Name: agent-project-board-sync
Rating: 46.400000000000006 (1 reviews)
Author: ruvnet

Blog Docs Log in Get started

agent-project-board-sync

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

4.00x

Quality

18%

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

The canonical home for this skill is agent-project-board-sync in ruvnet/claude-flow

Quality

Content

25%Weight 40%Scale 1-5

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 exhaustive but non-executable command dump: malformed URLs/paths prevent copy-paste use, destructive and batch operations lack validation checkpoints, and nothing is split into reference files. It needs executable commands, a sequenced workflow with validation, and progressive disclosure.

Suggestions

Fix the malformed URLs and paths throughout (every '$' used as a path separator should be '/'), and verify each 'npx ruv-swarm github ...' subcommand actually exists before presenting it as executable.

Add an ordered quick-start workflow with explicit validation checkpoints (e.g. 'gh auth status' pre-check, dry-run before board-bulk/cross-org-sync, verify sync result before declaring done) for the destructive and batch operations.

Split the large reference material (full board-mapping YAML, view/dashboard configs, the analytics pipeline) into files under references/ and link to them from a concise SKILL.md overview; create the files referenced by the 'See also' links or remove those links.

Dimension	Reasoning	Score
Conciseness	The body is a ~470-line catalog of near-duplicate 'npx ruv-swarm github board-*' command blocks; while not conceptually over-explaining, the redundancy and volume make it noticeably padded and token-inefficient.	2 / 5
Actionability	Commands appear concrete but are not copy-paste executable: URLs and paths use a corrupted '$'-for-'/' substitution (e.g. 'https:/$api.example.com$github-sync', '.github$board-sync.yml', '.github.com$GITHUB_REPOSITORY$issues'), and several ruv-swarm/claude-flow subcommands are unverifiable.	2 / 5
Workflow Clarity	Features are grouped but there is no sequenced multi-step workflow with validation checkpoints, and destructive/batch operations (board-recover, cross-org-sync, board-bulk) lack validation; per the rubric cap this cannot exceed 3, and the rough-sequence-with-no-validation fit is closest to 2.	2 / 5
Progressive Disclosure	It is a single monolithic SKILL.md with no bundle files, content that belongs in separate reference files is inlined, and the inline 'See also' links point to nonexistent files (swarm-issue.md, multi-repo-swarm.md), matching 'content that clearly belongs in separate files is inlined'.	2 / 5
	Total	8 / 20 Passed

Description

12%Weight 40%Scale 1-5

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 fails to communicate what the skill does or when to use it, offering only a self-referential invocation token instead of capabilities or triggers. It needs to be rewritten as third-person capability + 'Use when...' guidance.

Suggestions

Replace the invocation hint with concrete third-person capabilities, e.g. 'Synchronizes AI swarm tasks with GitHub Projects, maps task statuses to board columns, and auto-assigns cards to agents'.

Add an explicit trigger clause: 'Use when coordinating swarm work on a GitHub Projects board, mapping task state to columns, or tracking agent workload visually.'

Drop the '$agent-project-board-sync' token from the description; move invocation mechanics out of the user-facing summary.

Dimension	Reasoning	Score
Specificity	The description ('Agent skill for project-board-sync - invoke with $agent-project-board-sync') names the domain but lists no concrete capabilities, only a self-referential invocation hint, matching 'names the domain but actions are minimal or generic'.	2 / 5
Completeness	It states neither a real 'what' (no capability description) nor any 'when to use it' clause; the text is a meta-reference to the skill itself, so both what and when are effectively absent.	1 / 5
Trigger Term Quality	No natural keywords a user would say appear; the only trigger language is an internal invocation token ('$agent-project-board-sync'), which is technical jargon rather than user phrasing.	1 / 5
Distinctiveness Conflict Risk	The 'project-board-sync' name token is fairly specific and unlikely to trigger unrelated skills, but the description carries no usable trigger language, leaving moderate overlap risk with other coordination/sync skills.	3 / 5
	Total	7 / 20 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/ruflo
Path: .agents/skills/agent-project-board-sync/SKILL.md
Commit: fa13ee4

Reviewed: about 8 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.