[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6R7FCDN9AS7RSQFGZWHTF7F":3,"skill-same:01M6R7FCDN9AS7RSQFGZWHTF7F":75},{"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":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":53,"commitSha":54,"skillDirectory":55,"forksCount":56,"repositoryHtmlUrl":57,"repositoryHomepageUrl":6,"ownerHtmlUrl":58,"ownerBlogUrl":59,"ownerDescription":60,"updatedAt":61,"install":62,"resources":74},"01M6R7FCDN9AS7RSQFGZWHTF7F","breezing",null,"Use when running the full team\u002Fbreezing flow end-to-end — all tasks with parallel workers. Do NOT load for: single-task implementation, planning, review, release, or setup.","tim-hub\u002Fpowerball-harness","tim-hub","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F2884320?v=4","01M6R7B70M93Y25SH3DV1B4Q26","Tim","01M6R7B74YQWC556YVC0FRVS3T",35,"MIT","https:\u002F\u002Fgithub.com\u002Ftim-hub\u002Fpowerball-harness\u002Fblob\u002Fmaster\u002Fharness\u002Ftemplates\u002Fcodex-skills\u002Fbreezing\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37],"edit","running","when","single-task","mode","websearch","end","full","auto","review","write","read","parallel","Bash","team","flow","release","tasks","commit","2026-11-10 10:12:30",false,"---\nname: breezing\ndescription: \"Use when running the full team\u002Fbreezing flow end-to-end — all tasks with parallel workers. Do NOT load for: single-task implementation, planning, review, release, or setup.\"\nallowed-tools: [\"Read\", \"Write\", \"Edit\", \"Bash\", \"Grep\", \"Glob\", \"Task\", \"WebSearch\"]\nargument-hint: \"[all|N-M|--codex|--parallel N|--no-commit|--no-discuss|--auto-mode]\"\nuser-invocable: true\n---\n\n# Breezing — Team Execution Mode\n\n> **Backward-compatible alias**: Runs `harness-work` in team execution mode.\n\n## Quick Reference\n\n| User Input | Subcommand | Behavior |\n|------------|------------|----------|\n| `breezing` | _(none)_ | Ask for scope before executing |\n| `breezing all` | `all` | Complete all tasks in Plans.md |\n| `breezing 3-6` | `N-M` | Complete tasks 3 through 6 |\n| `breezing --codex all` | `--codex` | Complete all tasks via Codex CLI |\n| `breezing --parallel 2 all` | `--parallel N` | Complete all tasks with 2 parallel workers |\n| `breezing --no-commit all` | `--no-commit` | Complete all tasks, suppress automatic commits |\n| `breezing --no-discuss all` | `--no-discuss` | Complete all tasks, skipping planning discussion |\n| `breezing --auto-mode all` | `--auto-mode` | Try Auto Mode rollout on a compatible parent session |\n\n## Options\n\n| Option | Description | Default |\n|--------|-------------|---------|\n| `all` | Target all incomplete tasks | - |\n| `N` or `N-M` | Task number\u002Frange specification | - |\n| `--codex` | Delegate implementation to Codex CLI | false |\n| `--parallel N` | Number of parallel Implementers | auto |\n| `--no-commit` | Suppress automatic commits | false |\n| `--no-discuss` | Skip planning discussion | false |\n| `--auto-mode` | Explicitly opt in to Auto Mode rollout. Only considered when the parent session's permission mode is compatible | false |\n\n## Execution\n\n**This skill delegates to `harness-work`.** Run `harness-work` with the following settings:\n\n1. **Pass arguments directly to `harness-work`**\n2. **Force team execution mode** — Three-way separation: Lead → Worker spawn → Reviewer spawn\n3. **Lead focuses on delegation only** — Does not write code directly\n4. **Auto Mode is opt-in** — `--auto-mode` is accepted as a rollout flag for compatible parent sessions\n\n### Differences from `harness-work`\n\n| Aspect | `harness-work` | `breezing` (this skill) |\n|--------|-----------------|------------------------|\n| Parallelization | Automatic splitting based on need | **Lead\u002FWorker\u002FReviewer