN","baisharg","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F204916775?v=4","01M6CC8XHZYVK2DR22FZ1BESCG","BAISH","01M6CC8XP400QZ9DXAWTC8EG3X",2,"AGPL-3.0","https:\u002F\u002Fgithub.com\u002Fbaisharg\u002FASTN\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fgsd-milestone-sprint\u002FSKILL.md",[],[19,20,21,22,23,24,25,26],"gsd:milestone sprint","codex","run","validation","audit","interactive","auto","resume","2026-11-10 10:12:30",false,"---\nname: gsd:milestone-sprint\ndescription: Run entire milestone autonomously with Codex validation. Auto-detects current milestone, executes all phases, and runs audit.\nargument-hint: '[milestone] [--interactive] [--skip-codex] [--resume] [--complete]'\n---\n\n# Milestone Sprint\n\nRun an entire milestone autonomously, from current position to milestone completion.\n\n## How It Differs from `\u002Fgsd:sprint`\n\n| Aspect     | `\u002Fgsd:sprint`              | `\u002Fgsd:milestone-sprint`                   |\n| ---------- | -------------------------- | ----------------------------------------- |\n| Input      | Manual phase range (`3 6`) | Auto-detect from ROADMAP.md               |\n| Scope      | Arbitrary phases           | One complete milestone                    |\n| Discussion | Skips (assumes done)       | Auto-discuss via Claude ↔ Codex           |\n| Completion | Just finishes phases       | Optionally runs `\u002Fgsd:complete-milestone` |\n| State file | `SPRINT.md`                | `MILESTONE-SPRINT.md`                     |\n\n## Usage\n\n```bash\n# Run current milestone in YOLO mode (default - auto-continue, use defaults)\n\u002Fgsd:milestone-sprint\n\n# Run specific milestone\n\u002Fgsd:milestone-sprint v1.2\n\n# Interactive mode (pause between phases, prompt on warnings)\n\u002Fgsd:milestone-sprint --interactive\n\n# Skip codex validation (audit still runs)\n\u002Fgsd:milestone-sprint --skip-codex\n\n# Resume interrupted milestone sprint\n\u002Fgsd:milestone-sprint --resume\n\n# Auto-complete milestone when done (run audit → \u002Fgsd:complete-milestone)\n\u002Fgsd:milestone-sprint --complete\n```\n\n## Flow\n\n1. **Detect\u002Fparse milestone** → get phase range from ROADMAP.md\n2. **For each phase:**\n   - **Auto-discuss** (Claude ↔ Codex dialogue) → creates CONTEXT.md\n   - **Plan** (`\u002Fgsd:plan-phase`) → creates PLAN.md files\n   - **Execute** (`\u002Fgsd:execute-phase`) → runs tasks, creates SUMMARY.md\n   - **Codex reviews** at each step (unless --skip-codex)\n3. **Always run audit** (`\u002Fgsd:audit-milestone`) — halt if gaps found\n4. If `--complete`: run `\u002Fgsd:complete-milestone`\n5. Otherwise: stop, user finalizes manually\n\n## Auto-Discuss (Claude ↔ Codex Conversation)\n\nInstead of human Q&A, phases are discussed via AI dialogue:\n\n1. **Claude proposes** — Analyzes phase, makes decisions grounded in milestone goal\n2. **Codex challenges** — Plays devil's advocate, suggests alternatives\n3. **Claude incorporates** — Finalizes decisions, flags genuine uncertainties\n4. **Output** — CONTEXT.md with locked decisions + flagged items\n\nMax 5 rounds. Early exit if Codex returns `[READY]` with no questions.\n\n**Uncertainties:**\n\n- In **yolo mode**: Uses reasonable defaults, logs what was skipped\n- In **interactive mode**: Prompts user for flagged items only\n\n## Modes\n\n| Mode                              | Behavior                                                                    |\n| --------------------------------- | --------------------------------------------------------------------------- |\n| **YOLO** (default)                | Auto-continue, use defaults for uncertainties, only halt on critical issues |\n| **Interactive** (`--interactive`) | Pause between phases, prompt on warnings, ask about uncertainties           |\n| **No Codex** (`--skip-codex`)     | Skip Codex validation steps (audit still runs at end)                       |\n\n## State File\n\nCreates `.planning\u002FMILESTONE-SPRINT.md` with progress tracking:\n\n```yaml\n---\nstarted: '2024-01-25T...'\nmilestone: v1.2\nmilestone_name: 'Org CRM'\nmode: yolo\nphase_range: '11-16'\ncurrent_phase: 13\nphases_remaining: [14, 15, 16]\nstatus: running\nauto_complete: false\n---\n```\n\n## Execution\n\nThis runs in a tmux session so you can detach and reattach.