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

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-release-swarm/SKILL.md

Quality

Discovery

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 description is critically deficient across all dimensions. It provides no information about what the skill does, when it should be used, or what domain it operates in. It reads as a placeholder rather than a functional description, making it impossible for Claude to correctly select this skill from a pool of available skills.

Suggestions

Add concrete actions describing what 'release-swarm' actually does (e.g., 'Coordinates multi-agent release workflows, manages version bumps, generates changelogs, and publishes packages').

Add an explicit 'Use when...' clause with natural trigger terms (e.g., 'Use when the user needs to orchestrate a software release, publish a new version, or coordinate release tasks across multiple components').

Replace the invocation instruction ('invoke with $agent-release-swarm') with domain-specific keywords that distinguish this skill from other agent or release-related skills.

Dimension	Reasoning	Score
Specificity	The description provides no concrete actions whatsoever. 'Agent skill for release-swarm' 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 'release-swarm', which is a technical/internal name rather than a natural keyword a user would say. There are no natural language trigger terms.	1 / 3
Distinctiveness Conflict Risk	The description is so vague that it provides no distinguishing characteristics. 'Agent skill' is entirely generic and could apply to any agent-based skill.	1 / 3
	Total	4 / 12 Passed

Implementation

12%

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, largely aspirational document that describes a hypothetical release automation system rather than providing actionable instructions. The content is dominated by opaque `npx ruv-swarm` CLI calls that aren't real executable commands, making most of the skill non-actionable. The massive length (~400+ lines) with significant repetition across sections (rollback, changelog, deployment each appear multiple times) wastes token budget without adding proportional value.

Suggestions

Reduce content to under 100 lines by eliminating redundant sections (rollback appears 3+ times, changelog generation is repeated) and moving configuration examples, workflow templates, and integration examples to separate referenced files.

Replace hypothetical `npx ruv-swarm` commands with actual executable code using real tools (gh CLI, npm, docker) that Claude can run, or clearly document what ruv-swarm actually does and how to install it.

Fix path syntax errors throughout (e.g., `repos/:owner/:repo$compare` should use `/` not `$`) to make the gh CLI examples actually executable.

Add explicit validation checkpoints with concrete success/failure criteria between release steps, rather than delegating all validation to opaque CLI flags like `--block-on-failure`.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at 400+ lines with massive repetition. Many sections cover the same concepts (rollback appears 3+ times, changelog generation repeated). Includes template release notes, best practices lists, and integration examples that are largely redundant. Most commands are hypothetical `npx ruv-swarm` invocations that aren't real executable code, making the bulk of content low-value padding.	1 / 3
Actionability	Nearly all commands rely on `npx ruv-swarm github ...` which is a proprietary/hypothetical CLI tool with no documentation of actual behavior. The gh CLI snippets are more concrete but contain syntax errors (e.g., `repos/:owner/:repo$compare` uses `$` instead of `/`). Most code blocks are aspirational rather than executable — they describe what a tool would do rather than providing working commands Claude can run.	1 / 3
Workflow Clarity	The GitHub Actions workflow and release orchestration section do present a sequential flow (init → changelog → build → test → deploy → publish). However, validation checkpoints are weak — 'release-validate' is just another opaque CLI call with no feedback loop. The relationship between agents (changelog, version, build, test, deploy) and their sequencing is described but not clearly enforced with explicit validation gates.	2 / 3
Progressive Disclosure	Monolithic wall of text with no meaningful content separation. References to `workflow-automation.md` and `multi-repo-swarm.md` at the bottom, but no bundle files are provided. The YAML config, workflow files, agent descriptions, integration examples, emergency procedures, and best practices are all inlined in one massive file when they should be split across focused documents.	1 / 3
	Total	5 / 12 Passed

Validation

90%

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 — 10 / 11 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

	Total	10 / 11 Passed

Repository: ruvnet/claude-flow
Commit: e6dc21f

Reviewed: 4 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.