role separation** |\n| Lead's role | Coordination + implementation | **Delegation only (coordination focused)** |\n| Review | Lead self-review | **Independent Reviewer** |\n| Default scope | Next task | **All tasks** |\n\n### Team Composition\n\n| Role | Agent Type | Mode | Responsibility |\n|------|-----------|------|----------------|\n| Lead | (self) | - | Coordination, command, task distribution |\n| Worker xN | `harness:worker` | `bypassPermissions` (current) \u002F Auto Mode (follow-up)* | Implementation |\n| Reviewer | `harness:reviewer` | `bypassPermissions` (current) \u002F Auto Mode (follow-up)* | Independent review |\n\n> *If the parent session or frontmatter specifies `bypassPermissions`, that takes precedence. The distributed template currently uses `bypassPermissions`, so Auto Mode is a follow-up rollout target and not the default behavior.\n\n### Codex Mode (`--codex`)\n\nA mode that delegates all implementation to Codex CLI via the official plugin `codex-plugin-cc`:\n\n```bash\n# Task delegation (writable)\nbash \"${CLAUDE_SKILL_DIR}\u002F..\u002F..\u002Fscripts\u002Fcodex-companion.sh\" task --write \"task content\"\n\n# Via stdin (for large prompts)\nCODEX_PROMPT=$(mktemp \u002Ftmp\u002Fcodex-prompt-XXXXXX.md)\n# Write task content\ncat \"$CODEX_PROMPT\" | bash \"${CLAUDE_SKILL_DIR}\u002F..\u002F..\u002Fscripts\u002Fcodex-companion.sh\" task --write\nrm -f \"$CODEX_PROMPT\"\n```\n\n## Flow Summary\n\n```\nbreezing [scope] [--codex] [--parallel N] [--no-discuss] [--auto-mode]\n    │\n    ↓ Load harness-work with team mode\n    │\nPhase 0: Planning Discussion (skipped with --no-discuss)\nPhase A: Pre-delegate (team initialization)\nPhase B: Delegate (Worker implementation + Reviewer review)\nPhase C: Post-delegate (integration verification + Plans.md update + commit)\n```\n\n### Progress Feed (progress notifications during Phase B)\n\nThe Lead outputs progress in the following format each time a Worker completes a task:\n\n```\n? Progress: Task {completed}\u002F{total} done — \"{task_subject}\"\n```\n\n**Example output**:\n```\n? Progress: Task 1\u002F5 done — \"Add failure re-ticketing to harness-work\"\n? Progress: Task 2\u002F5 done — \"Add --snapshot to harness-sync\"\n? Progress: Task 3\u002F5 done — \"Add progress feed to breezing\"\n```\n\n> **Design intent**: Breezing often involves long-running execution.\n> This allows users to see \"how far along things are\" at a glance when checking the terminal.\n> The task-completed.sh hook outputs equivalent information via systemMessage, complementing the Lead's output.\n\n### Review Policy (unified across all modes)\n\nEven in Breezing mode, reviews follow the unified policy of **Codex exec first → internal Reviewer fallback**.\nSee the \"Review Loop\" section of `harness-work` for details.\n\n- Worker implements and commits within the worktree → returns results to Lead\n- Lead reviews via Codex exec (120s timeout, fallback: Reviewer agent)\n- REQUEST_CHANGES → Lead sends fix instructions to Worker via SendMessage, Worker amends (up to 3 times)\n- APPROVE → **Lead** cherry-picks to main → updates Plans.md to `cc:done [{hash}]`\n\n### Completion Report (Phase C — generated by Lead)\n\nAfter all tasks are complete, the **Lead** generates a rich completion report with the following steps:\n\n1. Collect all cherry-pick commits with `git log --oneline {base_ref}..HEAD`\n2. Get the overall change scope with `git diff --stat {base_ref}..HEAD`\n3. Extract remaining `cc:TODO` \u002F `cc:WIP` tasks from Plans.md\n4. Output according to the Breezing template in `harness-work`'s \"Completion Report Format\"\n\n> **The Lead generates this report**, not Workers or hooks. The Lead reads git + Plans.md during Phase C to produce it.