vibe-kanban
Manage AI coding agents on a visual Kanban board. Run parallel agents through a To Do→In Progress→Review→Done flow with automatic git worktree isolation and GitHub PR creation.
80
72%
Does it follow best practices?
Impact
98%
2.13xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agent-skills/vibe-kanban/SKILL.mdQuality
Discovery
67%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description excels at specificity and distinctiveness, clearly articulating a unique capability around managing AI coding agents with Kanban workflows and git integration. However, it lacks explicit trigger guidance ('Use when...') which limits Claude's ability to know when to select this skill, and could benefit from more natural user-facing keywords.
Suggestions
Add a 'Use when...' clause with trigger scenarios like 'Use when the user wants to run multiple coding tasks in parallel, manage agent workflows, or coordinate automated development work'
Include natural trigger terms users might say such as 'parallel tasks', 'task board', 'agent workflow', 'multi-agent', or 'automated coding'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Manage AI coding agents', 'visual Kanban board', 'Run parallel agents', 'To Do→In Progress→Review→Done flow', 'automatic git worktree isolation', and 'GitHub PR creation'. | 3 / 3 |
Completeness | Clearly describes WHAT it does (manage agents on Kanban board with git/PR features), but lacks an explicit 'Use when...' clause to indicate WHEN Claude should select this skill. | 2 / 3 |
Trigger Term Quality | Contains some relevant keywords like 'Kanban board', 'agents', 'git worktree', 'GitHub PR', but missing common variations users might say like 'task board', 'parallel tasks', 'agent management', or 'workflow automation'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche combining Kanban boards, AI coding agents, git worktrees, and GitHub PRs - unlikely to conflict with other skills due to this specific combination. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill document with excellent executable examples and clear workflows. The main weaknesses are verbosity (repeated information, extensive version tables) and the monolithic structure that could benefit from moving detailed reference content to separate files. The troubleshooting section and quick reference are particularly strong.
Suggestions
Move the detailed 'Supported Agents' table, 'Representative Use Cases', and 'Architecture Overview' sections to separate reference files to reduce main document length
Remove duplicate information like the port conflict warning that appears in multiple places
Consider removing or condensing the 'Platform Support Status' table at the top since it's not essential for using the skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some unnecessary verbosity like the platform support table at the top, extensive version numbers, and repeated information (port conflict warning appears multiple times). Some sections could be tightened. | 2 / 3 |
Actionability | Excellent executable guidance throughout with copy-paste ready commands, complete JSON configs for MCP setup, specific CLI examples, and clear step-by-step workflows. Code examples are complete and runnable. | 3 / 3 |
Workflow Clarity | Clear multi-step workflows with explicit sequences (Create Workspace → Agent execution → Review → PR). Includes validation checkpoints, troubleshooting section with specific fixes, and clear state transitions (Running → Needs Attention → Archive). | 3 / 3 |
Progressive Disclosure | References external files (scripts/, references/, templates/) but the main document is quite long (~500 lines). Some content like the full architecture diagram and extensive use cases could be moved to separate reference files. The Quick Reference at the end is helpful but the document could benefit from better content splitting. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (621 lines); consider splitting into references/ and linking | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 9 / 11 Passed | |
- Repository
- supercent-io/skills-template
- Commit
c033769
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.