Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Beads Workflow

ASecurity

AI-native issue tracking with Beads. Use when managing work items, tracking issues, or coordinating tasks in multi-agent workflows. Covers bd commands, dependencies, and sync patterns.

34 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentsbashgitbackend

Works with

mcp

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add nguyenhuuca/assessment --skill beads-workflow --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Beads Workflow?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Beads Workflow
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/nguyenhuuca-beads-workflow/badge)](https://www.skillsdirectory.com/skills/nguyenhuuca-beads-workflow)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: beads-workflow
description: AI-native issue tracking with Beads. Use when managing work items, tracking issues, or coordinating tasks in multi-agent workflows. Covers bd commands, dependencies, and sync patterns.
allowed-tools: Read, Bash, Glob, Grep, mcp__github__*
---

# Beads Workflow

## Overview

Beads is an AI-native issue tracker designed for agent workflows. Issues live in your repo, sync via git, and require no web UI.

## MCP Tools

**GitHub** (remote collaboration):
- Link Beads issues to GitHub PRs
- Create GitHub issues for team visibility
- Track PR status for blocked work
- Auto-close Beads issues when PRs merge

## Core Commands

### Issue Management

```bash
# Create a new issue
bd create "Title" -t feature -p 2

# List open issues
bd list --status open

# View issue details
bd show <issue-id>

# Update issue
bd update <id> --status in_progress
bd update <id> --assignee claude

# Close issue
bd close <id> --reason "Completed: description"
```

### Finding Work

```bash
# Get unblocked issues (no dependencies blocking)
bd ready --sort hybrid

# Filter by priority
bd list --priority 1 --status open

# Filter by labels
bd list --label backend
```

### Dependencies

```bash
# Add dependency (X blocks Y)
bd dep add <blocking-id> <blocked-id> --type blocks

# View dependency tree
bd dep tree <id>

# Remove dependency
bd dep rm <blocking-id> <blocked-id>
```

### Syncing

```bash
# Sync with git remote
bd sync

# Force flush to JSONL
bd flush
```

## GitHub Integration Patterns

### Linking Issues to PRs

1. Create Beads issue: `bd create "Feature X"`
2. Implement and create PR via GitHub MCP
3. Reference Beads ID in PR description
4. When PR merges, close Beads issue: `bd close <id>`

### Syncing Status

```bash
# Check if related PR is merged (use GitHub MCP)
# Then update Beads status accordingly
bd update <id> --status done
```

### Team Visibility

For issues that need team visibility:
1. Create in Beads for local tracking
2. Use GitHub MCP to create corresponding GitHub issue
3. Link both in descriptions
4. Keep Beads as source of truth for agents

## Workflow Patterns

### Starting a Session

1. **Check ready work**: `bd ready --sort hybrid`
2. **Check GitHub**: Use GitHub MCP to verify no blocking PRs
3. **Claim an issue**: `bd update <id> --status in_progress`
4. **Review dependencies**: `bd dep tree <id>`
5. **Begin implementation**

### During Implementation

1. **Track sub-tasks**: `bd create "Sub-task" --parent <id>`
2. **Add blockers**: `bd dep add <new-blocker> <id> --type blocks`
3. **Update progress**: `bd comment <id> "Progress update"`
4. **Create PR**: Use GitHub MCP when ready

### Completing Work

1. **Verify completion**: All acceptance criteria met
2. **PR status**: Use GitHub MCP to check CI/review status
3. **Close issue**: `bd close <id> --reason "Implemented X, PR #123"`
4. **Sync**: `bd sync`
5. **Check next**: `bd ready`

### Multi-Agent Coordination

```bash
# See who's working on what
bd list --status in_progress --json | jq '.[] | {id, title, assignee}'

# Avoid conflicts - check before claiming
bd show <id>  # Check assignee field

# Hand off work
bd update <id> --assignee other-agent
bd comment <id> "Handoff: context and next steps"
```

## Issue Types

| Type | When to Use |
|------|-------------|
| `feature` | New functionality |
| `bug` | Defect fixes |
| `task` | General work items |
| `spike` | Research/investigation |
| `chore` | Maintenance, cleanup |

## Priority Levels

| Priority | Meaning |
|----------|---------|
| 0 | Critical - Drop everything |
| 1 | High - Next up |
| 2 | Medium - Normal flow |
| 3 | Low - When time permits |
| 4 | Backlog - Future consideration |

## Status Flow

```
open -> in_progress -> done
         |-> blocked -> in_progress
```

## Best Practices

1. **One issue per logical unit**: Don't combine unrelated work
2. **Clear titles**: Should explain what, not how
3. **Use dependencies**: Makes ready work visible
4. **Sync frequently**: Keep other agents informed
5. **Close promptly**: Don't leave stale in_progress issues
6. **Link to GitHub**: Create GitHub issues for team-visible work

## Integration with Swarm

When working in a swarm:

1. **Check active work**: `bd list --status in_progress`
2. **Claim before editing**: Update status before touching code
3. **Document blockers**: Create issues for discovered blockers
4. **Handoff cleanly**: Update assignee and add context
5. **Sync before ending**: `bd sync` to share state
6. **Create PRs**: Use GitHub MCP for review visibility

## Troubleshooting

```bash
# Check daemon health
bd daemons health

# View daemon logs
bd daemons logs

# Force reimport from JSONL
bd import --force

# Check for conflicts
bd sync --dry-run
```

Attribution

nguyenhuucanguyenhuuca
View sourceMore from nguyenhuuca →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693161 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →