agent-project-board-sync

Agent skill for project-board-sync - invoke with $agent-project-board-sync

4.00x

Quality

—

Does it follow best practices?

Impact

100%

4.00x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

42%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is an extensive, mostly concrete command catalog for a ruv-swarm/GitHub Projects integration, but it is verbose, lacks an end-to-end workflow with validation checkpoints, contains broken URL/path syntax, and relies on dangling references to absent files. It is more of a feature dump than a focused, navigable skill.

Suggestions

Condense the repetitive ruv-swarm command stubs into a compact reference table and keep only a few full executable examples, moving the rest into a separate reference file.

Add a sequenced workflow (init -> sync -> validate -> handle conflicts) with explicit validation checkpoints and error-recovery feedback loops for the bidirectional sync and batch operations.

Fix the corrupted path/URL syntax (e.g. 'https:/$github.com/...', '>$dev$null') and either create the referenced swarm-issue.md / multi-repo-swarm.md files or remove the dangling links.

Dimension	Reasoning	Score
Conciseness	The ~470-line body enumerates dozens of near-identical 'npx ruv-swarm github board-*' command stubs with redundant flag listings, which is bloated, though it avoids explaining concepts Claude already knows, keeping it above score 1.	2 / 3
Actionability	It supplies many concrete, copy-pasteable commands with flags, but several contain broken placeholder syntax (e.g. 'https:/$github.com/...', '>$dev$null') and rely on an unverified 'ruv-swarm' CLI, so guidance is concrete yet incomplete, matching the 'some concrete guidance but incomplete' anchor.	2 / 3
Workflow Clarity	Content is organized as a feature catalog rather than a sequenced workflow, and the bidirectional sync / batch operations lack validation checkpoints or feedback loops; per the rubric, missing validation for risky batch operations caps this at 2.	2 / 3
Progressive Disclosure	No bundle files exist, the body is a monolithic wall of inline command listings that should be split out, and the only references (swarm-issue.md, multi-repo-swarm.md) point to non-existent files, matching the 'monolithic wall of text' anchor.	1 / 3
	Total	7 / 12 Passed

Description

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The frontmatter description is a templated, non-informative label that reuses the skill name and an internal invocation hint instead of describing capabilities or trigger conditions. It fails on every dimension because it conveys nothing a user or Claude could act on.

Suggestions

Replace the description with concrete actions, e.g. 'Synchronize AI swarm tasks with GitHub Projects boards, map task statuses to columns, and visualize agent workload and progress.'

Add an explicit trigger clause such as 'Use when managing GitHub Projects boards, syncing swarm task state, or tracking sprint/agent progress.'

Use third-person capability language and natural user terms (GitHub Projects, board, columns, cards) instead of the internal '$invoke' syntax.

Dimension	Reasoning	Score
Specificity	The description names only a domain ('project-board-sync') and offers no concrete actions or verbs describing what the skill does, matching the 'vague or no actions' anchor rather than score 2 which requires naming some actions.	1 / 3
Completeness	It restates the skill's name as its 'what' (circular) and provides no 'when'/'Use when' trigger guidance, so both what and when are very weak, matching the score 1 anchor; it cannot reach 2 because there is no actionable description of capability.	1 / 3
Trigger Term Quality	The only terms are the skill's own name and the internal '$invoke' syntax, which are machinery rather than natural phrases a user would say; no user-facing keywords like 'GitHub Projects' or 'board' appear, matching the 'no natural keywords; technical jargon' anchor.	1 / 3
Distinctiveness Conflict Risk	The generic 'Agent skill for X - invoke with $X' template would apply to virtually any skill and establishes no distinct niche, matching the 'very generic; would conflict with many skills' anchor.	1 / 3
	Total	4 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 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
relative_links	Relative link issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: ruvnet/claude-flow
Commit: 03d4f84

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.