\n\n### Phase 0: Planning Discussion (structured 3-question check)\n\nBefore executing all tasks, verify plan health with the following 3 questions.\nAll are skipped when `--no-discuss` is specified.\n\n**Q1. Scope confirmation**:\n> \"Executing {{N}} tasks. Is the scope appropriate?\"\n\nIf too many, suggest narrowing by priority (Required > Recommended > Optional).\n\n**Q2. Dependency confirmation** (only when Plans.md has a Depends column):\n> \"Task {{X}} depends on {{Y}}. Is the execution order correct?\"\n\nRead the Depends column and display the dependency chain. Error if circular dependencies exist.\n\n**Q3. Risk flag** (only when `[needs-spike]` tasks exist):\n> \"Task {{Z}} is [needs-spike]. Should we spike it first?\"\n\nIf there are incomplete `[needs-spike]` tasks, confirm whether to run the spike first.\n\nIf all 3 questions pass, proceed to Phase A (designed to complete in 30 seconds total).\n\n### Task Assignment Based on Dependency Graph\n\nWhen Plans.md has a Depends column (v2 format), tasks are executed following the dependency graph:\n\n1. Execute **tasks with Depends set to `-`** first. If multiple independent tasks exist, they can be spawned in parallel\n2. After each Worker completes, Lead reviews → cherry-picks (see harness-work Phase B)\n3. Once a dependency source task is cherry-picked to main, execute tasks that depended on it next\n4. Repeat until all tasks are complete\n\n> **Note**: The \"Worker complete → review → cherry-pick\" cycle for each task is sequential.\n> Only the Worker spawn portion of independent tasks (Depends is `-`) can be parallelized.\n\n## Codex Native Orchestration\n\nCodex uses native subagents.\nKey control surfaces are `spawn_agent`, `wait`, `send_input`, `resume_agent`, `close_agent`.\n\n> **Claude Code vs Codex communication API** (SSOT: API mapping table in `team-composition.md`):\n> - Claude Code: `SendMessage(to: agentId, message: \"...\")` to send fix instructions to Workers\n> - Codex: `resume_agent(agent_id)` to resume Workers → `send_input(agent_id, \"...\")` to send instructions\n>\n> Pseudo-code in harness-work is written in Claude Code syntax. Translate to the above when running in a Codex environment.\n\n## Related Skills\n\n- `harness-work` — From single tasks to team execution (core)\n- `harness-sync` — Progress synchronization\n- `harness-review` — Code review (auto-triggered within breezing)\n","# Breezing — Team Execution Mode\n\n> **Backward-compatible alias**: Runs `harness-work` in team execution mode.\n\n## Quick Reference\n\n| User Input | Subcommand | Behavior |\n|------------|------------|----------|\n| `breezing` | _(none)_ | Ask for scope before executing |\n| `breezing all` | `all` | Complete all tasks in Plans.md |\n| `breezing 3-6` | `N-M` | Complete tasks 3 through 6 |\n| `breezing --codex all` | `--codex` | Complete all tasks via Codex CLI |\n| `breezing --parallel 2 all` | `--parallel N` | Complete all tasks with 2 parallel workers |\n| `breezing --no-commit all` | `--no-commit` | Complete all tasks, suppress automatic commits |\n| `breezing --no-discuss all` | `--no-discuss` | Complete all tasks, skipping planning discussion |\n| `breezing --auto-mode all` | `--auto-mode` | Try Auto Mode rollout on a compatible parent session |\n\n## Options\n\n| Option | Description | Default |\n|--------|-------------|---------|\n| `all` | Target all incomplete tasks | - |\n| `N` or `N-M` | Task number\u002Frange specification | - |\n| `--codex` | Delegate implementation to Codex CLI | false |\n| `--parallel N` | Number of parallel Implementers | auto |\n| `--no-commit` | Suppress automatic commits | false |\n| `--no-discuss` | Skip planning discussion | false |\n| `--auto-mode` | Explicitly opt in to Auto Mode rollout. Only considered when the parent session's permission mode is compatible | false |\n\n## Execution\n\n**This skill delegates to `harness-work`.