agent-release-manager

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

2.51x

Quality

13%

Does it follow best practices?

Impact

78%

2.51x

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-manager/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 triggers should activate it. It reads more like a label than a description, making it nearly useless for skill selection among multiple options.

Suggestions

Add concrete actions the skill performs, e.g., 'Creates release branches, generates changelogs, bumps version numbers, tags releases, and manages release notes.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about creating a release, cutting a release branch, generating a changelog, bumping versions, or managing deployment workflows.'

Remove the invocation syntax ('$agent-release-manager') from the description and replace it with domain-specific keywords users would naturally use, such as 'release', 'version', 'changelog', 'tag', 'deploy'.

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. It only says 'Agent skill for release-manager' which is entirely vague about what the skill actually does.	1 / 3
Completeness	Neither 'what does this do' nor 'when should Claude use it' is answered. There is no explanation of capabilities and no 'Use when...' clause or equivalent trigger guidance.	1 / 3
Trigger Term Quality	The only potentially relevant term is 'release-manager', but there are no natural keywords a user would say like 'release', 'deploy', 'version bump', 'changelog', etc. The invocation syntax '$agent-release-manager' is technical jargon, not a natural trigger.	1 / 3
Distinctiveness Conflict Risk	The description is so vague that it's impossible to distinguish it from any other agent or release-related skill. 'Release-manager' hints at a domain but provides no specifics to differentiate it.	1 / 3
	Total	4 / 12 Passed

Implementation

27%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is excessively verbose and repo-specific, reading more like a release log for a particular project than a reusable skill. While it demonstrates the general shape of a release workflow with concrete tool calls, the hardcoded paths, version numbers, and massive inline templates severely limit its utility. The content would benefit enormously from being condensed to a concise workflow with parameterized examples and splitting detailed templates into separate referenced files.

Suggestions

Remove hardcoded repo names, version numbers, and paths — replace with parameterized placeholders (e.g., `{version}`, `{owner}`, `{repo}`) to make the skill reusable.

Move the large PR body template, CI/CD YAML config, and changelog template into separate referenced files (e.g., `PR_TEMPLATE.md`, `CI_CONFIG.md`) and link from the main skill.

Add explicit validation checkpoints with failure handling: 'If tests fail → stop release, create issue with failure details, do NOT proceed to PR creation.'

Cut the abstract strategy sections (Release Strategies, Monitoring and Metrics, Best Practices) which describe concepts Claude already knows — replace with a brief checklist of release-specific validation steps.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~250+ lines with massive inline PR body templates, hardcoded version numbers, repo-specific paths, and lengthy JSON/YAML examples that are not generalizable. Much of this is filler that Claude doesn't need — semantic versioning definitions, lists of monitoring metrics, and abstract strategy objects that describe rather than instruct.	1 / 3
Actionability	Contains concrete code examples with specific tool calls and bash commands, but they are heavily tied to a single repo (ruvnet/ruv-FANN) with hardcoded versions and paths, making them more like a release log than reusable instructions. The JavaScript-like pseudocode for MCP tool calls isn't truly executable — it uses a non-standard syntax that mixes JSON with JS comments.	2 / 3
Workflow Clarity	There is a sequential flow visible (create branch → update files → test → create PR → review → merge), and the TodoWrite section tracks stages. However, validation checkpoints are implicit rather than explicit — there's no clear 'if tests fail, do X' feedback loop, and the rollback strategy section is purely abstract with no concrete commands for recovery.	2 / 3
Progressive Disclosure	This is a monolithic wall of text with everything inlined — massive PR body templates, CI/CD YAML, strategy objects, monitoring metrics, and best practices all in one file. Nothing is split into referenced sub-files, and the content would greatly benefit from separating the PR template, CI config, and detailed examples into linked documents.	1 / 3
	Total	6 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/claude-flow
Commit: 322b2ae

Reviewed: 1 day 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.