agent-project-board-sync

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

4.00x

Quality

25%

Does it follow best practices?

Impact

100%

4.00x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-project-board-sync/SKILL.md

Quality

Content

50%

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, command-heavy catalog of GitHub Projects integration features with decent section organization, but it is verbose with speculative sections and a generic best-practices list. Executability is undermined by malformed URLs/variables and likely invented subcommands, and it lacks validation checkpoints and real progressive disclosure.

Suggestions

Fix malformed strings (e.g. 'https:/$...' → 'https://...', '>$dev$null' → '>/dev/null', '.$swarm-issue.md' → './swarm-issue.md') and verify that the 'npx ruv-swarm github' subcommands actually exist.

Add explicit validation/verification steps around batch and destructive operations (board-bulk, cross-org-sync, board-recover).

Split the monolithic body into referenced bundle files under references/ with a concise overview in SKILL.md, or trim speculative sections to reduce token bloat.

Dimension	Reasoning	Score
Conciseness	The body is mostly concrete command examples rather than explanations of known concepts, but it is inflated with many speculative sections (multi-board sync, cross-org sync, Jira integration) and a generic best-practices list of Agile knowledge Claude already has ('Clear column definitions', 'Regular board grooming'), so it could be tightened.	2 / 3
Actionability	It provides many concrete-looking 'npx ruv-swarm github ...' commands, but several are malformed ('https:/$api.example.com$github-sync', 'https:/$github.com/$GITHUB_REPOSITORY$issues/$issue', '>$dev$null') and reference speculative subcommands, so they are not reliably copy-paste executable, fitting the score-2 'concrete guidance but incomplete / missing key details' anchor.	2 / 3
Workflow Clarity	The body is organized as a feature catalog with an implied init→sync→realtime sequence, but it has no explicit validation checkpoints, and batch/destructive operations (board-bulk, cross-org-sync, board-recover) lack verify steps, which caps workflow clarity at 2 per the batch-operations guideline.	2 / 3
Progressive Disclosure	Section headers provide structure, but ~510 lines of content sit inline in one monolithic file and the only external references use broken paths ('.$swarm-issue.md', '.$multi-repo-swarm.md') to nonexistent files with no bundle present, matching the score-2 anchor where content that should be separate is inline and references are not clearly signaled.	2 / 3
	Total	8 / 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 boilerplate placeholder that names only the skill slug and an invoke token, providing no real capabilities, natural trigger terms, or usage guidance. It fails every dimension because nothing concrete distinguishes it from any other agent skill.

Suggestions

Replace the placeholder with a concrete description of what the skill does, e.g. 'Synchronize AI swarms with GitHub Projects for visual task management, progress tracking, and team coordination.'

Add an explicit 'Use when...' clause naming natural trigger terms users would say (GitHub Projects, project board, task tracking, swarm coordination).

Drop the generic 'Agent skill for X - invoke with $X' template so the description is distinctive and written in third person.

Dimension	Reasoning	Score
Specificity	The description ('Agent skill for project-board-sync' / 'invoke with $agent-project-board-sync') names only the skill's own slug and a generic invoke instruction; no concrete capability actions such as syncing or tracking are stated, matching the vague 'Helps with documents' anchor rather than the score-2 anchor that requires 'some actions'.	1 / 3
Completeness	It states only that this is an agent skill to invoke; neither what it does nor when to use it is described, and there is no 'Use when...' trigger, so both 'what' and 'when' are very weak per the score-1 anchor.	1 / 3
Trigger Term Quality	It contains only the technical skill slug 'project-board-sync' and an invoke token, with no natural terms a user would actually say (e.g., 'GitHub Projects', 'project board', 'task management'), fitting the score-1 'technical jargon or overly generic' anchor.	1 / 3
Distinctiveness Conflict Risk	The 'Agent skill for X - invoke with $X' template is generic and structurally identical across agent skills, so it cannot distinguish this skill or prevent triggering the wrong one, matching the score-1 '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
Path: .agents/skills/agent-project-board-sync/SKILL.md
Commit: 26c35b5

Reviewed: about 7 hours 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.