ReddRadar
Agent skill
batch-report
Generate post-run analysis reports for batch processing jobs. Analyzes manifests, timings, and failures to produce comprehensive markdown reports. Optionally sends to agent-inbox for cross-project communication.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/batch-report
Metadata
Additional technical details for this skill
- short description
- Post-run batch analysis and reporting
SKILL.md
Batch Report Skill
Generate comprehensive analysis reports for completed batch processing jobs.
Features
- Manifest analysis - Count successes, failures, partial completions
- Timing breakdown - Per-step latency analysis, identify bottlenecks
- Failure patterns - Categorize and summarize failure modes
- Quality metrics - Sample outputs for quality assessment
- Markdown report - Human-readable summary
- Agent-inbox integration - Auto-send to project inbox
Quick Start
cd .pi/skills/batch-report
# Generate report for extractor batch (auto-detects format)
uv run python report.py analyze /path/to/batch/output
# Generate and send to agent-inbox
uv run python report.py analyze /path/to/batch/output --send-to extractor
# Just show summary stats
uv run python report.py summary /path/to/batch/output
# Analyze a standalone state file
uv run python report.py state /path/to/.batch_state.json
# JSON output for piping
uv run python report.py summary /path/to/output --json | jq .success_rate
Commands
analyze - Full analysis report
uv run python report.py analyze /path/to/output \
--output report.md \
--send-to extractor \
--priority high
Options:
| Option | Short | Description |
|---|---|---|
--output |
-o |
Output file path (default: stdout) |
--send-to |
-s |
Send report to agent-inbox project |
--priority |
-p |
Priority for agent-inbox (low/normal/high/critical) |
--sample |
-n |
Number of samples to include (default: 5) |
--format |
-f |
Batch format: extractor, youtube, generic, auto (default: auto) |
--json |
-j |
Output as JSON for piping to other tools |
summary - Quick stats only
uv run python report.py summary /path/to/output
uv run python report.py summary /path/to/output --json
Output:
Batch: run-2025-12-18_144426-2eb428c
Total: 230 | Success: 180 | Failed: 35 | Partial: 15
Success rate: 78.3%
Avg time: 4.2 min | Slowest: 09_section_summarizer (45%)
JSON Output:
{
"batch": "run-2025-12-18_144426-2eb428c",
"format": "extractor",
"total": 230,
"successful": 180,
"partial": 15,
"failed": 35,
"success_rate": 78.3,
"avg_time_min": 4.2
}
state - Analyze standalone state files
uv run python report.py state /path/to/.batch_state.json
uv run python report.py state /path/to/.batch_state.json --json
Works with any .batch_state.json file from any batch job.
failures - List failures with reasons
uv run python report.py failures /path/to/output
uv run python report.py failures /path/to/output --json
Report Format
# Batch Report: run-2025-12-18_144426-2eb428c
## Summary
- **Total items:** 230
- **Successful:** 180 (78.3%)
- **Failed:** 35 (15.2%)
- **Partial:** 15 (6.5%)
## Timing Analysis
| Step | Avg (s) | Max (s) | % of Total |
|------|---------|---------|------------|
| 09_section_summarizer | 120.5 | 341.0 | 45.2% |
| 05_table_extractor | 65.3 | 105.0 | 24.5% |
...
## Failure Patterns
| Pattern | Count | Example |
|---------|-------|---------|
| Empty text_content | 12 | 047ca6ef... |
| CUDA OOM | 5 | 9497a4e5... |
...
## Recommendations
1. Consider --text-only mode for knowledge extraction
2. Add table confidence threshold before VLM
...
Supported Batch Formats
The --format flag accepts: extractor, youtube, generic, or auto (default).
Auto-detect logic:
- If
*/manifest.jsonand*/timings_summary.jsonexist →extractor - If
.batch_state.jsonhas "transcript" in description →youtube - If
.batch_state.jsonexists →generic
Extractor batches
Expects:
*/manifest.json- Per-item manifests*/timings_summary.json- Timing data*/14_report_generator/json_output/final_report.json- Quality metricsfailed_urls.txt- Failed items list
YouTube transcript batches
Expects:
.batch_state.json- State file with transcript-related description
Generic batches
Expects:
.batch_state.json- State file with completed/failed counts*.logfiles for failure analysis (optional)
Integration with agent-inbox
# Send report as bug
uv run python report.py analyze /path/to/output \
--send-to extractor \
--priority high
# Message sent: extractor_abc123
Dependencies
dependencies = [
"typer",
"rich",
]
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?