agent-release-swarm

Agent skill for release-swarm - invoke with $agent-release-swarm

2.94x

Quality

—

Does it follow best practices?

Impact

100%

2.94x

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 a sprawling reference catalog of release-automation commands that is actionable in intent but undermined by repeated content, broken command interpolation, missing validation checkpoints for risky operations, and a complete absence of progressive disclosure. It needs structural splitting and cleanup of its examples.

Suggestions

Break the monolithic body into separate reference files (e.g. agents.md, workflows.md, validation.md) and keep SKILL.md as a concise overview with clearly signaled one-level-deep links.

Fix the mangled path/interpolation syntax throughout (replace '$' with '/' in paths like '.github$release-swarm.yml' and 'repos/:owner/:repo$compare/') so examples are copy-paste-ready.

Add explicit validation/verification checkpoints to the deployment and rollback workflows (e.g. verify health metrics before promoting, confirm rollback target before executing).

Dimension	Reasoning	Score
Conciseness	The ~540-line body repeats the changelog-generation pattern across multiple sections and pads with generic best-practice platitudes ('Regular release cycles', 'Comprehensive CI/CD'); it avoids defining basic concepts but is far from lean and could be tightened considerably.	2 / 3
Actionability	It provides many concrete gh/ruv-swarm commands and YAML workflows, but numerous examples contain mangled interpolations (e.g. 'repos/:owner/:repo$compare/', '.github$release-swarm.yml', '$api$old-endpoint') that render them not copy-paste-ready and missing key details.	2 / 3
Workflow Clarity	The release process (plan -> version -> orchestrate -> validate -> deploy -> monitor -> rollback) is sequenced and a Standard Release Flow is laid out, but batch/destructive operations like deployment and rollback lack explicit validation checkpoints and feedback loops, capping this at 2.	2 / 3
Progressive Disclosure	It is a monolithic ~540-line wall of text with all content inline; the only references ('workflow-automation.md', 'multi-repo-swarm.md') point to nonexistent files via mangled paths (.$workflow-automation.md) and are not clearly signaled as navigation.	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 effectively placeholder text that names the skill and its invocation syntax but states nothing about its capabilities or when to use it. It fails on every dimension, offering no actionable or distinctive information.

Suggestions

Rewrite the description to list concrete capabilities, e.g. 'Orchestrate software releases by generating changelogs, bumping versions, building artifacts, and deploying across npm, Docker, and GitHub.'

Add an explicit trigger clause such as 'Use when planning or executing a software release, cutting a new version, or generating release notes and changelogs.'

Replace the invocation-syntax filler ('invoke with $agent-release-swarm') with natural user-facing terms like 'releases', 'deployment', and 'changelog'.

Dimension	Reasoning	Score
Specificity	The description 'Agent skill for release-swarm - invoke with $agent-release-swarm' names the domain but describes zero concrete actions (no mention of releases, changelogs, versioning, or deployment), matching the 'vague or no actions' anchor.	1 / 3
Completeness	Both 'what does this do' (barely 'Agent skill for release-swarm') and 'when to use it' are essentially missing, with no 'Use when...' clause, so it falls at the lowest anchor.	1 / 3
Trigger Term Quality	The only keyword is the invocation syntax '$agent-release-swarm', which is technical jargon rather than a natural term a user would say; common triggers like 'release', 'deploy', or 'changelog' are absent.	1 / 3
Distinctiveness Conflict Risk	'Agent skill for release-swarm' is generic scaffolding text with no distinguishable trigger, making it indistinguishable from other agent skills and prone to conflicting.	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 (588 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 2 missing, 1 suspicious	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.