\n\n```bash\nARGS=\"$ARGUMENTS\"\nSESSION_NAME=\"gsd-milestone\"\n\n# Find the script (project-local or global)\nif [[ -f \".claude\u002Fskills\u002Fgsd-milestone-sprint\u002Fscripts\u002Fmilestone-sprint.sh\" ]]; then\n  SCRIPT=\".claude\u002Fskills\u002Fgsd-milestone-sprint\u002Fscripts\u002Fmilestone-sprint.sh\"\nelse\n  SCRIPT=\"$HOME\u002F.claude\u002Fskills\u002Fgsd-milestone-sprint\u002Fscripts\u002Fmilestone-sprint.sh\"\nfi\n\n# Kill existing session if running, create new one\ntmux kill-session -t \"$SESSION_NAME\" 2>\u002Fdev\u002Fnull || true\ntmux new-session -d -s \"$SESSION_NAME\" -c \"$(pwd)\"\n\n# Run the milestone sprint script in the tmux session\ntmux send-keys -t \"$SESSION_NAME\" \"bash $SCRIPT $ARGS\" Enter\n\n# Tell user how to attach\necho \"\"\necho \"━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\"\necho \"Milestone Sprint started in tmux session: $SESSION_NAME\"\necho \"━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\"\necho \"\"\necho \"To attach and watch progress:\"\necho \"  tmux attach -t $SESSION_NAME\"\necho \"\"\necho \"To detach (while attached):\"\necho \"  Ctrl+b then d\"\necho \"\"\necho \"To check if still running:\"\necho \"  tmux has-session -t $SESSION_NAME 2>\u002Fdev\u002Fnull && echo 'Running' || echo 'Finished'\"\necho \"\"\n```\n\nThis executes the milestone autonomously in a bash loop, calling Claude for each phase operation.\n","# Milestone Sprint\n\nRun an entire milestone autonomously, from current position to milestone completion.\n\n## How It Differs from `\u002Fgsd:sprint`\n\n| Aspect     | `\u002Fgsd:sprint`              | `\u002Fgsd:milestone-sprint`                   |\n| ---------- | -------------------------- | ----------------------------------------- |\n| Input      | Manual phase range (`3 6`) | Auto-detect from ROADMAP.md               |\n| Scope      | Arbitrary phases           | One complete milestone                    |\n| Discussion | Skips (assumes done)       | Auto-discuss via Claude ↔ Codex           |\n| Completion | Just finishes phases       | Optionally runs `\u002Fgsd:complete-milestone` |\n| State file | `SPRINT.md`                | `MILESTONE-SPRINT.md`                     |\n\n## Usage\n\n```bash\n# Run current milestone in YOLO mode (default - auto-continue, use defaults)\n\u002Fgsd:milestone-sprint\n\n# Run specific milestone\n\u002Fgsd:milestone-sprint v1.2\n\n# Interactive mode (pause between phases, prompt on warnings)\n\u002Fgsd:milestone-sprint --interactive\n\n# Skip codex validation (audit still runs)\n\u002Fgsd:milestone-sprint --skip-codex\n\n# Resume interrupted milestone sprint\n\u002Fgsd:milestone-sprint --resume\n\n# Auto-complete milestone when done (run audit → \u002Fgsd:complete-milestone)\n\u002Fgsd:milestone-sprint --complete\n```\n\n## Flow\n\n1. **Detect\u002Fparse milestone** → get phase range from ROADMAP.md\n2. **For each phase:**\n   - **Auto-discuss** (Claude ↔ Codex dialogue) → creates CONTEXT.md\n   - **Plan** (`\u002Fgsd:plan-phase`) → creates PLAN.md files\n   - **Execute** (`\u002Fgsd:execute-phase`) → runs tasks, creates SUMMARY.md\n   - **Codex reviews** at each step (unless --skip-codex)\n3. **Always run audit** (`\u002Fgsd:audit-milestone`) — halt if gaps found\n4. If `--complete`: run `\u002Fgsd:complete-milestone`\n5. Otherwise: stop, user finalizes manually\n\n## Auto-Discuss (Claude ↔ Codex Conversation)\n\nInstead of human Q&A, phases are discussed via AI dialogue:\n\n1. **Claude proposes** — Analyzes phase, makes decisions grounded in milestone goal\n2. **Codex challenges** — Plays devil's advocate, suggests alternatives\n3. **Claude incorporates** — Finalizes decisions, flags genuine uncertainties\n4. **Output** — CONTEXT.md with locked decisions + flagged items\n\nMax 5 rounds. Early exit if Codex returns `[READY]` with no questions.