** Run `harness-work` with the following settings:\n\n1. **Pass arguments directly to `harness-work`**\n2. **Force team execution mode** — Three-way separation: Lead → Worker spawn → Reviewer spawn\n3. **Lead focuses on delegation only** — Does not write code directly\n4. **Auto Mode is opt-in** — `--auto-mode` is accepted as a rollout flag for compatible parent sessions\n\n### Differences from `harness-work`\n\n| Aspect | `harness-work` | `breezing` (this skill) |\n|--------|-----------------|------------------------|\n| Parallelization | Automatic splitting based on need | **Lead\u002FWorker\u002FReviewer role separation** |\n| Lead's role | Coordination + implementation | **Delegation only (coordination focused)** |\n| Review | Lead self-review | **Independent Reviewer** |\n| Default scope | Next task | **All tasks** |\n\n### Team Composition\n\n| Role | Agent Type | Mode | Responsibility |\n|------|-----------|------|----------------|\n| Lead | (self) | - | Coordination, command, task distribution |\n| Worker xN | `harness:worker` | `bypassPermissions` (current) \u002F Auto Mode (follow-up)* | Implementation |\n| Reviewer | `harness:reviewer` | `bypassPermissions` (current) \u002F Auto Mode (follow-up)* | Independent review |\n\n> *If the parent session or frontmatter specifies `bypassPermissions`, that takes precedence. The distributed template currently uses `bypassPermissions`, so Auto Mode is a follow-up rollout target and not the default behavior.\n\n### Codex Mode (`--codex`)\n\nA mode that delegates all implementation to Codex CLI via the official plugin `codex-plugin-cc`:\n\n```bash\n# Task delegation (writable)\nbash \"${CLAUDE_SKILL_DIR}\u002F..\u002F..\u002Fscripts\u002Fcodex-companion.sh\" task --write \"task content\"\n\n# Via stdin (for large prompts)\nCODEX_PROMPT=$(mktemp \u002Ftmp\u002Fcodex-prompt-XXXXXX.md)\n# Write task content\ncat \"$CODEX_PROMPT\" | bash \"${CLAUDE_SKILL_DIR}\u002F..\u002F..\u002Fscripts\u002Fcodex-companion.sh\" task --write\nrm -f \"$CODEX_PROMPT\"\n```\n\n## Flow Summary\n\n```\nbreezing [scope] [--codex] [--parallel N] [--no-discuss] [--auto-mode]\n    │\n    ↓ Load harness-work with team mode\n    │\nPhase 0: Planning Discussion (skipped with --no-discuss)\nPhase A: Pre-delegate (team initialization)\nPhase B: Delegate (Worker implementation + Reviewer review)\nPhase C: Post-delegate (integration verification + Plans.md update + commit)\n```\n\n### Progress Feed (progress notifications during Phase B)\n\nThe Lead outputs progress in the following format each time a Worker completes a task:\n\n```\n? Progress: Task {completed}\u002F{total} done — \"{task_subject}\"\n```\n\n**Example output**:\n```\n? Progress: Task 1\u002F5 done — \"Add failure re-ticketing to harness-work\"\n? Progress: Task 2\u002F5 done — \"Add --snapshot to harness-sync\"\n? Progress: Task 3\u002F5 done — \"Add progress feed to breezing\"\n```\n\n> **Design intent**: Breezing often involves long-running execution.\n> This allows users to see \"how far along things are\" at a glance when checking the terminal.\n> The task-completed.sh hook outputs equivalent information via systemMessage, complementing the Lead's output.\n\n### Review Policy (unified across all modes)\n\nEven in Breezing mode, reviews follow the unified policy of **Codex exec first → internal Reviewer fallback**.\nSee the \"Review Loop\" section of `harness-work` for details.