// Deterministic field validation for task status transitions. Returns pass/fail with errors and warnings as JSON. Used by managing-tasks, executing-tasks, and running-daily-tasks.
Unified daily routine: ingests messages into tasks, then guides user through task refinement and dispatch. Works in both Claude Code and Cowork. Triggers on: "daily tasks", "daily routine", "run daily tasks", "デイリータスク", "日次ルーティン"
Generates or refines Acceptance Criteria and Execution Plans for tasks. Single task or batch mode. Ensures tasks are executable at agent-autonomous quality. Uses multi-round brainstorming to extract quality information from users. Triggers: "plan task", "refine task", "generate AC", "write execution plan", "plan all tasks", "auto-plan", "タスク計画", "AC作成", "実行計画作成", "タスクを計画して"
Delegates a task to another organization member by updating Assignees, resetting executor fields, and recording delegation history in Context. Triggers on: "delegate task", "assign to", "transfer task", "reassign", "タスク委任", "タスク移管", "割り当て変更"
Orchestrates autonomous task execution via current session, tmux parallel, or Cowork scheduled tasks. Fetches ready tasks, validates working directories, and dispatches to the chosen execution mode. Triggers on: "do the next task", "process tasks", "execute tasks", "ready tasks", "タスク実行", "次のタスクを実行", "タスク処理".
Performs a health check on tasks. Analyzes task age (stagnation), field completeness by status, blocked tasks (including other assignees' blockers), and executor ratio (human vs AI delegation). Supports 3 modes: specific assignee (by name), all tasks (team-wide overview), or defaults to current user when no target is specified. Use this skill whenever the user wants to monitor task health, check stagnation, audit task quality, or review AI delegation metrics — even if they don't say "monitor" explicitly. Triggers on: "monitor tasks", "task health check", "task analysis", "stagnation report", "task monitoring", "task report"
Reads incoming messages (Slack, Teams, Discord) addressed to the current user and auto-converts them into categorized Notion tasks (hearing-needed, self-action, or delegate). Designed for daily scheduled execution. Triggers on: "message intake", "intake", "process messages", "メッセージ取り込み", "メッセージ処理"
| name | validating-fields |
| description | Deterministic field validation for task status transitions. Returns pass/fail with errors and warnings as JSON. Used by managing-tasks, executing-tasks, and running-daily-tasks. |
| user-invocable | false |
This shared skill provides a deterministic bash+jq validation script for task status transitions. It enforces required fields as hard-block errors and recommends optional fields as warnings.
bash ${CLAUDE_PLUGIN_ROOT}/skills/validating-fields/scripts/validate-task-fields.sh \
<target_status> <task_json_file>
target_status: The status being transitioned TO (e.g., Ready, In Progress, Blocked, Done)task_json_file: Path to a JSON file containing a single Notion page object (full properties){
"valid": true,
"target_status": "Ready",
"errors": [],
"warnings": [
{"field": "Issuer", "rule": "recommended", "message": "Issuer is empty. Consider running backfill."}
]
}
valid: false → block the transition, present errors to uservalid: true with warnings → allow proceeding, present warnings to user.valid in the JSON output| Target Status | Required (errors) | Recommended (warnings) |
|---|---|---|
| Ready | Description (non-empty, ≥50 chars), AC (non-empty + semantic check), Execution Plan (non-empty) | Issuer (non-empty), Assignees (non-empty), Priority (set) |
| In Progress | All Ready requirements + Executor (set), Working Directory (non-empty for AI executors) | Issuer, Branch (for claude-code executor) |
| Blocked | Description (non-empty), AC (non-empty) | Issuer, Error Message |
| Done | Description (non-empty) | Agent Output (for AI executors) |
Issuer is always a warning, never an error — ensures backward compatibility with pre-migration tasks.
AC text is scanned for at least one verifiable condition indicator:
npm, curl, git, python, bash, test, run, build, deploy/ or common extensions (.ts, .js, .py, .md, .html, .css)%, ms, s, count, times, itemsreturns, displays, creates, exists, passes, fails, contains, shows, generates, sends, receives, confirms, records, updatesIf none found → error: "AC lacks verifiable conditions. Include commands, file paths, metrics, or observable outcomes."
This is a heuristic backstop, not a perfect quality gate. It catches worst-case garbage but not subtle gaps.