agent-release-swarm

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

2.94x

Quality

28%

Does it follow best practices?

Impact

100%

2.94x

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-release-swarm/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, concrete catalog of release-automation commands and config, but it is verbose and repetitive, contains broken/non-executable syntax (corrupted '$' separators and placeholders), lacks explicit validation feedback loops in its workflows, and ships dangling references to files that do not exist.

Suggestions

Fix the corrupted path separators ('$' should be '/') throughout so commands and file paths are valid and copy-paste ready, and resolve placeholder tokens like ':owner/:repo'.

Tighten the body by consolidating the repetitive 'npx ruv-swarm github ...' agent/feature sections and moving detailed config and template content into reference files.

Weave explicit validate->fix->retry checkpoints into the Standard Release Flow and deploy steps, and remove or create the dangling references to '.$workflow-automation.md' and '.$multi-repo-swarm.md'.

Dimension	Reasoning	Score
Conciseness	The ~540-line body does not explain concepts Claude already knows (good), but it is padded with repetitive near-duplicate 'npx ruv-swarm github <subcommand> --flag' catalogs across many sections that could be consolidated, fitting the mostly-efficient-but-could-be-tightened anchor rather than the lean level 3.	2 / 3
Actionability	It provides many concrete bash commands, but they are not copy-paste ready: they contain unresolved placeholders (':owner/:repo', '$LAST_TAG') and corrupted path separators ('$' in place of '/', e.g. 'repos/:owner/:repo$compare'), matching the concrete-but-incomplete anchor rather than fully-executable level 3.	2 / 3
Workflow Clarity	The Standard Release Flow is sequenced (init, generate, upload, publish) and a Release Validation section exists, but validation is presented as a separate catalog rather than explicit validate->fix->retry checkpoints woven into the orchestration; for destructive release/deploy operations the guideline caps this at 2.	2 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets absent), yet the body ends with links to non-existent files ('.$workflow-automation.md', '.$multi-repo-swarm.md') with corrupted paths, and all content (config, workflows, agents, monitoring, examples) is inlined in one monolithic document, fitting the some-structure-but-inline anchor.	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 description is meta and non-functional: it identifies the skill and how to invoke it but never states what it does or when to use it. It fails on specificity, trigger quality, and completeness, and only marginally distinguishes itself via its niche name.

Suggestions

Rewrite the description to state concrete actions, e.g. 'Generate changelogs, bump versions, build multi-platform artifacts, and deploy releases 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 coordinating multi-platform deployment.'

Drop the invocation syntax ('$agent-release-swarm') from the description; it is not a natural trigger term and wastes the description's purpose.

Dimension	Reasoning	Score
Specificity	The description 'Agent skill for release-swarm - invoke with $agent-release-swarm' names no concrete actions at all; it only labels the artifact as a skill, matching the vague/no-actions anchor rather than the level-2 anchor that names a domain and some actions.	1 / 3
Completeness	It answers neither 'what does this do' (no capabilities stated) nor 'when should Claude use it' (no 'Use when...' clause); both halves are missing, matching the level-1 anchor and the guideline capping completeness when explicit trigger guidance is absent.	1 / 3
Trigger Term Quality	The only terms are 'release-swarm' and the invocation syntax '$agent-release-swarm'; these are technical invocation tokens, not natural phrases a user would say when they need release automation, fitting the no-natural-keywords anchor.	1 / 3
Distinctiveness Conflict Risk	The niche term 'release-swarm' gives it some specificity and a distinct name, but with no described triggers or capabilities it could still overlap with other release/CI skills, matching the somewhat-specific-but-could-overlap anchor rather than the clearly-distinct level 3.	2 / 3
	Total	5 / 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
Path: .agents/skills/agent-release-swarm/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.