\n\n- Worker implements and commits within the worktree → returns results to Lead\n- Lead reviews via Codex exec (120s timeout, fallback: Reviewer agent)\n- REQUEST_CHANGES → Lead sends fix instructions to Worker via SendMessage, Worker amends (up to 3 times)\n- APPROVE → **Lead** cherry-picks to main → updates Plans.md to `cc:done [{hash}]`\n\n### Completion Report (Phase C — generated by Lead)\n\nAfter all tasks are complete, the **Lead** generates a rich completion report with the following steps:\n\n1. Collect all cherry-pick commits with `git log --oneline {base_ref}..HEAD`\n2. Get the overall change scope with `git diff --stat {base_ref}..HEAD`\n3. Extract remaining `cc:TODO` \u002F `cc:WIP` tasks from Plans.md\n4. Output according to the Breezing template in `harness-work`'s \"Completion Report Format\"\n\n> **The Lead generates this report**, not Workers or hooks. The Lead reads git + Plans.md during Phase C to produce it.\n\n### Phase 0: Planning Discussion (structured 3-question check)\n\nBefore executing all tasks, verify plan health with the following 3 questions.\nAll are skipped when `--no-discuss` is specified.\n\n**Q1. Scope confirmation**:\n> \"Executing {{N}} tasks. Is the scope appropriate?\"\n\nIf too many, suggest narrowing by priority (Required > Recommended > Optional).\n\n**Q2. Dependency confirmation** (only when Plans.md has a Depends column):\n> \"Task {{X}} depends on {{Y}}. Is the execution order correct?\"\n\nRead the Depends column and display the dependency chain. Error if circular dependencies exist.\n\n**Q3. Risk flag** (only when `[needs-spike]` tasks exist):\n> \"Task {{Z}} is [needs-spike]. Should we spike it first?\"\n\nIf there are incomplete `[needs-spike]` tasks, confirm whether to run the spike first.\n\nIf all 3 questions pass, proceed to Phase A (designed to complete in 30 seconds total).\n\n### Task Assignment Based on Dependency Graph\n\nWhen Plans.md has a Depends column (v2 format), tasks are executed following the dependency graph:\n\n1. Execute **tasks with Depends set to `-`** first. If multiple independent tasks exist, they can be spawned in parallel\n2. After each Worker completes, Lead reviews → cherry-picks (see harness-work Phase B)\n3. Once a dependency source task is cherry-picked to main, execute tasks that depended on it next\n4. Repeat until all tasks are complete\n\n> **Note**: The \"Worker complete → review → cherry-pick\" cycle for each task is sequential.\n> Only the Worker spawn portion of independent tasks (Depends is `-`) can be parallelized.\n\n## Codex Native Orchestration\n\nCodex uses native subagents.\nKey control surfaces are `spawn_agent`, `wait`, `send_input`, `resume_agent`, `close_agent`.\n\n> **Claude Code vs Codex communication API** (SSOT: API mapping table in `team-composition.md`):\n> - Claude Code: `SendMessage(to: agentId, message: \"...\")` to send fix instructions to Workers\n> - Codex: `resume_agent(agent_id)` to resume Workers → `send_input(agent_id, \"...\")` to send instructions\n>\n> Pseudo-code in harness-work is written in Claude Code syntax. Translate to the above when running in a Codex environment.\n\n## Related Skills\n\n- `harness-work` — From single tasks to team execution (core)\n- `harness-sync` — Progress synchronization\n- `harness-review` — Code review (auto-triggered within breezing)\n",{"name":5,"description":7,"allowed-tools":43,"argument-hint":51,"user-invocable":52},[44,45,46,32,47,48,49,50],"Read","Write","Edit","Grep","Glob","Task","WebSearch","[all|N-M|--codex|--parallel N|--no-commit|--no-discuss|--auto-mode]",true,"master","cf086c6a667d37610d30a4236b94d8ab02e4efc5","harness\u002Ftemplates\u002Fcodex-skills\u002Fbreezing",0,"https:\u002F\u002Fgithub.com\u002Ftim-hub\u002Fpowerball-harness","https:\u002F\u002Fgithub.com\u002Ftim-hub","https:\u002F\u002Ftim.bai.uno","Building things.","2026-08-05 17:45:08",{"source":8,"skillName":5,"commands":63,"prompt":73,"zipAvailable":52},[64,67,70],{"tool":65,"command":66},"npx","npx skills add tim-hub\u002Fpowerball-harness --skill