agent-release-manager
Agent skill for release-manager - invoke with $agent-release-manager
40
13%
Does it follow best practices?
Impact
78%
2.51xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-release-manager/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is critically deficient across all dimensions. It provides no information about what the skill does, when it should be used, or what triggers should activate it. It reads more like a label than a description, making it nearly useless for skill selection among multiple options.
Suggestions
Add concrete actions the skill performs, e.g., 'Creates release branches, generates changelogs, bumps version numbers, tags releases, and manages deployment workflows.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about creating a release, cutting a new version, generating a changelog, tagging a release, or managing deployment pipelines.'
Remove the invocation syntax from the description (it's metadata, not a capability description) and replace with domain-specific keywords users would naturally use like 'release', 'version', 'changelog', 'deploy', 'tag'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. It only says 'Agent skill for release-manager' which is entirely vague about what the skill actually does. | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is answered. There is no description of capabilities and no 'Use when...' clause or equivalent trigger guidance. | 1 / 3 |
Trigger Term Quality | The only keyword is 'release-manager' which is somewhat relevant but there are no natural user terms like 'release', 'deploy', 'version bump', 'changelog', 'tag', etc. The invocation syntax '$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' alone provides minimal differentiation without specifying what kind of releases, what actions, or what context. | 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 tightly coupled to a specific repository (ruvnet/ruv-FANN) with hardcoded version numbers, paths, and PR templates, making it poorly generalizable. While it demonstrates a comprehensive release workflow concept, the content is bloated with inline templates and declarative data structures that explain concepts Claude already understands, rather than providing lean, actionable, reusable guidance. The lack of progressive disclosure and explicit error-recovery feedback loops further weakens its utility.
Suggestions
Extract the massive PR body template, CI/CD YAML, and batch workflow into separate reference files (e.g., TEMPLATES.md, CI_CD.md) and link to them from the main skill
Replace hardcoded repo names, version numbers, and paths with parameterized placeholders (e.g., `{owner}`, `{repo}`, `{version}`) to make the skill generalizable
Remove the declarative strategy objects (versionStrategy, validationStages, rollbackPlan) and replace with concrete executable steps or decision trees with explicit error-handling feedback loops
Cut the content by at least 50%—remove the Best Practices and Monitoring sections which describe concepts Claude already knows, and focus on the unique orchestration workflow
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~250+ lines with massive inline PR body templates, hardcoded version numbers (v1.0.72), repo-specific paths, and repetitive examples. Much of this is project-specific boilerplate that doesn't teach a generalizable skill. The semantic versioning strategy section explains concepts Claude already knows. | 1 / 3 |
Actionability | Provides concrete code examples with specific tool calls and commands, but they are pseudocode-like JavaScript that isn't directly executable (e.g., `mcp__claude-flow__swarm_init { topology: "hierarchical" }` syntax is ambiguous). Hardcoded to a specific repo (ruvnet/ruv-FANN) making it non-generalizable. The rollback and versioning strategy sections are purely declarative objects with no executable guidance. | 2 / 3 |
Workflow Clarity | The overall release pipeline sequence is present (branch → update → test → PR → review → merge), and the TodoWrite tracking is a nice touch. However, validation checkpoints are weak—tests are run but there's no explicit 'if tests fail, do X' feedback loop. The rollback strategy is described abstractly as a data structure rather than as actionable recovery steps. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with everything inline—massive PR body templates, CI/CD configs, strategy objects, and the complete batch workflow are all in a single file. No references to external files for detailed templates, examples, or configuration. The content would benefit enormously from splitting into separate reference files. | 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.
- Repository
- ruvnet/ruflo
- Commit
0f7c750
- 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.