beam-ai-team/beam-retry-tasks
skills/beam/beam-tools/beam-retry-tasks/SKILL.md
Retry failed Beam.ai tasks. Load when user says "retry tasks", "rerun failed tasks", "retry beam tasks", "resubmit tasks", or needs to re-execute failed agent tasks.
data-ai
Updated Apr 29, 2026
$ install --global
skillsauthnpx skillsauth add beam-ai-team/beam-next-skills beam-retry-tasksInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 29, 2026, 5:57 AM237.8s2 files scanned
SKILL.md
- name:
- beam-retry-tasks
- version:
- 1.0
- description:
- Retry failed Beam.ai tasks. Load when user says "retry tasks", "rerun
- author:
- Jack Li
- category:
- integrations
- platform:
- Beam AI
- updated:
- 2025-12-15
- visibility:
- public
Beam Retry Tasks
Retry failed or stopped Beam.ai tasks using the retry API.
When to Use
- Retry tasks that failed due to transient errors (API timeouts, 400/500 errors)
- Re-execute tasks after fixing underlying issues
- Batch retry multiple failed tasks from an agent
Prerequisites
.env file at project root:
# Beam.ai - BID instance (default)
BEAM_API_KEY=your_bid_api_key
BEAM_WORKSPACE_ID=your_bid_workspace_id
# Beam.ai - Production instance
BEAM_API_KEY_PROD=your_prod_api_key
BEAM_WORKSPACE_ID_PROD=your_prod_workspace_id
Dependencies: pip install requests python-dotenv
Quick Start
# Retry a single task
python 03-skills/beam-retry-tasks/scripts/retry_tasks.py --task-id <task_id>
# Retry all FAILED tasks from an agent (last 1 day)
python 03-skills/beam-retry-tasks/scripts/retry_tasks.py --agent <agent_id>
# Retry from JSON file (output from debug_issue_tasks.py)
python 03-skills/beam-retry-tasks/scripts/retry_tasks.py --file /tmp/failed_tasks.json
# Dry run (preview without executing)
python 03-skills/beam-retry-tasks/scripts/retry_tasks.py --agent <agent_id> --dry-run
Workspaces
| Workspace | API Endpoint | Default |
|-----------|--------------|---------|
| bid | api.bid.beamstudio.ai | Yes |
| prod | api.beamstudio.ai | No |
Retryable Statuses
By default, retries these statuses:
FAILED- Task execution failedERROR- Processing errorSTOPPED- Condition failedTIMEOUT- Execution timeout
Use --status to customize:
python retry_tasks.py --agent abc123 --status FAILED --status STOPPED
CLI Reference
| Flag | Description | Default |
|------|-------------|---------|
| --task-id, -t | Single task ID to retry | - |
| --agent, -a | Agent ID - retry all issue tasks | - |
| --file, -f | JSON file with task IDs | - |
| --status, -s | Status to include (repeatable) | FAILED, ERROR, STOPPED, TIMEOUT |
| --days, -d | Look back period (1,3,7,14,30) | 1 |
| --limit, -l | Max tasks to retry | 100 |
| --workspace, -w | Workspace: bid or prod | bid |
| --dry-run | Preview without executing | false |
| --delay | Delay between retries (seconds) | 0.2 |
| --output, -o | Save results to JSON file | - |
Input Formats
Single Task
python retry_tasks.py --task-id abc123-def456-...
From Agent
python retry_tasks.py --agent 455269b0-4d8d-4071-a8a0-6b07450462aa --days 7
From JSON File
Supports multiple formats:
Array of task objects:
[
{"task_id": "abc123", "custom_id": "INS-001"},
{"task_id": "def456", "custom_id": "INS-002"}
]
Array of strings:
["abc123", "def456", "ghi789"]
Example Output
Workspace: bid
API Base: https://api.bid.beamstudio.ai
Fetching FAILED, ERROR, STOPPED, TIMEOUT tasks from agent 455269b0...
Look back: 1 day(s)
Found 55 tasks to retry
============================================================
Retrying 55 tasks...
Started: 2025-12-15T09:22:31
[ 1/55] OK INS-29980 (0351632e...)
[ 2/55] OK INS-30137 (289bbb78...)
[ 3/55] OK INS-30138 (e5b5aa28...)
...
[ 55/55] OK INS-30298 (678327b2...)
============================================================
=== SUMMARY ===
Total tasks: 55
Successfully retried: 55
Failed to retry: 0
Integration with Debug Skill
Use with beam-debug-issue-tasks for a complete workflow:
# 1. Debug and identify failed tasks
python 03-skills/beam-debug-issue-tasks/scripts/debug_issue_tasks.py <agent_id> \
--days 7 --output /tmp/failed_tasks.json
# 2. Review the output
cat /tmp/failed_tasks.json
# 3. Retry all failed tasks
python 03-skills/beam-retry-tasks/scripts/retry_tasks.py \
--file /tmp/failed_tasks.json --output /tmp/retry_results.json
API Details
Uses Beam.ai retry endpoint:
- Endpoint:
POST /agent-tasks/retry - Body:
{"taskId": "<task_id>"} - Response: HTTP 201 (success, empty body)
Rate limiting: Built-in 0.2s delay between requests (configurable with --delay)
Retry logic: Automatically retries on 502, 503, 504 errors
Error Handling
| Error | Solution |
|-------|----------|
| BEAM_API_KEY not found | Add to .env file |
| 401 Unauthorized | Verify API key is valid |
| 404 Not Found | Task ID doesn't exist |
| 503 Service Unavailable | Transient error, will auto-retry |
Related Skills
beam-debug-issue-tasks- Find failed tasks and diagnose root causebeam-create-agent-task- Create new tasksbeam-list-agents- List available agents
Related Skills
beam-ai-team/skills/general/taste-skill
development
VerifiedTrustedCommunity
--- name: taste-skill type: skill version: '1.0' author: Leonxlnx (packaged by Zhichao Li) category: general tags: - frontend - design - anti-slop - landing-page updated: '2026-06-11' visibility: public description: Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check. license: MIT.
SKILL.mdUpdated Jun 12, 2026
beam-ai-team/numbers
development
VerifiedTrustedCommunity
Use when communicating quantitative information in any form — Slack updates, emails, reports, decks, dashboards, landing pages, product UI, public talks. Covers two integrated layers: (1) making numbers semantically meaningful (translation, anchoring, simplification, story-pairing) and (2) showing numbers cleanly (chart vs table vs prose, chart-by-message, pre-attentive emphasis, color discipline, decluttering). Distilled and integrated from *Show Me the Numbers* (Stephen Few) and *Make Numbers Count* (Chip Heath & Karla Starr). Not for raw data analysis or statistics — this is about communication of numbers, not their derivation.
SKILL.mdUpdated Jun 12, 2026
beam-ai-team/impeccable
development
VerifiedTrustedCommunity
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
SKILL.mdUpdated Jun 12, 2026
beam-ai-team/beam-teach
tools
VerifiedTrustedCommunity
Stateful multi-session tutor adapted for Beam — teach a stakeholder to understand, trust, and operate a specific agent, or teach a Solution Engineer a client's business process for delivery. Grounds every lesson in Knowledge Hub sources (real agent graphs, real tasks, transcripts, Linear) before any web resource. Also works for any general topic. Trigger on "teach me", "beam teach", "教我", "onboard <person> on <agent>", "help <stakeholder> understand the agent", "learn this client's process".
SKILL.mdUpdated Jun 12, 2026