breezing",{"tool":68,"command":69},"bunx","bunx skills add tim-hub\u002Fpowerball-harness --skill breezing",{"tool":71,"command":72},"pnpm","pnpm dlx skills add tim-hub\u002Fpowerball-harness --skill breezing","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftim-hub\u002Fpowerball-harness\u002Fblob\u002Fmaster\u002Fharness\u002Ftemplates\u002Fcodex-skills\u002Fbreezing\u002FSKILL.md",[],[76,94,102,126,136,142],{"skillNo":77,"name":78,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":86,"publishedAt":38},"01M6R7GH70ABV40CS95W4WWMQZ","escape-skill","https:\u002F\u002Fgithub.com\u002Ftim-hub\u002Fpowerball-harness\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskills\u002Fzz-review-escape\u002FSKILL.md",[81],{"categoryNo":82,"categoryName":83,"taxonomyType":84,"taxonomyTypeDesc":85},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[87,88,89,90,91,92,93],"escape skill","escape","quoted","path","true","false","Tools",{"skillNo":95,"name":96,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":38},"01M6R7G8A2BQHYTAR39BY7X3GK","zz-review-empty","https:\u002F\u002Fgithub.com\u002Ftim-hub\u002Fpowerball-harness\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskills\u002Fzz-review-empty\u002FSKILL.md",[],[28,100,101,91,92],"zz review empty","empty",{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":109,"publishedAt":38},"01M6R7G3XH6C43JKP2RX1SZW6V","harness-schedule-run","Use when running Plans.md tasks on a scheduled cadence (fresh context per wake-up, sprint-contract flow, plateau detection, flock guard). Do NOT load for: single-task work (harness-work), planning, review, release.","https:\u002F\u002Fgithub.com\u002Ftim-hub\u002Fpowerball-harness\u002Fblob\u002Fmaster\u002Fharness\u002Ftemplates\u002Fopencode\u002Fskills\u002Fharness-schedule-run\u002FSKILL.md",[108],{"categoryNo":82,"categoryName":83,"taxonomyType":84,"taxonomyTypeDesc":85},[110,111,112,113,28,36,114,115,116,117,21,118,32,119,120,121,122,123,124,125],"run","harness schedule run","harness","schedule","ci","MCP","mem","wake","sprint-contract","scheduled","cadence","sprint","fresh","worker","up","work",{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":132,"publishedAt":38},"01M6R7FY3ZVYDDKXBT3D7QSFFK","harness-work","Use when implementing, executing, or running Plans.md tasks — single task, parallel workers, or full team\u002Fbreezing run. Accepts specific task numbers or ranges. Do NOT load for: planning, review, release, or setup.","https:\u002F\u002Fgithub.com\u002Ftim-hub\u002Fpowerball-harness\u002Fblob\u002Fmaster\u002Fharness\u002Ftemplates\u002Fcodex-skills\u002Fharness-work\u002FSKILL.md",[],[133,112,125,26,21,134,23,135,5,27,19,29,33,32,35,110,36,37,28,30],"harness work","implementing","number",{"skillNo":137,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":141,"publishedAt":38},"01M6R7FGP3R612506A5GKMBF5C","https:\u002F\u002Fgithub.com\u002Ftim-hub\u002Fpowerball-harness\u002Fblob\u002Fmaster\u002Fharness\u002Ftemplates\u002Fcodex-skills\u002Fharness-schedule-run\u002FSKILL.md",[140],{"categoryNo":82,"categoryName":83,"taxonomyType":84,"taxonomyTypeDesc":85},[111,112,110,113,28,115,36,119,21,118,117,120,121,122,123,116,124,125,32,114],{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":148,"publishedAt":38},"01M6R7F867HKSBNS7DDQ09ZE8H","maintenance","Periodic housekeeping and session lifecycle management. Use when performing cleanup, pruning, or session commands.","https:\u002F\u002Fgithub.com\u002Ftim-hub\u002Fpowerball-harness\u002Fblob\u002Fmaster\u002Fharness\u002Fskills\u002Fmaintenance\u002FSKILL.md",[],[144,19,21,91,149,150,151,152,153,154,29,30,155,32,156,157,158,159,160,161],"message","clean","worktrees","periodic","use","session","check","lifecycle","cache","inbox","state","cleanup","sessions"]