\n\n**Uncertainties:**\n\n- In **yolo mode**: Uses reasonable defaults, logs what was skipped\n- In **interactive mode**: Prompts user for flagged items only\n\n## Modes\n\n| Mode                              | Behavior                                                                    |\n| --------------------------------- | --------------------------------------------------------------------------- |\n| **YOLO** (default)                | Auto-continue, use defaults for uncertainties, only halt on critical issues |\n| **Interactive** (`--interactive`) | Pause between phases, prompt on warnings, ask about uncertainties           |\n| **No Codex** (`--skip-codex`)     | Skip Codex validation steps (audit still runs at end)                       |\n\n## State File\n\nCreates `.planning\u002FMILESTONE-SPRINT.md` with progress tracking:\n\n```yaml\n---\nstarted: '2024-01-25T...'\nmilestone: v1.2\nmilestone_name: 'Org CRM'\nmode: yolo\nphase_range: '11-16'\ncurrent_phase: 13\nphases_remaining: [14, 15, 16]\nstatus: running\nauto_complete: false\n---\n```\n\n## Execution\n\nThis runs in a tmux session so you can detach and reattach.\n\n```bash\nARGS=\"$ARGUMENTS\"\nSESSION_NAME=\"gsd-milestone\"\n\n# Find the script (project-local or global)\nif [[ -f \".claude\u002Fskills\u002Fgsd-milestone-sprint\u002Fscripts\u002Fmilestone-sprint.sh\" ]]; then\n  SCRIPT=\".claude\u002Fskills\u002Fgsd-milestone-sprint\u002Fscripts\u002Fmilestone-sprint.sh\"\nelse\n  SCRIPT=\"$HOME\u002F.claude\u002Fskills\u002Fgsd-milestone-sprint\u002Fscripts\u002Fmilestone-sprint.sh\"\nfi\n\n# Kill existing session if running, create new one\ntmux kill-session -t \"$SESSION_NAME\" 2>\u002Fdev\u002Fnull || true\ntmux new-session -d -s \"$SESSION_NAME\" -c \"$(pwd)\"\n\n# Run the milestone sprint script in the tmux session\ntmux send-keys -t \"$SESSION_NAME\" \"bash $SCRIPT $ARGS\" Enter\n\n# Tell user how to attach\necho \"\"\necho \"━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\"\necho \"Milestone Sprint started in tmux session: $SESSION_NAME\"\necho \"━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\"\necho \"\"\necho \"To attach and watch progress:\"\necho \"  tmux attach -t $SESSION_NAME\"\necho \"\"\necho \"To detach (while attached):\"\necho \"  Ctrl+b then d\"\necho \"\"\necho \"To check if still running:\"\necho \"  tmux has-session -t $SESSION_NAME 2>\u002Fdev\u002Fnull && echo 'Running' || echo 'Finished'\"\necho \"\"\n```\n\nThis executes the milestone autonomously in a bash loop, calling Claude for each phase operation.\n",{"name":5,"description":7,"argument-hint":32},"[milestone] [--interactive] [--skip-codex] [--resume] [--complete]","main","83212e6d909b6a0fe9e93fd5a3ff1723300f5b5b",".claude\u002Fskills\u002Fgsd-milestone-sprint","https:\u002F\u002Fgithub.com\u002Fbaisharg\u002FASTN","https:\u002F\u002Fsafetytalent.org","https:\u002F\u002Fgithub.com\u002Fbaisharg","2026-11-13 01:54:27",{"source":8,"skillName":5,"commands":41,"prompt":51,"zipAvailable":52},[42,45,48],{"tool":43,"command":44},"npx","npx skills add baisharg\u002FASTN --skill \"gsd:milestone-sprint\"",{"tool":46,"command":47},"bunx","bunx skills add baisharg\u002FASTN --skill \"gsd:milestone-sprint\"",{"tool":49,"command":50},"pnpm","pnpm dlx skills add baisharg\u002FASTN --skill \"gsd:milestone-sprint\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbaisharg\u002FASTN\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fgsd-milestone-sprint\u002FSKILL.md",true,[54,60,66,70,74,78,82],{"path":55,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":58,"sourceHtmlUrl":59},"_meta.json","REFERENCE","参考文档",134,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fdefi\u002Fpump-mcp-server\u002F_meta.json",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fauto-discuss.sh","SCRIPT","脚本",14407,"https:\u002F\u002Fgithub.com\u002Fbaisharg\u002FASTN\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fgsd-milestone-sprint\u002Fscripts\u002Fauto-discuss.sh",{"path":67,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fmilestone-helpers.sh",17491,"https:\u002F\u002Fgithub.com\u002Fbaisharg\u002FASTN\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fgsd-milestone-sprint\u002Fscripts\u002Fmilestone-helpers.sh",{"path":71,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Fmilestone-sprint.sh",18946,"https:\u002F\u002Fgithub.com\u002Fbaisharg\u002FASTN\