An automated Openclaw Skills report generator that aggregates task outcomes into daily tenant reports, fairness metrics, and 30-day welcome-back summaries.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install completion-report-generator
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install completion-report-generator using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Completion Report Generator?
Completion Report Generator is an orchestration-layer Openclaw Skills component for producing daily completion analytics from task execution data. It runs through a 23:00 Cron trigger, aggregates completed, failed, and skipped tasks from the task_result table, calculates tenant-level completion rates, and records results in daily_completion_report.
The skill also supports returning users by generating WelcomeBackCard data from the previous 30 days, including historical totals, unresolved deferred tasks, and completion-rate recommendations. Optional notifications can be written to tenant_notification, while real-time queries remain outside this skill and should use task-dispatcher.
Completion Report Generator Use Cases
- Automatically generate a daily completion report at 23:00 through Cron.
- Give users returning after 30 days a concise WelcomeBackCard with historical progress and pending work.
- Help administrators compare tenant completion rates and monitor scheduling fairness.
- Summarize completed, failed, and skipped task outcomes for operational reporting.
- Trigger optional notifications when a P0 task fails.
- Produce safe fallback output when the database is unavailable, task data is empty, or aggregation exceeds 60 seconds.
How Completion Report Generator Works
- Receive a report request containing
report_dateand an optionaltenant_filter. - Query
task_resultfor the selected date and aggregate completed, failed, and skipped task counts. - Group task outcomes by tenant and calculate each tenant's completion rate.
- Read the fairness checkpoint from
fair_schedule_checkpointand calculate the Jain fairness index. - Write one or more records to
daily_completion_reportwith date, tenant, task totals, fairness, and notes. - Aggregate the most recent 30 days of daily reports for eligible returning users.
- Generate WelcomeBackCard data containing 30-day completion and failure totals, average completion rate, unresolved deferred tasks, and a recommendation.
- Apply recommendation bands: below 60% suggests additional allocation, 60–80% is considered normal, and above 80% is considered excellent.
- Optionally write notifications to
tenant_notification; P0 task failures are eligible for immediate delivery. - Return a structured success response with tenant totals, completion metrics, fairness data, and the number of generated welcome-back cards.
Completion Report Generator Setup
- Ensure Python is installed and the PostgreSQL connection string is available through the required
PG_DSNenvironment variable. - Place the
report_generator.pyexecution script in the skill's configured script location. - Configure the OpenClaw Cron scheduler to invoke
completion-report-generatordaily at 23:00. This skill has no declared package dependencies or additional configuration keys. - Configure database access before execution:
export PG_DSN="postgresql://user:password@host:5432/database"
- For a direct script-based smoke test, invoke the registered execution script with the runtime's supported input mechanism. The documented request payload is:
{
"report_date": "2026-07-08",
"tenant_filter": null
}
- Verify that the process can read
task_result,fair_schedule_checkpoint, and recentdaily_completion_reportdata, and can write report and optional notification records. - Do not use this skill for real-time task queries; route those requests to
task-dispatcherinstead.
Completion Report Generator Data Schema & Taxonomy
Input payload
| Field | Type | Description |
|---|---|---|
report_date |
date string | Date for the daily report, such as 2026-07-08. |
tenant_filter |
string or null | Optional tenant restriction; null processes all eligible tenants. |
Source and destination data
task_result: Source of daily task outcomes, including completed, failed, and skipped counts.fair_schedule_checkpoint: Source used to calculate the Jain fairness index.daily_completion_report: Durable daily report records.deferred_task: Source of unresolved tasks shown in WelcomeBackCard data.tenant_notification: Optional destination for report or urgent failure notifications.
Daily report fields
| Field | Description |
|---|---|
plan_date |
Date represented by the report. |
tenant_id |
Tenant associated with the metrics. |
total_tasks |
Total tasks considered for the tenant and date. |
completed_tasks |
Number of completed tasks. |
failed_tasks |
Number of failed tasks. |
skipped_tasks |
Number of skipped tasks. |
fairness_index |
Jain fairness index derived from scheduling data. |
note |
Status or exception marker such as no_data or partial. |
Output envelope
The result uses success, data, error, and code fields. The data section can include report_date, tenants_reported, total_completed, total_failed, average_completion_rate, fairness_index, and welcome_back_cards_generated.
Status markers and failure behavior
DB_NOT_CONNECTED: Returns a simulated report when the database cannot be reached.no_data: Produces an empty report when no task data exists.partial: Marks results when aggregation exceeds the 60-second timeout and only partial aggregation is available.
Completion Report Generator Advanced Features
- Tenant-level aggregation supports multi-tenant operational reporting and filtering.
- Jain fairness index reporting exposes scheduling fairness alongside completion performance.
- 30-day WelcomeBackCard generation combines historical metrics, recommendations, and unresolved deferred tasks.
- Recommendation logic automatically classifies completion performance into below 60%, 60–80%, and above 80% bands.
- Optional notification integration supports immediate handling of failed P0 tasks.
- Structured fallback responses preserve observability during database outages, empty datasets, and aggregation timeouts.
- Cross-platform metadata supports Windows, Linux, and macOS environments.
- The skill is protected as an R72.1 component, and its report data relies on the R72.2-protected
daily_completion_reporttable.
SKILL.md
Loading
Related Openclaw Skills
回译反思法 · 越南语翻译实战版
A rigorous 10-stage Chinese-Vietnamese translation workflow that combines terminology management, multi-model reflection, blind back-translation, and human review.
Contract Management
A template-driven contract management suite that routes legal requests to the right workflow, validates every output, and delivers traceable contract insights and documents.
Trade Alert — Crypto Trading Notifications
Trade Alert monitors real-time cryptocurrency markets and sends actionable price, risk, stop-loss, and take-profit notifications through Telegram.
Novel Writing SOP
A file-based AI writing workflow for planning, drafting, reviewing, and scaling original Chinese web novels.
Seedance 2.5 First-and-Last-Frame Video
Generate controlled Seedance 2.5 videos by defining the opening and closing frames, then automate media upload, task tracking, and result downloads.
Seedance 2.0 Discount Video Generation Channel
Create production-ready Seedance 2.0 videos from prompts and reference media with automated uploads, pricing checks, task tracking, and downloads.
Featured*
