agent-release-manager
Agent skill for release-manager - invoke with $agent-release-manager
Install with Tessl CLI
npx tessl i github:ruvnet/claude-flow --skill agent-release-manager31
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
0%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 functions only as an invocation reference ('invoke with $agent-release-manager') rather than a proper skill description. It provides zero information about capabilities, use cases, or trigger conditions that would help Claude select this skill appropriately.
Suggestions
Add concrete actions describing what release-manager does (e.g., 'Creates release notes, manages version bumps, generates changelogs, tags releases')
Add an explicit 'Use when...' clause with natural trigger terms (e.g., 'Use when the user mentions releases, versioning, changelogs, deployment preparation, or semantic versioning')
Remove the invocation syntax from the description field - this belongs elsewhere; the description should focus on capabilities and selection criteria
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for release-manager' is completely abstract with no indication of what the skill actually does. | 1 / 3 |
Completeness | Missing both 'what' and 'when'. The description only provides an invocation command but explains neither what the skill does nor when Claude should use it. | 1 / 3 |
Trigger Term Quality | The only potential trigger term is 'release-manager' which is technical jargon. No natural keywords users would say like 'release', 'deploy', 'version', 'changelog', etc. | 1 / 3 |
Distinctiveness Conflict Risk | While 'release-manager' sounds specific, without any description of capabilities, it's impossible to distinguish from other release, deployment, or versioning skills. | 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 poorly organized, containing over 300 lines of content that could be condensed to under 100. While it provides concrete tool usage patterns, the examples are more illustrative than executable, and the lack of explicit validation checkpoints in workflows is a significant gap for release management operations. The content would benefit greatly from splitting into a concise overview with references to detailed guides.
Suggestions
Reduce content by 70%+ by removing explanatory sections (Best Practices, Release Strategies, Monitoring) that describe concepts Claude already knows, keeping only the actionable tool invocation patterns
Split into SKILL.md (quick start + common patterns) with references to separate files: WORKFLOWS.md (detailed pipelines), CICD.md (GitHub Actions), EXAMPLES.md (full code samples)
Add explicit validation gates with failure handling: 'If npm test fails: stop pipeline, create issue with mcp__github__create_issue, do not proceed to PR creation'
Replace placeholder paths ($workspaces$ruv-FANN) with generic patterns or variables that Claude can adapt, making examples more directly usable
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive boilerplate, repeated patterns, and unnecessary detail. The skill contains massive code blocks that could be condensed significantly, and includes explanatory content Claude doesn't need (e.g., explaining what semantic versioning is, what rollback strategies are). | 1 / 3 |
Actionability | Provides concrete code examples with specific MCP tool calls and bash commands, but many examples use placeholder syntax (e.g., '$workspaces$ruv-FANN') and pseudocode-like JavaScript that isn't directly executable. The JSON.stringify patterns and template literals are illustrative rather than copy-paste ready. | 2 / 3 |
Workflow Clarity | Multi-step processes are shown but validation checkpoints are implicit rather than explicit. The 'Batch Release Workflow' shows a sequence but lacks clear 'if validation fails, do X' feedback loops. The TodoWrite at the end tracks status but doesn't integrate validation gates into the workflow. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. All content is inline including CI/CD examples, monitoring metrics, best practices, and multiple lengthy code blocks that could be split into separate reference documents. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
100%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.
- Reviewed
Table of Contents
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.