agent-project-board-sync
Agent skill for project-board-sync - invoke with $agent-project-board-sync
35
0%
Does it follow best practices?
Impact
100%
4.00xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-project-board-sync/SKILL.mdQuality
Discovery
0%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 is an extremely weak description that provides virtually no useful information for skill selection. It only names the skill and its invocation command without describing any capabilities, use cases, or trigger conditions. It fails on every dimension of the rubric.
Suggestions
Describe the concrete actions the skill performs, e.g., 'Synchronizes tasks between project boards and external tools, updates card statuses, and maps columns across platforms.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks to sync project boards, update Trello/Jira cards, or keep task trackers in sync.'
Remove the invocation instruction ('invoke with $agent-project-board-sync') from the description and replace it with functional details that help Claude decide when to select this skill.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for project-board-sync' is entirely vague and does not describe what the skill actually does. | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is answered. The description only states it's an 'agent skill' and how to invoke it, providing no functional or contextual information. | 1 / 3 |
Trigger Term Quality | The only potentially relevant term is 'project-board-sync' which is a technical/internal identifier, not a natural keyword a user would say. No natural language trigger terms like 'project board', 'sync tasks', 'kanban', etc. are present. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague that it's impossible to distinguish it from other skills. 'Project-board-sync' hints at a domain but without any specifics, it could overlap with any project management or synchronization skill. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
0%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is an extremely verbose feature catalog for what appears to be a largely fictional CLI tool (ruv-swarm), with hundreds of lines of unverifiable commands. It lacks any clear workflow, validation steps, or practical guidance that Claude could actually execute. The content would need to be fundamentally restructured around real, executable commands (primarily gh CLI) with clear step-by-step workflows.
Suggestions
Replace fabricated 'npx ruv-swarm' commands with actual executable workflows using gh CLI, MCP tools listed in the frontmatter, and standard bash - verify every command actually works
Reduce content by 80%+ to focus on a single clear workflow: initialize board sync, map tasks, update status - with explicit validation at each step
Add a concrete sequential workflow with numbered steps, validation checkpoints (e.g., verify project exists, verify field creation succeeded), and error recovery paths
Move configuration examples, view configs, and advanced features into separate referenced files, keeping SKILL.md as a concise overview with quick-start instructions
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines covering dozens of features, most of which are CLI commands for a tool (ruv-swarm) that Claude cannot verify exists or works. Massive amounts of configuration examples, dashboard JSON, and repetitive command patterns that could be condensed dramatically. Explains concepts like board organization best practices that Claude already knows. | 1 / 3 |
Actionability | Nearly all commands reference 'npx ruv-swarm github ...' subcommands that appear fabricated or unverifiable - there's no evidence these CLI commands actually exist. The gh CLI commands are real but fragmented and incomplete. The skill reads like aspirational product documentation rather than executable guidance Claude can act on. | 1 / 3 |
Workflow Clarity | No clear sequential workflow with validation checkpoints. The content is organized as a feature catalog rather than a step-by-step process. There are no feedback loops, no error recovery steps, and no validation between steps. For a sync operation that could affect project state, this is a significant gap. | 1 / 3 |
Progressive Disclosure | Monolithic wall of content with no meaningful separation into referenced files. Everything is inline in one massive document. The two references at the bottom (swarm-issue.md, multi-repo-swarm.md) are minimal. The configuration examples, dashboard configs, and advanced features should be split into separate reference files. | 1 / 3 |
Total | 4 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (514 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- ruvnet/claude-flow
- Commit
f547cec
- 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.