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fgsd-milestone-sprint\u002Fscripts\u002Fmilestone-sprint.sh",{"path":75,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":76,"sourceHtmlUrl":77},"skill-card.md",2396,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fdefi\u002Fpump-mcp-server\u002Fskill-card.md",{"path":79,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":80,"sourceHtmlUrl":81},"SOURCE.md",254,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fdefi\u002Fpump-mcp-server\u002FSOURCE.md",{"path":83,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":84,"sourceHtmlUrl":85},"TRUST.auto.yaml",2187,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fdefi\u002Fpump-mcp-server\u002FTRUST.auto.yaml",[87,109,123,137,149,166],{"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":98,"publishedAt":27},"01M6CCE5DVER8DQWJDY51HAJF7","schema-builder","Design and generate Convex database schemas with proper validation, indexes, and relationships. Use when creating schema.ts or modifying table definitions.","https:\u002F\u002Fgithub.com\u002Fbaisharg\u002FASTN\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fschema-builder\u002FSKILL.md",[93],{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",[99,100,101,102,103,104,105,106,22,107,108],"schema builder","schema","builder","table","indexes","design","convex","generate","database","use",{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":27},"01M6CCE36AA57CG36R4VHKFRXV","integration-tanstack-start","PostHog integration for TanStack Start full-stack applications","https:\u002F\u002Fgithub.com\u002Fbaisharg\u002FASTN\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fposthog-integration-tanstack-start\u002FSKILL.md",[],[116,117,118,119,120,121,122],"integration","start","tanstack","integration tanstack start","posthog","applications","stack",{"skillNo":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":129,"publishedAt":27},"01M6CCE0FK6N8XAB093X7TTQ4F","migration-helper","Plan and execute Convex schema migrations safely, including adding fields, creating tables, and data transformations. Use when schema changes affect existing data.","https:\u002F\u002Fgithub.com\u002Fbaisharg\u002FASTN\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fmigration-helper\u002FSKILL.md",[],[130,131,132,133,134,108,100,135,136,105],"migration","migration helper","data","plan","execute","migrations","schema migrations safely",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":143,"publishedAt":27},"01M6CCDY3644G8WXXP0BDNMZPR","gsd:sprint","Autonomous phase execution with Codex validation. Runs plan\u002Fexecute\u002Fverify cycles in a bash loop until done or halted.","https:\u002F\u002Fgithub.com\u002Fbaisharg\u002FASTN\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fgsd-sprint\u002FSKILL.md",[],[139,134,20,22,117,144,145,146,147,133,148,26],"execution","verify","Bash","loop","autonomous",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":155,"publishedAt":27},"01M6CCDVTZRTFWWGREMV6FF956","gsd:second-opinion","Get a second opinion from OpenAI Codex (GPT-5.2-codex) on code, architecture, or implementation decisions. Use when you want independent verification or an alternative perspective.","https:\u002F\u002Fgithub.com\u002Fbaisharg\u002FASTN\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fgsd-second-opinion\u002FSKILL.md",[],[156,157,158,20,159,160,161,162,163,164,165,108],"gsd:second opinion","second opinion","implementation","architecture","code","verification","openai","gpt","decisions","question",{"skillNo":167,"name":168,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":170,"categories":171,"keywords":175,"publishedAt":27},"01M6CCDQPC27AN5P984R46TRF7","gsd:health-check","Verify GSD setup - checks Claude, Codex, skills, and MCP servers are working correctly.","https:\u002F\u002Fgithub.com\u002Fbaisharg\u002FASTN\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fgsd-health-check\u002FSKILL.md",[172],{"categoryNo":173,"categoryName":174,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000023","Skill与智能体开发",[176,177,178,179,20,180,181,145,182],"gsd:health check","health check","check","health","setup","mcp servers","MCP"]